{"models":{"text":{"xingchen-agi/xing4.0-29b-a4b":{"name":"Xing 4.0 29B A4B","model":"xingchen-agi/xing4.0-29b-a4b","description":"China Telecom’s Xing 4.0 is an Apache 2.0 open-weight mixture-of-experts model with 29B total and 4B active parameters, designed for coding, reasoning and tool use. Supports text input, structured output and a shared 262,144-token input/output context. This route does not use a TEE.","totalParams":29,"activeParams":4,"cost":"Input $0.22/m, Cached input $0.011/m, Output $0.90/m","costEstimate":0.00056,"provider":"other","visible":true,"isOpenSource":true,"dateAdded":"2026-10-24","maxInputTokens":262144,"maxOutputTokens":262144,"category":"More","capabilities":["reasoning","tool-calling","parallel-tool-calls","structured-output"],"tags":["coding","reasoning","tools","long context"],"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high","xhigh","max"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1.05,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.2e-7,"output_price":9e-7,"input_price_per_million":0.22,"output_price_per_million":0.9,"input":0.22,"output":0.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000022","completion":"0.0000009","input":0.22,"output":0.9,"cacheReadInputPer1kTokens":0.000011,"prompt_per_million":0.22,"completion_per_million":0.9,"prompt_per_token":"0.00000022","completion_per_token":"0.0000009","per_input_token":2.2e-7,"per_output_token":9e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00022,"outputPer1kTokens":0.0009,"cacheReadInputPer1kTokens":0.000011},"effective_price":{"inputPer1kTokens":0.00022,"outputPer1kTokens":0.0009,"cacheReadInputPer1kTokens":0.000011},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.349Z"},"avgOutputTokens":663.6},"fireworks/ember-1":{"name":"Ember 1","model":"fireworks/ember-1","description":"Fireworks Research reasoning model built on Kimi K3. It accepts text and images, supports tool calling and structured output, and has a 1M-token context window.","cost":"Input $3/m, Cached input $0.30/m, Output $15/m","costEstimate":0.009,"provider":"fireworks","visible":true,"dateAdded":"2026-09-24","maxInputTokens":1048576,"category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"tags":["chat","reasoning","vision","tools","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"api":"chat","input_price":0.000003,"output_price":0.000015,"input_price_per_million":3,"output_price_per_million":15,"input":3,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000015","input":3,"output":15,"cacheReadInputPer1kTokens":0.0003,"prompt_per_million":3,"completion_per_million":15,"prompt_per_token":"0.000003","completion_per_token":"0.000015","per_input_token":0.000003,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.349Z"},"avgOutputTokens":3294.8},"stealth/space-bunny-alpha":{"name":"Space Bunny Alpha","model":"stealth/space-bunny-alpha","description":"Space Bunny Alpha is an anonymous stealth preview model for coding and multimodal tasks. It accepts text, images, and video, supports tool calling and structured output, and always reasons with adjustable effort across a 1M-token context window.","cost":"Input $0.05/m, Output $0.15/m","costEstimate":0.0001,"provider":"other","visible":true,"disabled":true,"dateAdded":"2026-09-23","maxInputTokens":1000000,"maxOutputTokens":524288,"category":"More","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"tags":["chat","vision","video","reasoning","coding","tools","long context","stealth preview"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"api":"chat","input_price":5e-8,"output_price":1.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.15,"input":0.05,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000015","input":0.05,"output":0.15,"prompt_per_million":0.05,"completion_per_million":0.15,"prompt_per_token":"0.00000005","completion_per_token":"0.00000015","per_input_token":5e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.349Z"}},"prism-ml/ternary-bonsai-2-9b":{"totalParams":9,"name":"Ternary Bonsai2 9B","model":"prism-ml/ternary-bonsai-2-9b","description":"Ternary Bonsai2 9B is Prism ML’s open-weight model derived from Qwen3.5-9B with ternary language weights. It accepts text and generates text, supports reasoning and tool calling, and offers a shared 262,144-token context window with up to 65,536 output tokens. Thinking is enabled by default and can be turned off.","cost":"Input $0.08/m, Cached input $0.04/m, Output $0.13/m","costEstimate":0.000105,"provider":"prism-ml","visible":true,"isOpenSource":true,"dateAdded":"2026-10-23","maxInputTokens":262144,"maxOutputTokens":65536,"category":"More","capabilities":["reasoning","tool-calling"],"tags":["chat","reasoning","tools","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":20,"topA":0,"frequencyPenalty":0,"presencePenalty":1,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning":{"enabled":true}},"api":"chat","input_price":8e-8,"output_price":1.3e-7,"input_price_per_million":0.08,"output_price_per_million":0.13,"input":0.08,"output":0.13,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000008","completion":"0.00000013","input":0.08,"output":0.13,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.08,"completion_per_million":0.13,"prompt_per_token":"0.00000008","completion_per_token":"0.00000013","per_input_token":8e-8,"per_output_token":1.3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00008,"outputPer1kTokens":0.00013,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.00008,"outputPer1kTokens":0.00013,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"},"avgOutputTokens":317},"prism-ml/ternary-bonsai-2-27b":{"totalParams":27,"name":"Ternary Bonsai 2 27B","model":"prism-ml/ternary-bonsai-2-27b","description":"Ternary Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.","cost":"Input $0.075/m, Output $0.50/m","costEstimate":0.0002875,"provider":"prism-ml","visible":true,"isOpenSource":true,"dateAdded":"2026-09-18","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"xhigh"},"additionalParams":{"reasoning_effort":{"levels":["medium","xhigh"]}},"tags":["chat","reasoning","coding","tools","multimodal","long context"],"api":"chat","input_price":7.5e-8,"output_price":5e-7,"input_price_per_million":0.075,"output_price_per_million":0.5,"input":0.075,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000075","completion":"0.0000005","input":0.075,"output":0.5,"prompt_per_million":0.075,"completion_per_million":0.5,"prompt_per_token":"0.000000075","completion_per_token":"0.0000005","per_input_token":7.5e-8,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"},"avgOutputTokens":464.7},"unbiased/pareto-26.10":{"name":"Pareto 26.10","model":"unbiased/pareto-26.10","description":"Pareto 26.10 is Unbiased AI's multimodal composite model for research, coding, and agentic workflows. It accepts text and images, supports tool calling, and provides a 1M-token context window with up to 131K output tokens. This is the stable release of Pareto 26.10. Tool selection is automatic; forced tool selection, structured output, and adjustable reasoning controls are not supported.","cost":"Input $0.80/m, Cached input $0.03/m, Output $3.20/m","costEstimate":0.002,"provider":"unbiased","visible":true,"isOpenSource":false,"dateAdded":"2026-10-01","maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","capabilities":["vision","tool-calling"],"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["multimodal","coding","agents","research","long context"],"api":"chat","input_price":8e-7,"output_price":0.0000032,"input_price_per_million":0.8,"output_price_per_million":3.2,"input":0.8,"output":3.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000008","completion":"0.0000032","input":0.8,"output":3.2,"cacheReadInputPer1kTokens":0.00003,"prompt_per_million":0.8,"completion_per_million":3.2,"prompt_per_token":"0.0000008","completion_per_token":"0.0000032","per_input_token":8e-7,"per_output_token":0.0000032},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0008,"outputPer1kTokens":0.0032,"cacheReadInputPer1kTokens":0.00003},"effective_price":{"inputPer1kTokens":0.0008,"outputPer1kTokens":0.0032,"cacheReadInputPer1kTokens":0.00003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"},"avgOutputTokens":346.3},"unbiased/pareto-26.9":{"name":"Pareto 26.9","model":"unbiased/pareto-26.9","description":"Pareto 26.9 is an experimental multimodal composite model from Unbiased AI for research, coding, agentic workflows, and general-purpose tasks. It runs several frontier and open models for each request and returns a single selected or synthesized answer. This experimental release supports text and image input, tool calling, a 262K-token context window, and up to 131K output tokens. Its underlying model mix and behavior may change as it is evaluated. Request content may be retained for abuse prevention and security monitoring for up to 30 days, and is not used for model training without explicit consent.","cost":"Input $2.50/m, Cached input $0.25/m, Output $7.50/m","costEstimate":0.00625,"provider":"unbiased","visible":true,"isOpenSource":false,"dateAdded":"2026-09-18","maxInputTokens":262144,"maxOutputTokens":131072,"category":"More","label":"Experimental","labelVariant":"outline","labelColor":"orange.4","capabilities":["vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["experimental","multimodal","coding","agents","research","long context"],"api":"chat","input_price":0.0000025,"output_price":0.0000075,"input_price_per_million":2.5,"output_price_per_million":7.5,"input":2.5,"output":7.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.0000075","input":2.5,"output":7.5,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":7.5,"prompt_per_token":"0.0000025","completion_per_token":"0.0000075","per_input_token":0.0000025,"per_output_token":0.0000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0075,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0075,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"},"avgOutputTokens":41.1},"slowburn/gemma4-31b-splituntied":{"totalParams":31,"name":"Gemma 4 31B Split-Untied","model":"google/gemma4-31b-splituntied","description":"Blazed-Forge's Split-Untied is a text-only Gemma 4 31B community finetune with an untied BF16 output head, built for creative writing, roleplay, expressive dialogue, and tool use.","cost":"Input $0.10/m, Output $0.30/m","costEstimate":0.0003,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-09-17","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","capabilities":["tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["chat","roleplay","creative writing","tools","long context"],"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"},"avgOutputTokens":317},"decision-large":{"name":"d3 (Decision Large)","model":"vllm-sr/decision-large","description":"vLLM Semantic Router’s d3 is the current 27B decision model for complex classification and policy judgments. Runs in an attested TEE (Trusted Execution Environment), with encrypted requests and attestation verified by NanoGPT. It evaluates text against predicate, choice and score questions and returns calibrated probabilities without generating text. Supports a 32,768-token context, up to 64 questions per request, and up to 26 choice options and 10 score levels. Text input only; reasoning, tools and streaming are unsupported. Use the native input and questions-array format through the Decisions API, or supported text questions through System One compatibility. The public ID decision-large is a mutable size alias, not an immutable checkpoint.","cost":"Input $0.40/m, Output free","costEstimate":0.0004,"label":"TEE","provider":"other","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-22","maxInputTokens":32768,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0,"input_price_per_million":0.4,"output_price_per_million":0,"input":0.4,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0","input":0.4,"output":0,"prompt_per_million":0.4,"completion_per_million":0,"prompt_per_token":"0.0000004","completion_per_token":"0","per_input_token":4e-7,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"decision-medium":{"name":"d3 Flash (Decision Medium)","model":"vllm-sr/decision-medium","description":"vLLM Semantic Router’s d3 Flash is the current 9B decision model for triage, routing and policy evaluation. Runs in an attested TEE (Trusted Execution Environment), with encrypted requests and attestation verified by NanoGPT. It evaluates text against predicate, choice and score questions and returns calibrated probabilities without generating text. Supports a 32,768-token context, up to 64 questions per request, and up to 26 choice options and 10 score levels. Text input only; reasoning, tools and streaming are unsupported. Use the native input and questions-array format through the Decisions API, or supported text questions through System One compatibility. The public ID decision-medium is a mutable size alias, not an immutable checkpoint.","cost":"Input $0.06/m, Output free","costEstimate":0.000059999999999999995,"label":"TEE","provider":"other","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-22","maxInputTokens":32768,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-8,"output_price":0,"input_price_per_million":0.06,"output_price_per_million":0,"input":0.06,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000006","completion":"0","input":0.06,"output":0,"prompt_per_million":0.06,"completion_per_million":0,"prompt_per_token":"0.00000006","completion_per_token":"0","per_input_token":6e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"decision-small":{"name":"d3 Mini (Decision Small)","model":"vllm-sr/decision-small","description":"vLLM Semantic Router’s d3 Mini is the current 4B decision model for fast first-pass classification and high-volume routing. Runs in an attested TEE (Trusted Execution Environment), with encrypted requests and attestation verified by NanoGPT. It evaluates text against predicate, choice and score questions and returns calibrated probabilities without generating text. Supports a 32,768-token context, up to 64 questions per request, and up to 26 choice options and 10 score levels. Text input only; reasoning, tools and streaming are unsupported. Use the native input and questions-array format through the Decisions API, or supported text questions through System One compatibility. The public ID decision-small is a mutable size alias, not an immutable checkpoint.","cost":"Input $0.02/m, Output free","costEstimate":0.00002,"label":"TEE","provider":"other","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-22","maxInputTokens":32768,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-8,"output_price":0,"input_price_per_million":0.02,"output_price_per_million":0,"input":0.02,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000002","completion":"0","input":0.02,"output":0,"prompt_per_million":0.02,"completion_per_million":0,"prompt_per_token":"0.00000002","completion_per_token":"0","per_input_token":2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"jaredpalmer/kev-4b":{"name":"Kev 4B TEE","model":"jaredpalmer/kev-4b","description":"Redpill lists Kev 4B as running on Phala in a TDX-attested TEE (Trusted Execution Environment). NanoGPT does not currently enforce attestation or verify signed receipts for this route. Jared Palmer's Kev 4B scores typed Choice, Score and Noul questions about text or JSON state in one forward pass, returning decisions and probabilities without generating text. Based on Qwen3.5-4B-Base with Apache 2.0 weights, it supports English and an 8,192-token context. Use /v1/decisions or /api/v1/systemone, or a questions response format through Chat Completions, Messages or Responses. Choice and Score support 1–255 options or levels. Input, including cached input, costs $0.042 per million tokens; output usage is free.","cost":"Input $0.042/m, Output free","costEstimate":0.000042,"provider":"other","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-13","maxInputTokens":8192,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.2e-8,"output_price":0,"input_price_per_million":0.042,"output_price_per_million":0,"input":0.042,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000042","completion":"0","input":0.042,"output":0,"cacheReadInputPer1kTokens":0.000042,"prompt_per_million":0.042,"completion_per_million":0,"prompt_per_token":"0.000000042","completion_per_token":"0","per_input_token":4.2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0,"cacheReadInputPer1kTokens":0.000042},"effective_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0,"cacheReadInputPer1kTokens":0.000042},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"llmtech/decider-0.8b-fp8":{"name":"Decider 0.8B FP8","model":"llmtech/decider-0.8b-fp8","description":"Mapika's Decider, quantized and hosted by LLM Tech, answers typed Choice, Score and Noul questions about application state. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It returns probabilities and decisions without generating text; only input tokens are billed.","cost":"Input $0.02/m, Output free","costEstimate":0.00002,"provider":"llmtech","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-01","maxInputTokens":32768,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-8,"output_price":0,"input_price_per_million":0.02,"output_price_per_million":0,"input":0.02,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000002","completion":"0","input":0.02,"output":0,"prompt_per_million":0.02,"completion_per_million":0,"prompt_per_token":"0.00000002","completion_per_token":"0","per_input_token":2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"llmtech/decider-2b-fp8":{"name":"Decider 2B FP8","model":"llmtech/decider-2b-fp8","description":"Mapika's Decider, quantized and hosted by LLM Tech, answers typed Choice, Score and Noul questions about application state. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It returns probabilities and decisions without generating text; only input tokens are billed.","cost":"Input $0.03/m, Output free","costEstimate":0.000029999999999999997,"provider":"llmtech","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-01","maxInputTokens":32768,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-8,"output_price":0,"input_price_per_million":0.03,"output_price_per_million":0,"input":0.03,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0","input":0.03,"output":0,"prompt_per_million":0.03,"completion_per_million":0,"prompt_per_token":"0.00000003","completion_per_token":"0","per_input_token":3e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"llmtech/decider-4b-nvfp4":{"name":"Decider 4B NVFP4","model":"llmtech/decider-4b-nvfp4","description":"Mapika's Decider, quantized and hosted by LLM Tech, answers typed Choice, Score and Noul questions about application state. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It returns probabilities and decisions without generating text; only input tokens are billed.","cost":"Input $0.04/m, Output free","costEstimate":0.00004,"provider":"llmtech","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-01","maxInputTokens":32768,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-8,"output_price":0,"input_price_per_million":0.04,"output_price_per_million":0,"input":0.04,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000004","completion":"0","input":0.04,"output":0,"prompt_per_million":0.04,"completion_per_million":0,"prompt_per_token":"0.00000004","completion_per_token":"0","per_input_token":4e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"perplexity/pplx-decider-v1.2":{"name":"PPLX Decider v1.2","model":"perplexity/pplx-decider-v1.2","description":"Perplexity's 27B decision model, succeeding PPLX Decider v1.1 with the same API contract; requests for perplexity/pplx-decider-v1.1-27b now run on v1.2. Typed Choice, Score and Noul decisions. Use /v1/decisions or /v1/systemone; text-only questions compatibility is available through Chat Completions, Messages and Responses. Accepts inline images through the Perplexity endpoint. The local image limit is four images, each at most 512 by 512 pixels. Input tokens are billed; output is free.","cost":"Input $0.02/m, Output free","costEstimate":0.00002,"provider":"perplexity","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-20","maxInputTokens":262144,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-8,"output_price":0,"input_price_per_million":0.02,"output_price_per_million":0,"input":0.02,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000002","completion":"0","input":0.02,"output":0,"prompt_per_million":0.02,"completion_per_million":0,"prompt_per_token":"0.00000002","completion_per_token":"0","per_input_token":2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"cloudflare/clef":{"name":"Clef","model":"cloudflare/clef","description":"Typed Choice, Score and Noul decisions. Use /v1/decisions or /v1/systemone; text-only questions compatibility is available through Chat Completions, Messages and Responses. Accepts inline images. Text admission is limited to 1,800 estimated tokens to avoid truncation; up to four images, each at most 512 by 512 pixels. Input tokens are billed; output is free.","cost":"Input $0.24/m, Output free","costEstimate":0.00024,"provider":"cloudflare","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-08","maxInputTokens":1800,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.4e-7,"output_price":0,"input_price_per_million":0.24,"output_price_per_million":0,"input":0.24,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000024","completion":"0","input":0.24,"output":0,"prompt_per_million":0.24,"completion_per_million":0,"prompt_per_token":"0.00000024","completion_per_token":"0","per_input_token":2.4e-7,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00024,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00024,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"cloudflare/clef-omni":{"name":"Clef Omni","model":"cloudflare/clef-omni","description":"Typed Choice, Score and Noul decisions about text, inline images and one PCM16 WAV audio clip up to 10 seconds. Use /v1/decisions or /v1/systemone. Up to four 512x512 images; image and audio bytes share a 512 KiB base64 / 384 KiB decoded limit. Text admission is limited to 1,800 estimated tokens including questions. Video is not enabled. No ZDR, audio moderation or media redaction. Compatibility APIs accept text only. Actual input tokens are billed; output is free.","cost":"Input $0.15/m, Output free","costEstimate":0.00015,"provider":"cloudflare","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-14","maxInputTokens":1800,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","audio","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":0,"input_price_per_million":0.15,"output_price_per_million":0,"input":0.15,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0","input":0.15,"output":0,"prompt_per_million":0.15,"completion_per_million":0,"prompt_per_token":"0.00000015","completion_per_token":"0","per_input_token":1.5e-7,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"cloudflare/clef-flash":{"name":"Clef Flash","model":"cloudflare/clef-flash","description":"Typed Choice, Score and Noul decisions. Use /v1/decisions or /v1/systemone; text-only questions compatibility is available through Chat Completions, Messages and Responses. Accepts inline images. Text admission is limited to 1,800 estimated tokens to avoid truncation; up to four images, each at most 512 by 512 pixels. Input tokens are billed; output is free.","cost":"Input $0.09/m, Output free","costEstimate":0.00009,"provider":"cloudflare","visible":true,"apiOnly":true,"isOpenSource":true,"dateAdded":"2026-10-08","maxInputTokens":1800,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":9e-8,"output_price":0,"input_price_per_million":0.09,"output_price_per_million":0,"input":0.09,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000009","completion":"0","input":0.09,"output":0,"prompt_per_million":0.09,"completion_per_million":0,"prompt_per_token":"0.00000009","completion_per_token":"0","per_input_token":9e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00009,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00009,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"openai/gpt-6-luna-decisions":{"name":"GPT-6 Luna Decisions","model":"openai/gpt-6-luna-decisions","description":"Typed Choice, Score and Noul decisions about text, JSON or inline images for classification, routing and scoring. Use /v1/decisions or /v1/systemone; text-only questions compatibility is available through Chat Completions, Messages and Responses. Uses OpenAI’s native Decisions API. Input tokens are billed; output is free.","cost":"Input $0.10/m ($0.20/m above 272K), Output free","costEstimate":0.0001,"provider":"openai","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-08","maxInputTokens":1050000,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":0,"input_price_per_million":0.1,"output_price_per_million":0,"input":0.1,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0","input":0.1,"output":0,"prompt_per_million":0.1,"completion_per_million":0,"prompt_per_token":"0.0000001","completion_per_token":"0","per_input_token":1e-7,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0,"highContextThresholdTokens":272000},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0,"highContextThresholdTokens":272000},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"eu-jev/eu-jeff-1.0.0":{"name":"eu/jev Jeff 1.0.0","model":"eu-jev/eu-jeff-1.0.0","description":"Bevel's Winnow-12B fine-tune for Choice, Noul and Score decisions, with inference in Germany. Use /v1/decisions or /v1/systemone, or the typed questions format through Chat Completions, Messages and Responses. Supports text and JSON, eight questions per request, up to 64 Choice options, and 2–10 Score levels. Output is free. The latest ID follows new releases; version 1.0.0 is pinned. USD pricing uses a fixed conversion of the provider's EUR tariff. Personal data requires a DPA with the provider.","cost":"Input $0.0416435/m, Output free","costEstimate":0.0000416435,"provider":"eujev","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-16","maxInputTokens":32768,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output","EU"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.1644e-8,"output_price":0,"input_price_per_million":0.041644,"output_price_per_million":0,"input":0.041644,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000041644","completion":"0","input":0.041644,"output":0,"prompt_per_million":0.041644,"completion_per_million":0,"prompt_per_token":"0.000000041644","completion_per_token":"0","per_input_token":4.1644e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000416435,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.0000416435,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"eu-jev/eu-jeff-latest":{"name":"eu/jev Jeff Latest","model":"eu-jev/eu-jeff-latest","description":"Bevel's Winnow-12B fine-tune for Choice, Noul and Score decisions, with inference in Germany. Use /v1/decisions or /v1/systemone, or the typed questions format through Chat Completions, Messages and Responses. Supports text and JSON, eight questions per request, up to 64 Choice options, and 2–10 Score levels. Output is free. The latest ID follows new releases; version 1.0.0 is pinned. USD pricing uses a fixed conversion of the provider's EUR tariff. Personal data requires a DPA with the provider.","cost":"Input $0.0416435/m, Output free","costEstimate":0.0000416435,"provider":"eujev","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-16","maxInputTokens":32768,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output","EU"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.1644e-8,"output_price":0,"input_price_per_million":0.041644,"output_price_per_million":0,"input":0.041644,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000041644","completion":"0","input":0.041644,"output":0,"prompt_per_million":0.041644,"completion_per_million":0,"prompt_per_token":"0.000000041644","completion_per_token":"0","per_input_token":4.1644e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000416435,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.0000416435,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"subq/subq-snap-1.1":{"name":"SubQ Snap 1.1","model":"subq/subq-snap-1.1","description":"Subquadratic's long-context decision model returns typed Choice, Score and Noul answers with probabilities. Use /v1/decisions or /v1/systemone; text-only questions compatibility is available through Chat Completions, Messages and Responses. Accepts text, JSON and up to four inline images, each at most 512 by 512 pixels. Included in subscriptions at the regular input-token rate. Only input tokens are billed; output is free.","cost":"Input $0.04/m, Output free","costEstimate":0.00004,"provider":"subq","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-23","maxInputTokens":384000,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output","preview"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-8,"output_price":0,"input_price_per_million":0.04,"output_price_per_million":0,"input":0.04,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000004","completion":"0","input":0.04,"output":0,"prompt_per_million":0.04,"completion_per_million":0,"prompt_per_token":"0.00000004","completion_per_token":"0","per_input_token":4e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"subq/subq-snap-preview":{"name":"SubQ Snap Preview","model":"subq/subq-snap-preview","description":"Subquadratic's long-context decision model returns typed Choice, Score and Noul answers with probabilities. Use /v1/decisions or /v1/systemone; text-only questions compatibility is available through Chat Completions, Messages and Responses. Accepts text, JSON and up to four inline images, each at most 512 by 512 pixels. Only input tokens are billed; output is free.","cost":"Input $0.05/m, Output free","costEstimate":0.00005,"provider":"subq","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-13","maxInputTokens":384000,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output","preview"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":0,"input_price_per_million":0.05,"output_price_per_million":0,"input":0.05,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0","input":0.05,"output":0,"prompt_per_million":0.05,"completion_per_million":0,"prompt_per_token":"0.00000005","completion_per_token":"0","per_input_token":5e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"liquid/d1":{"name":"Liquid D1","model":"liquid/d1","description":"Liquid AI's D1 evaluates application state and returns typed Choice, Score and yes/no answers with calibrated probabilities. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It supports a 65,536-token context and generates no text tokens; only input tokens are billed.","cost":"Input $0.04/m, Output free","costEstimate":0.00004,"provider":"liquid","visible":true,"apiOnly":true,"isOpenSource":false,"dateAdded":"2026-10-02","maxInputTokens":65536,"maxOutputTokens":0,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-8,"output_price":0,"input_price_per_million":0.04,"output_price_per_million":0,"input":0.04,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000004","completion":"0","input":0.04,"output":0,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.04,"completion_per_million":0,"prompt_per_token":"0.00000004","completion_per_token":"0","per_input_token":4e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"typesafe/jev-1.13":{"name":"Jev 1.13","model":"typesafe/jev-1.13","description":"TypeSafe's Jev 1.13 is a System One decision model for routing, classification, scoring, and other application decision points. Use /v1/decisions directly, point the official TypeSafe SDK at the /api base URL for /api/v1/systemone compatibility, or pass a questions response format through Chat Completions, Messages, or Responses; Jev returns typed answers with calibrated probabilities instead of generated text.","cost":"Input $0.042/m, Output free","costEstimate":0.000013,"provider":"typesafe","visible":true,"apiOnly":true,"dateAdded":"2026-09-18","maxInputTokens":32000,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.2e-8,"output_price":0,"input_price_per_million":0.042,"output_price_per_million":0,"input":0.042,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000042","completion":"0","input":0.042,"output":0,"prompt_per_million":0.042,"completion_per_million":0,"prompt_per_token":"0.000000042","completion_per_token":"0","per_input_token":4.2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"typesafe/jev-1.14":{"name":"Jev 1.14","model":"typesafe/jev-1.14","description":"TypeSafe's Jev 1.14 (jev-1.14.0) returns typed decisions for routing, classification, scoring, and yes/no judgments, with improved multilingual performance. Use /v1/decisions, TypeSafe SDK compatibility through /api/v1/systemone, or a questions response format through Chat Completions, Messages, or Responses. Text and JSON input only on this route, with 64k tokens per request and 32k per question. Experimental images, Box localization, and extended context are not enabled.","cost":"Input $0.042/m, Output free","costEstimate":0.000013,"provider":"typesafe","visible":true,"apiOnly":true,"dateAdded":"2026-10-15","maxInputTokens":64000,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output","multilingual"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.2e-8,"output_price":0,"input_price_per_million":0.042,"output_price_per_million":0,"input":0.042,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000042","completion":"0","input":0.042,"output":0,"prompt_per_million":0.042,"completion_per_million":0,"prompt_per_token":"0.000000042","completion_per_token":"0","per_input_token":4.2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"~typesafe/jev-latest":{"name":"Jev Latest","model":"typesafe/jev-latest","description":"An alias that routes to the latest TypeSafe Jev System One decision model. Use /v1/decisions directly, point the official TypeSafe SDK at the /api base URL for /api/v1/systemone compatibility, or pass a questions response format through Chat Completions, Messages, or Responses; Jev returns typed answers with calibrated probabilities instead of generated text.","cost":"Input $0.042/m, Output free","costEstimate":0.000013,"provider":"typesafe","visible":true,"apiOnly":true,"dateAdded":"2026-09-18","maxInputTokens":32000,"outputModalities":["decisions"],"category":"Decisions","toolCallingUnsupported":true,"tags":["decisions","classification","scoring","routing","structured output","latest"],"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.2e-8,"output_price":0,"input_price_per_million":0.042,"output_price_per_million":0,"input":0.042,"output":0,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000042","completion":"0","input":0.042,"output":0,"prompt_per_million":0.042,"completion_per_million":0,"prompt_per_token":"0.000000042","completion_per_token":"0","per_input_token":4.2e-8,"per_output_token":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000042,"outputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"inference-net/schematron-v2-small":{"name":"Schematron V2 Small","model":"inference-net/schematron-v2-small","description":"Inference.net's 3B-parameter HTML-to-JSON extraction model, focused on accuracy for complex schemas and long web pages. It turns HTML into typed, structured data for web scraping and product catalog ingestion, with a 128K-token context window. Supply HTML in the user message and extraction instructions in a JSON schema via response_format; it does not follow ordinary chat or system prompts.","cost":"Input $0.05/m, Output $0.23/m","costEstimate":0.00014,"provider":"inference-net","visible":true,"apiOnly":true,"dateAdded":"2026-09-12","totalParams":3,"maxInputTokens":128000,"maxOutputTokens":4096,"category":"More","capabilities":["structured-output"],"toolCallingUnsupported":true,"tags":["data extraction","web scraping","HTML","JSON","structured output","long context"],"defaultSettings":{"stream":true,"temperature":0,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":2.3e-7,"input_price_per_million":0.05,"output_price_per_million":0.23,"input":0.05,"output":0.23,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000023","input":0.05,"output":0.23,"prompt_per_million":0.05,"completion_per_million":0.23,"prompt_per_token":"0.00000005","completion_per_token":"0.00000023","per_input_token":5e-8,"per_output_token":2.3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00023},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00023},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"inference-net/schematron-v2-turbo":{"name":"Schematron V2 Turbo","model":"inference-net/schematron-v2-turbo","description":"Inference.net's 3B-parameter HTML-to-JSON extraction model, optimized for throughput and low cost on high-volume workloads. It turns HTML into typed, structured data for web scraping and product catalog ingestion, with a 128K-token context window. Supply HTML in the user message and extraction instructions in a JSON schema via response_format; it does not follow ordinary chat or system prompts.","cost":"Input $0.03/m, Output $0.15/m","costEstimate":0.00009,"provider":"inference-net","visible":true,"apiOnly":true,"dateAdded":"2026-09-12","totalParams":3,"maxInputTokens":128000,"maxOutputTokens":8192,"category":"More","capabilities":["structured-output"],"toolCallingUnsupported":true,"tags":["data extraction","web scraping","HTML","JSON","structured output","long context"],"defaultSettings":{"stream":true,"temperature":0,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-8,"output_price":1.5e-7,"input_price_per_million":0.03,"output_price_per_million":0.15,"input":0.03,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0.00000015","input":0.03,"output":0.15,"prompt_per_million":0.03,"completion_per_million":0.15,"prompt_per_token":"0.00000003","completion_per_token":"0.00000015","per_input_token":3e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.350Z"}},"mistralai/mistral-small-24b-instruct-2501":{"name":"Mistral Small 3 24B (2501)","model":"mistralai/mistral-small-24b-instruct-2501","description":"Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.","cost":"Usage-based","costEstimate":0.000462,"provider":"mistral","visible":true,"isOpenSource":true,"dateAdded":"2026-09-10","maxInputTokens":32768,"maxOutputTokens":8192,"category":"More","capabilities":["tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.155e-7,"output_price":3.465e-7,"input_price_per_million":0.1155,"output_price_per_million":0.3465,"input":0.1155,"output":0.3465,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001155","completion":"0.0000003465","input":0.1155,"output":0.3465,"prompt_per_million":0.1155,"completion_per_million":0.3465,"prompt_per_token":"0.0000001155","completion_per_token":"0.0000003465","per_input_token":1.155e-7,"per_output_token":3.465e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001155,"outputPer1kTokens":0.0003465},"effective_price":{"inputPer1kTokens":0.0001155,"outputPer1kTokens":0.0003465},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":402.6},"lightonai/LightOnOCR-2-1B":{"name":"LightOnOCR 2","model":"lightonai/LightOnOCR-2-1B","description":"LightOnOCR 2 hosted by IONOS in Berlin, Germany. Zero data retention.","cost":"Usage-based","costEstimate":0.0005250000000000001,"provider":"other","visible":true,"isOpenSource":true,"dateAdded":"2026-09-10","maxInputTokens":32768,"maxOutputTokens":8192,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.785e-7,"output_price":3.465e-7,"input_price_per_million":0.1785,"output_price_per_million":0.3465,"input":0.1785,"output":0.3465,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001785","completion":"0.0000003465","input":0.1785,"output":0.3465,"prompt_per_million":0.1785,"completion_per_million":0.3465,"prompt_per_token":"0.0000001785","completion_per_token":"0.0000003465","per_input_token":1.785e-7,"per_output_token":3.465e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001785,"outputPer1kTokens":0.0003465},"effective_price":{"inputPer1kTokens":0.0001785,"outputPer1kTokens":0.0003465},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":3792.5},"meta/muse-wonder":{"name":"Muse Wonder","model":"meta/muse-wonder","description":"Meta's Muse Wonder is a frontier reasoning model designed for complex personal and professional agentic tasks. It accepts text, images, audio, video, and PDF documents across a one-million-token context window, supports tool calling and structured output, and always reasons before answering.","cost":"Input $4/m, Cached input $0.20/m, Output $20/m","costEstimate":0.011,"provider":"meta","visible":true,"dateAdded":"2026-10-12","maxInputTokens":1048576,"maxImageInputs":50,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh","max"]}},"tags":["chat","reasoning","coding","agents","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000004,"output_price":0.00002,"input_price_per_million":4,"output_price_per_million":20,"input":4,"output":20,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000004","completion":"0.00002","input":4,"output":20,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":4,"completion_per_million":20,"prompt_per_token":"0.000004","completion_per_token":"0.00002","per_input_token":0.000004,"per_output_token":0.00002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1193.3},"meta/muse-spark-open":{"name":"Muse Spark Open","model":"meta/muse-spark-open","description":"Built with Muse Spark Open. Meta's open-weight 816B-A42B model for coding and agentic workflows. Text and image input, text output, tool calling and structured output. Always reasons at low, medium, high, or xhigh effort. Custom Muse Model License and Usage Policy apply.","totalParams":816,"activeParams":42,"provider":"meta","isOpenSource":false,"visible":true,"disabled":false,"dateAdded":"2026-10-15","maxInputTokens":1048576,"cost":"Input $1.25/m, Cached input $0.15/m, Output $4.25/m","costEstimate":0.00275,"category":"More","label":"Built with Muse Spark Open","capabilities":["reasoning","vision","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]}},"defaultThinkingEnabled":true,"defaultReasoningEffort":"medium","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"api":"chat","input_price":0.00000125,"output_price":0.00000425,"input_price_per_million":1.25,"output_price_per_million":4.25,"input":1.25,"output":4.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00000425","input":1.25,"output":4.25,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":1.25,"completion_per_million":4.25,"prompt_per_token":"0.00000125","completion_per_token":"0.00000425","per_input_token":0.00000125,"per_output_token":0.00000425},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1266.7},"meta/muse-spark-1.3":{"name":"Muse Spark 1.3","model":"meta/muse-spark-1.3","description":"Meta's Muse Spark 1.3 is a frontier multimodal reasoning model for long-horizon coding and agentic workflows, with strong gains in computer use, browsing, professional tool use, codebase understanding, instruction following, and million-token retrieval. It accepts text, images, audio, video, and files, supports tool calling and structured output, and always reasons before answering.","cost":"Input $1.25/m, Cached input $0.15/m, Output $4.25/m","costEstimate":0.00275,"provider":"meta","visible":true,"dateAdded":"2026-09-02","maxInputTokens":1048576,"maxImageInputs":50,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","coding","agents","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00000125,"output_price":0.00000425,"input_price_per_million":1.25,"output_price_per_million":4.25,"input":1.25,"output":4.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00000425","input":1.25,"output":4.25,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":1.25,"completion_per_million":4.25,"prompt_per_token":"0.00000125","completion_per_token":"0.00000425","per_input_token":0.00000125,"per_output_token":0.00000425},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1246.1},"meta/muse-spark-1.3-contributor":{"name":"Muse Spark 1.3 Contributor","model":"meta/muse-spark-1.3-contributor","description":"Meta's Muse Spark 1.3 Contributor is a frontier multimodal reasoning model for long-horizon coding and agentic workflows, with strong gains in computer use, browsing, professional tool use, codebase understanding, and million-token retrieval. It accepts text, images, audio, video, and files, supports tool calling and structured output, and always reasons before answering. Prompts and outputs may be used by Meta for training and to improve its products.","cost":"Input $0.10/m, Cached input $0.002/m, Output $0.20/m","costEstimate":0.0002,"provider":"meta","visible":true,"dateAdded":"2026-09-02","maxInputTokens":1048576,"maxImageInputs":50,"category":"More","label":"Training Opt-In","labelColor":"red","labelVariant":"outline","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","coding","agents","long context","training opt-in"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":2e-7,"input_price_per_million":0.1,"output_price_per_million":0.2,"input":0.1,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000002","input":0.1,"output":0.2,"cacheReadInputPer1kTokens":0.000002,"prompt_per_million":0.1,"completion_per_million":0.2,"prompt_per_token":"0.0000001","completion_per_token":"0.0000002","per_input_token":1e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000002},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1201.9},"inception/mercury-3":{"name":"Mercury 3","model":"inception/mercury-3","description":"Mercury 3 is Inception's diffusion language model for fast chat, coding, and multi-step agents. It accepts and generates text, with adjustable reasoning, parallel tool calls, structured JSON output, and a shared 1,000,000-token context window. Responses can use up to 131,072 tokens, including reasoning, within the remaining context.","cost":"Input $0.10/m, Cached input $0.01/m, Output $0.35/m","costEstimate":0.000225,"provider":"inception","visible":true,"isOpenSource":false,"dateAdded":"2026-10-19","category":"More","maxInputTokens":1000000,"maxOutputTokens":131072,"defaultThinkingEnabled":true,"defaultReasoningEffort":"low","capabilities":["reasoning","tool-calling","parallel-tool-calls","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"tags":["chat","reasoning","coding","tools","long context"],"api":"chat","input_price":1e-7,"output_price":3.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.35,"input":0.1,"output":0.35,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000035","input":0.1,"output":0.35,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.35,"prompt_per_token":"0.0000001","completion_per_token":"0.00000035","per_input_token":1e-7,"per_output_token":3.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00035,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00035,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1944.9},"inception/mercury-2.5-preview":{"defaultThinkingEnabled":true,"defaultReasoningEffort":"medium","name":"Mercury 2.5 Preview","model":"inception/mercury-2.5-preview","description":"Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.","cost":"Input $0.04/m, Cached input $0.004/m, Output $0.15/m","costEstimate":0.000095,"provider":"inception","visible":true,"isOpenSource":false,"dateAdded":"2026-09-01","category":"More","maxInputTokens":260000,"maxOutputTokens":65536,"capabilities":["reasoning","tool-calling","parallel-tool-calls","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"tags":["chat","reasoning","tools","low-latency","long context"],"api":"chat","input_price":4e-8,"output_price":1.5e-7,"input_price_per_million":0.04,"output_price_per_million":0.15,"input":0.04,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000004","completion":"0.00000015","input":0.04,"output":0.15,"cacheReadInputPer1kTokens":0.000004,"prompt_per_million":0.04,"completion_per_million":0.15,"prompt_per_token":"0.00000004","completion_per_token":"0.00000015","per_input_token":4e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000004},"effective_price":{"inputPer1kTokens":0.00004,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1219.4},"moondream/moondream3-preview":{"name":"Moondream 3 Preview","model":"moondream/moondream3-preview","description":"Moondream 3 Preview is the original 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.","cost":"Input $0.30/m, Output $2.50/m","costEstimate":0.0014,"provider":"moondream","visible":true,"isOpenSource":false,"dateAdded":"2026-10-16","totalParams":9,"activeParams":2,"maxInputTokens":32000,"maxOutputTokens":4096,"maxImageInputs":1,"preferredProviders":["PrimeIntellect"],"category":"More","capabilities":["vision","reasoning"],"toolCallingUnsupported":true,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultThinkingEnabled":false,"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":0.2,"minP":0,"topP":0.9,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"tags":["chat","vision","reasoning"],"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":94.3},"moondream/moondream3.1-9b-a2b":{"name":"Moondream 3.1 9B A2B","model":"moondream/moondream3.1-9b-a2b","description":"Moondream 3.1 is the successor to Moondream 3 Preview: a distinct 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.","cost":"Input $0.30/m, Output $2.50/m","costEstimate":0.0014,"provider":"moondream","visible":true,"isOpenSource":false,"dateAdded":"2026-10-16","totalParams":9,"activeParams":2,"maxInputTokens":32000,"maxOutputTokens":4096,"maxImageInputs":1,"preferredProviders":["PrimeIntellect"],"category":"More","capabilities":["vision","reasoning"],"toolCallingUnsupported":true,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultThinkingEnabled":false,"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":0.2,"minP":0,"topP":0.9,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"tags":["chat","vision","reasoning"],"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":119.8},"ibm-granite/granite-4.2-8b":{"totalParams":8,"name":"Granite 4.2 8B","model":"ibm-granite/granite-4.2-8b","description":"IBM Granite 4.2 8B is an Apache 2.0-licensed dense model with native step-by-step reasoning and specialized training for agentic work. It can plan before acting, sequence tools, navigate codebases, work in terminals, and verify results across coding, search, mathematics, science, and complex instruction-following tasks.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.15/m","costEstimate":0.000125,"provider":"ibm","visible":true,"isOpenSource":true,"dateAdded":"2026-08-31","category":"More","maxInputTokens":131072,"capabilities":["reasoning","tool-calling","structured-output"],"preferredProviders":["CoreWeave"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","low","high"]}},"tags":["chat","reasoning","coding","tools"],"api":"chat","input_price":1e-7,"output_price":1.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.15,"input":0.1,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000015","input":0.1,"output":0.15,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.15,"prompt_per_token":"0.0000001","completion_per_token":"0.00000015","per_input_token":1e-7,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":2361.8},"tencent/hy4-preview":{"isOpenSource":true,"totalParams":770,"activeParams":49,"name":"Tencent Hy4 Preview","model":"tencent/hy4-preview","description":"Hy4 Preview is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters. It is designed for coding agents, complex tool-use workflows, and productivity tasks, with a 1M-token context window and configurable reasoning effort.","cost":"Input $0.834/m, Cached input $0.042/m, Output $2.501/m","costEstimate":0.0016675,"provider":"tencent","visible":true,"dateAdded":"2026-08-28","maxInputTokens":1048576,"maxOutputTokens":64000,"category":"More","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","low","high"]}},"tags":["chat","reasoning","coding","tools","long context"],"api":"chat","input_price":8.34e-7,"output_price":0.000002501,"input_price_per_million":0.834,"output_price_per_million":2.501,"input":0.834,"output":2.501,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000834","completion":"0.000002501","input":0.834,"output":2.501,"cacheReadInputPer1kTokens":0.000042,"prompt_per_million":0.834,"completion_per_million":2.501,"prompt_per_token":"0.000000834","completion_per_token":"0.000002501","per_input_token":8.34e-7,"per_output_token":0.000002501},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000834,"outputPer1kTokens":0.002501,"cacheReadInputPer1kTokens":0.000042},"effective_price":{"inputPer1kTokens":0.000834,"outputPer1kTokens":0.002501,"cacheReadInputPer1kTokens":0.000042},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":2020.1},"z-ai/glm-5.3-flash":{"totalParams":320,"activeParams":18,"name":"GLM 5.3 Flash","model":"z-ai/glm-5.3-flash","description":"ox-alpha out of stealth! GLM-5.3 Flash is Z.ai's first natively multimodal GLM-5 model, with 320B total parameters and just 18B active parameters for efficient coding, agentic work, and precise 1M-token context. Its hybrid sparse-and-linear attention architecture helps it outperform GLM-5.2 at one-tenth the price while approaching Claude Opus 4.8 on coding and agentic benchmarks.","cost":"Input $0.10/m, Cached input $0.025/m, Output $0.30/m","costEstimate":0.0002,"provider":"zhipu","visible":true,"isOpenSource":true,"dateAdded":"2026-08-26","maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","capabilities":["reasoning","vision","video-input","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["chat","reasoning","vision","video","tools","long context"],"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1285.7},"qwen/qwen3.8-max-prime":{"name":"Qwen3.8 Max Prime","model":"qwen/qwen3.8-max-prime","description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max for coding, complex analysis, and long-running agent workflows. It accepts text, image, and video input, supports tool calling and structured output, and has a 1M-token context window. Reasoning is always enabled.","cost":"Input $4/m, Cached input $0.50/m, Output $12/m","costEstimate":0.01,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-09-23","maxInputTokens":1000000,"maxOutputTokens":131072,"category":"More","capabilities":["reasoning","vision","video-input","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"xhigh","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","vision","video","tools","long context"],"api":"chat","input_price":0.000004,"output_price":0.000012,"input_price_per_million":4,"output_price_per_million":12,"input":4,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000004","completion":"0.000012","input":4,"output":12,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":4,"completion_per_million":12,"prompt_per_token":"0.000004","completion_per_token":"0.000012","per_input_token":0.000004,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":793.5},"google/diffusiongemma":{"totalParams":26,"activeParams":4,"name":"DiffusionGemma","model":"google/diffusiongemma","description":"DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window. Temperature, min-p, seed, minimum output tokens, logit bias, bad words, and allowed token IDs are unavailable; omit these parameters to use native diffusion sampling.","cost":"Input $0.05/m, Cached input $0.025/m, Output $0.15/m","costEstimate":0.00015,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-09-19","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","unsupportedResponseFormatTypes":["json_object","json_schema"],"capabilities":["reasoning"],"toolCallingUnsupported":true,"defaultSettings":{"stream":true,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none"},"additionalParams":{"reasoning_effort":{"levels":["none","xhigh"]}},"tags":["fast","chat","reasoning","long context"],"api":"chat","input_price":5e-8,"output_price":1.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.15,"input":0.05,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000015","input":0.05,"output":0.15,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.15,"prompt_per_token":"0.00000005","completion_per_token":"0.00000015","per_input_token":5e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":265.8},"qwen/qwen3.8-27b-cybersecurity":{"totalParams":27,"name":"Qwen 3.8 27B Cybersecurity","model":"qwen/qwen3.8-27b-cybersecurity","description":"Qwen 3.8 27B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.","cost":"Input $0.1/m, Cached input $0.05/m, Output $0.6/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-09-19","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"tags":["cybersecurity","coding","reasoning","vision","tools","long context"],"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":467.4},"google/gemma-4-26b-a4b-it-cybersecurity":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Cybersecurity","model":"google/gemma-4-26b-a4b-it-cybersecurity","description":"Gemma 4 26B A4B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.","cost":"Input $0.1056/m, Cached input $0.0528/m, Output $0.3344/m","costEstimate":0.0003344,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-09-19","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"tags":["cybersecurity","coding","reasoning","vision","tools","long context"],"api":"chat","input_price":1.056e-7,"output_price":3.344e-7,"input_price_per_million":0.1056,"output_price_per_million":0.3344,"input":0.1056,"output":0.3344,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001056","completion":"0.0000003344","input":0.1056,"output":0.3344,"cacheReadInputPer1kTokens":0.0000528,"prompt_per_million":0.1056,"completion_per_million":0.3344,"prompt_per_token":"0.0000001056","completion_per_token":"0.0000003344","per_input_token":1.056e-7,"per_output_token":3.344e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001056,"outputPer1kTokens":0.0003344,"cacheReadInputPer1kTokens":0.0000528},"effective_price":{"inputPer1kTokens":0.0001056,"outputPer1kTokens":0.0003344,"cacheReadInputPer1kTokens":0.0000528},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":600},"z-ai/glm-5.3-flash-cybersecurity":{"totalParams":320,"activeParams":18,"name":"GLM 5.3 Flash Cybersecurity","model":"z-ai/glm-5.3-flash-cybersecurity","description":"GLM 5.3 Flash Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports always-on reasoning, image understanding, tool calling, and a 1,048,576-token context window.","cost":"Input $0.15/m, Cached input $0.075/m, Output $0.5/m","costEstimate":0.0005,"provider":"zhipu","visible":true,"isOpenSource":true,"dateAdded":"2026-09-19","maxInputTokens":1048576,"maxOutputTokens":32768,"category":"More","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["cybersecurity","coding","reasoning","vision","tools","long context"],"api":"chat","input_price":1.5e-7,"output_price":5e-7,"input_price_per_million":0.15,"output_price_per_million":0.5,"input":0.15,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000005","input":0.15,"output":0.5,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.15,"completion_per_million":0.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000005","per_input_token":1.5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.000075},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.000075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":416.8},"z-ai/glm-5.3-flash-apex":{"totalParams":320,"activeParams":18,"name":"Apex Flash 1","model":"z-ai/glm-5.3-flash-apex","description":"Apex Flash 1 is Cantina Security and Yeta's cybersecurity-focused post-train of GLM 5.3 Flash for code investigation and tool use.","cost":"Input $0.15/m, Cached input $0.075/m, Output $0.5/m","costEstimate":0.0005,"provider":"zhipu","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":1048576,"maxOutputTokens":32768,"category":"More","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["cybersecurity","coding","reasoning","vision","tools","long context"],"api":"chat","input_price":1.5e-7,"output_price":5e-7,"input_price_per_million":0.15,"output_price_per_million":0.5,"input":0.15,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000005","input":0.15,"output":0.5,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.15,"completion_per_million":0.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000005","per_input_token":1.5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.000075},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.000075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":672.4},"z-ai/glm-5.3-flash-apex-abliterated":{"totalParams":320,"activeParams":18,"name":"Apex Flash 1 Abliterated","model":"z-ai/glm-5.3-flash-apex-abliterated","description":"Apex Flash 1 Abliterated is an experimental derivative of Cantina Security and Yeta's Apex Flash 1 with modified refusal behavior.","cost":"Input $0.15/m, Cached input $0.075/m, Output $0.5/m","costEstimate":0.0005,"provider":"zhipu","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":1048576,"maxOutputTokens":32768,"category":"Uncensored","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["cybersecurity","coding","reasoning","vision","tools","long context"],"api":"chat","input_price":1.5e-7,"output_price":5e-7,"input_price_per_million":0.15,"output_price_per_million":0.5,"input":0.15,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000005","input":0.15,"output":0.5,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.15,"completion_per_million":0.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000005","per_input_token":1.5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.000075},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.000075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":629.1},"nvidia/nemotron-3.5-content-safety":{"name":"Nemotron 3.5 Content Safety","model":"nvidia/nemotron-3.5-content-safety","description":"Nemotron 3.5 Content Safety is a content moderation classifier that labels user messages and assistant responses as safe or unsafe. It supports a 131,072-token context window and optional reasoning.","cost":"Input $0.05/m, Cached input $0.025/m, Output $0.15/m","costEstimate":0.00015,"provider":"nvidia","visible":true,"isOpenSource":true,"dateAdded":"2026-09-19","maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","capabilities":["reasoning"],"toolCallingUnsupported":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"tags":["moderation","content safety","classification","reasoning"],"api":"chat","input_price":5e-8,"output_price":1.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.15,"input":0.05,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000015","input":0.05,"output":0.15,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.15,"prompt_per_token":"0.00000005","completion_per_token":"0.00000015","per_input_token":5e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":16.3},"TheDrummer/Artemis-v1.1":{"totalParams":31,"name":"TheDrummer/Artemis v1.1","model":"TheDrummer/Artemis-v1.1","description":"TheDrummer's Artemis v1.1 is a Gemma 4 31B fine-tune for creative writing, expressive dialogue, and roleplay, with optional thinking and a 262K context window.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-09-06","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":419.9},"z-ai/glm-5.3-flash-uncensored":{"totalParams":320,"activeParams":18,"name":"GLM 5.3 Flash Uncensored","model":"z-ai/glm-5.3-flash-uncensored","description":"GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model with provider-dependent vision support, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.","cost":"Input $0.20/m, Output $0.80/m","costEstimate":0.0008,"provider":"zhipu","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":1048576,"maxOutputTokens":32768,"category":"Uncensored","capabilities":["reasoning","vision","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high"]}},"tags":["uncensored","chat","reasoning","vision","coding","tools","long context"],"api":"chat","input_price":2e-7,"output_price":8e-7,"input_price_per_million":0.2,"output_price_per_million":0.8,"input":0.2,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000008","input":0.2,"output":0.8,"cacheReadInputPer1kTokens":0.00007,"prompt_per_million":0.2,"completion_per_million":0.8,"prompt_per_token":"0.0000002","completion_per_token":"0.0000008","per_input_token":2e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0008,"cacheReadInputPer1kTokens":0.00007},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0008,"cacheReadInputPer1kTokens":0.00007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":691.6},"z-ai/glm-5.3-uncensored":{"totalParams":744,"activeParams":40,"name":"GLM 5.3 Uncensored","model":"z-ai/glm-5.3-uncensored","description":"An experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.","cost":"Input $1.25/m, Cached input $0.30/m, Output $2.25/m","costEstimate":0.00225,"provider":"zhipu","visible":true,"isOpenSource":true,"dateAdded":"2026-09-26","maxInputTokens":1048576,"maxOutputTokens":131072,"category":"Uncensored","capabilities":["reasoning","tool-calling"],"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["uncensored","chat","reasoning","coding","tools","long context"],"api":"chat","input_price":0.00000125,"output_price":0.00000225,"input_price_per_million":1.25,"output_price_per_million":2.25,"input":1.25,"output":2.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00000225","input":1.25,"output":2.25,"cacheReadInputPer1kTokens":0.0003,"prompt_per_million":1.25,"completion_per_million":2.25,"prompt_per_token":"0.00000125","completion_per_token":"0.00000225","per_input_token":0.00000125,"per_output_token":0.00000225},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00225,"cacheReadInputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00225,"cacheReadInputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":1127.3},"qwen/qwen3.8-27b-uncensored":{"totalParams":27,"name":"Qwen 3.8 27B Uncensored","model":"qwen/qwen3.8-27b-uncensored","description":"Qwen 3.8 27B Uncensored is an FP8 open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.","cost":"Input $1.00/m, Cached input $0.22/m, Output $3.00/m","costEstimate":0.003,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":524288,"maxOutputTokens":65536,"category":"Uncensored","tags":["uncensored","chat","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":0.000001,"output_price":0.000003,"input_price_per_million":1,"output_price_per_million":3,"input":1,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000003","input":1,"output":3,"cacheReadInputPer1kTokens":0.00022,"prompt_per_million":1,"completion_per_million":3,"prompt_per_token":"0.000001","completion_per_token":"0.000003","per_input_token":0.000001,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00022},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00022},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":501.1},"qwen/qwen3.8-27b-queen":{"totalParams":27,"name":"Qwen 3.8 27B Queen","model":"qwen/qwen3.8-27b-queen","description":"Qwen 3.8 27B Queen is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 524,288-token context window.","cost":"Input $0.25/m, Cached input $0.125/m, Output $1.5/m","costEstimate":0.0015,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-09-09","maxInputTokens":524288,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":2.5e-7,"output_price":0.0000015,"input_price_per_million":0.25,"output_price_per_million":1.5,"input":0.25,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000015","input":0.25,"output":1.5,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":0.25,"completion_per_million":1.5,"prompt_per_token":"0.00000025","completion_per_token":"0.0000015","per_input_token":2.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":220.1},"qwen/qwen3.8-27b-hemmingway":{"totalParams":27,"name":"Qwen 3.8 27B Hemingway","model":"qwen/qwen3.8-27b-hemmingway","description":"Qwen 3.8 27B Hemingway is an open-weight NVFP4 multimodal creative finetune for long-form prose, character dialogue, storytelling, and roleplay.","cost":"Input $0.25/m, Cached input $0.125/m, Output $1.50/m","costEstimate":0.0015,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-09-21","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":2.5e-7,"output_price":0.0000015,"input_price_per_million":0.25,"output_price_per_million":1.5,"input":0.25,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000015","input":0.25,"output":1.5,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":0.25,"completion_per_million":1.5,"prompt_per_token":"0.00000025","completion_per_token":"0.0000015","per_input_token":2.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":444.2},"qwen/qwen3.8-27b-antislop":{"totalParams":27,"name":"Qwen 3.8 27B Antislop","model":"qwen/qwen3.8-27b-antislop","description":"Qwen 3.8 27B Antislop is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":298.6},"qwen/qwen3.8-27b-darkidol":{"totalParams":27,"name":"Qwen 3.8 27B DarkIdol","model":"qwen/qwen3.8-27b-darkidol","description":"Qwen 3.8 27B DarkIdol is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.351Z"},"avgOutputTokens":554.1},"qwen/qwen3.8-27b-fimi":{"totalParams":27,"name":"Qwen 3.8 27B Fimi","model":"qwen/qwen3.8-27b-fimi","description":"Qwen 3.8 27B Fimi is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":289.8},"qwen/qwen3.8-27b-kimiko":{"totalParams":27,"name":"Qwen 3.8 27B Kimiko","model":"qwen/qwen3.8-27b-kimiko","description":"Qwen 3.8 27B Kimiko is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":210.3},"qwen/qwen3.8-27b-kiwen":{"totalParams":27,"name":"Qwen 3.8 27B Kiwen","model":"qwen/qwen3.8-27b-kiwen","description":"Qwen 3.8 27B Kiwen is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":222},"qwen/qwen3.8-27b-novelist":{"totalParams":27,"name":"Qwen 3.8 27B Novelist","model":"qwen/qwen3.8-27b-novelist","description":"Qwen 3.8 27B Novelist is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":744.7},"qwen/qwen3.8-27b-swift":{"totalParams":27,"name":"Qwen 3.8 27B Swift","model":"qwen/qwen3.8-27b-swift","description":"Qwen 3.8 27B Swift is a finetune for fast responses, served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","tags":["Thinking","fast responses","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":158},"qwen/qwen3.8-27b-synthia":{"totalParams":27,"name":"Qwen 3.8 27B Synthia","model":"qwen/qwen3.8-27b-synthia","toolCallingUnsupported":true,"description":"Qwen 3.8 27B Synthia is a text-only roleplay finetune served by Aoru in NVFP4 with a 262,144-token context window.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.60/m","costEstimate":0.0006,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-10-05","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","long context"],"labelVariant":"outline","capabilities":[],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":6e-7,"input_price_per_million":0.1,"output_price_per_million":0.6,"input":0.1,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000006","input":0.1,"output":0.6,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.6,"prompt_per_token":"0.0000001","completion_per_token":"0.0000006","per_input_token":1e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":1843.1},"gemma-4-12b-it-starry-ocean":{"totalParams":12,"name":"Gemma 4 12B Starry Ocean","model":"gemma-4-12b-it-starry-ocean","description":"Gemma 4 12B Starry Ocean is an open-weight merge for storytelling, roleplay, and creative writing. It supports image understanding, tool calling, optional reasoning, and a 131,072-token context window.","unsupportedResponseFormatTypes":["json_object","json_schema"],"cost":"Input $0.05/m, Cached input $0.025/m, Output $0.25/m","costEstimate":0.00025,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-10-15","maxInputTokens":131072,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"api":"chat","input_price":5e-8,"output_price":2.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.25,"input":0.05,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000025","input":0.05,"output":0.25,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.25,"prompt_per_token":"0.00000005","completion_per_token":"0.00000025","per_input_token":5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":233.3},"gemma-4-12b-it-semancer":{"totalParams":12,"name":"Gemma 4 12B Semancer","model":"gemma-4-12b-it-semancer","description":"Gemma 4 12B Semancer is an open-weight finetune by UnstableLlama trained on a custom occult-philosophy dataset. It is designed for in-depth philosophical discussion of topics such as truth, free will, consciousness, and meaning, with answers developed from first principles. It supports image understanding, tool calling, optional reasoning, and a 131,072-token context window.","cost":"Input $0.05/m, Cached input $0.025/m, Output $0.25/m","costEstimate":0.00025,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-09-09","maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","tags":["Thinking","philosophy","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":5e-8,"output_price":2.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.25,"input":0.05,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000025","input":0.05,"output":0.25,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.25,"prompt_per_token":"0.00000005","completion_per_token":"0.00000025","per_input_token":5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":71.1},"gemma-4-12b-it-station-keeper":{"totalParams":12,"name":"Gemma 4 12B StationKeeper","model":"gemma-4-12b-it-station-keeper","description":"Gemma 4 12B StationKeeper is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 131,072-token context window.","cost":"Input $0.05/m, Cached input $0.025/m, Output $0.25/m","costEstimate":0.00025,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-09-09","maxInputTokens":131072,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","multimodal","long context"],"labelVariant":"outline","capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":5e-8,"output_price":2.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.25,"input":0.05,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000025","input":0.05,"output":0.25,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.25,"prompt_per_token":"0.00000005","completion_per_token":"0.00000025","per_input_token":5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":37.5},"qwen/qwen3.8-27b-fable":{"totalParams":27,"name":"Qwen 3.8 27B Fable","model":"qwen/qwen3.8-27b-fable","description":"Qwen 3.8 27B Fable is an open-weight multimodal creative finetune for expressive dialogue, long-form storytelling, character work, and roleplay, with a 524,288-token context window.","cost":"Input $0.25/m, Cached input $0.125/m, Output $1.50/m","costEstimate":0.0015,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":524288,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":2.5e-7,"output_price":0.0000015,"input_price_per_million":0.25,"output_price_per_million":1.5,"input":0.25,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000015","input":0.25,"output":1.5,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":0.25,"completion_per_million":1.5,"prompt_per_token":"0.00000025","completion_per_token":"0.0000015","per_input_token":2.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":485.1},"qwen/qwen3.8-27b-uncensored:thinking":{"totalParams":27,"name":"Qwen 3.8 27B Uncensored Thinking","model":"qwen/qwen3.8-27b-uncensored:thinking","description":"Qwen 3.8 27B Uncensored with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.","cost":"Input $1.00/m, Cached input $0.22/m, Output $3.00/m","costEstimate":0.003,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":524288,"maxOutputTokens":65536,"category":"Uncensored","tags":["Thinking","uncensored","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"api":"chat","input_price":0.000001,"output_price":0.000003,"input_price_per_million":1,"output_price_per_million":3,"input":1,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000003","input":1,"output":3,"cacheReadInputPer1kTokens":0.00022,"prompt_per_million":1,"completion_per_million":3,"prompt_per_token":"0.000001","completion_per_token":"0.000003","per_input_token":0.000001,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00022},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00022},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":1449.8},"Gemma-4-31B-MeroMero-v2":{"totalParams":31,"name":"Gemma 4 31B MeroMero v2","model":"Gemma-4-31B-MeroMero-v2","description":"Gemma 4 31B MeroMero v2 is a LoRA finetune for emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":345.2},"Gemma-4-31B-MeroMero-v2:thinking":{"totalParams":31,"name":"Gemma 4 31B MeroMero v2 Thinking","model":"Gemma-4-31B-MeroMero-v2:thinking","description":"Gemma 4 31B MeroMero v2 with thinking enabled for more deliberate emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":1393.2},"Gemma-4-26B-A4B-MeroMero":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B MeroMero","model":"Gemma-4-26B-A4B-MeroMero","description":"Gemma 4 26B A4B MeroMero is an NVFP4 multimodal mixture-of-experts fine-tune for emotive dialogue, relationship scenes, creative writing, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":509.6},"Gemma-4-26B-A4B-MeroMero:thinking":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B MeroMero Thinking","model":"Gemma-4-26B-A4B-MeroMero:thinking","description":"Gemma 4 26B A4B MeroMero with thinking enabled for more deliberate emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":1218.3},"gemma-4-26b-a4b-it-musica":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Musica","model":"gemma-4-26b-a4b-it-musica","description":"Musica is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":200.6},"gemma-4-26b-a4b-it-shadowsiren":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Shadow Siren","model":"gemma-4-26b-a4b-it-shadowsiren","description":"Shadow Siren is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":296.2},"gemma-4-26b-a4b-it-chimerax":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Chimera X","model":"gemma-4-26b-a4b-it-chimerax","description":"Chimera X is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":593.2},"gemma-4-26b-a4b-it-chimeraxheretic":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Chimera X Heretic","model":"gemma-4-26b-a4b-it-chimeraxheretic","description":"Chimera X Heretic is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-10-08","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Uncensored","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":314.5},"gemma-4-26b-a4b-it-luminous":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Luminous Mirror","model":"gemma-4-26b-a4b-it-luminous","description":"Luminous Mirror is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":101.9},"gemma-4-26b-a4b-it-darksoul":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Dark Soul","model":"gemma-4-26b-a4b-it-darksoul","description":"Dark Soul is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":412.8},"gemma-4-26b-a4b-it-moonlight":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Moonlight Dusk","model":"gemma-4-26b-a4b-it-moonlight","description":"Moonlight Dusk is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":196.2},"gemma-4-26b-a4b-it-opusdistill":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Opus Distill","model":"gemma-4-26b-a4b-it-opusdistill","description":"Opus Distill is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":419.1},"gemma-4-31b-it-fabled":{"totalParams":31,"name":"Gemma 4 31B Fabled","model":"gemma-4-31b-it-fabled","description":"Fabled is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":347.6},"gemma-4-31b-it-darkidol":{"totalParams":31,"name":"Gemma 4 31B DarkIdol","model":"gemma-4-31b-it-darkidol","description":"DarkIdol is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":503.9},"gemma-4-31b-it-garnet":{"totalParams":31,"name":"Gemma 4 31B Garnet","model":"gemma-4-31b-it-garnet","description":"Garnet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":167.3},"gemma-4-31b-it-novelist":{"totalParams":31,"name":"Gemma 4 31B Novelist","model":"gemma-4-31b-it-novelist","description":"Novelist is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":476.1},"gemma-4-31b-it-isometry":{"totalParams":31,"name":"Gemma 4 31B Isometry","model":"gemma-4-31b-it-isometry","description":"Isometry is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":280.9},"gemma-4-31b-it-gembrain":{"totalParams":31,"name":"Gemma 4 31B Gembrain","model":"gemma-4-31b-it-gembrain","description":"Gembrain is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":397.2},"gemma-4-31b-it-gemsicle":{"totalParams":31,"name":"Gemma 4 31B Gemsicle","model":"gemma-4-31b-it-gemsicle","description":"Gemsicle is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.352Z"},"avgOutputTokens":427.1},"gemma-4-31b-it-scarlet":{"totalParams":31,"name":"Gemma 4 31B Scarlet","model":"gemma-4-31b-it-scarlet","description":"Scarlet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-10-08","maxInputTokens":262144,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","tags":["Thinking","roleplay","creative writing","multimodal"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":455.8},"ornith-ai/ornith-1.5-122b":{"totalParams":122,"name":"Ornith 1.5 122B","model":"ornith-ai/ornith-1.5-122b","description":"Ornith 1.5 122B is an MIT-licensed open-weight model for coding, reasoning, tool use and image understanding. It accepts text and images across a shared 262,144-token context, with up to 32,768 output tokens. Reasoning is enabled by default; JSON object output and streaming are supported.","cost":"Input $0.20/m, Cached input $0.02/m, Output $0.80/m","costEstimate":0.0005,"provider":"other","visible":true,"isOpenSource":true,"dateAdded":"2026-10-20","maxInputTokens":262144,"maxOutputTokens":32768,"maxImageInputs":8,"category":"More","tags":["Thinking","chat","reasoning","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":0.6,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled"}},"api":"chat","input_price":2e-7,"output_price":8e-7,"input_price_per_million":0.2,"output_price_per_million":0.8,"input":0.2,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000008","input":0.2,"output":0.8,"cacheReadInputPer1kTokens":0.00002,"prompt_per_million":0.2,"completion_per_million":0.8,"prompt_per_token":"0.0000002","completion_per_token":"0.0000008","per_input_token":2e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0008,"cacheReadInputPer1kTokens":0.00002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0008,"cacheReadInputPer1kTokens":0.00002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":7944.6},"ornith-ai/ornith-1.5-35b-a3b":{"totalParams":35,"activeParams":3,"name":"Ornith 1.5 35B","model":"ornith-ai/ornith-1.5-35b-a3b","description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.40/m","costEstimate":0.0004,"provider":"other","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","tags":["chat","reasoning","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":268},"ornith-ai/ornith-1.5-35b-a3b:thinking":{"totalParams":35,"activeParams":3,"name":"Ornith 1.5 35B Thinking","model":"ornith-ai/ornith-1.5-35b-a3b:thinking","description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, reasoning, tool use, image understanding, and long-context work. This variant enables thinking by default.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.40/m","costEstimate":0.0004,"provider":"other","visible":true,"isOpenSource":true,"dateAdded":"2026-07-29","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","tags":["Thinking","chat","reasoning","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":1465.8},"qwen3.8-27b":{"totalParams":27,"name":"Qwen3.8 27B","model":"qwen/qwen3.8-27b","description":"Qwen3.8 27B is an open-weight multimodal model from Alibaba for coding, visual understanding, tool use, and structured output. This variant keeps thinking disabled for faster direct responses. Requests containing video cost $0.32 per million input tokens and $2.50 per million output tokens.","cost":"Non-ZDR Auto: Input $0.15/m, Cached input $0.04/m, Output $0.70/m. ZDR Auto: Input $0.20/m, Cached input $0.04/m, Output $1.40/m","costEstimate":0.0007,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-08-16","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","tags":["chat","reasoning","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":1.5e-7,"output_price":7e-7,"input_price_per_million":0.15,"output_price_per_million":0.7,"input":0.15,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000007","input":0.15,"output":0.7,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.15,"completion_per_million":0.7,"prompt_per_token":"0.00000015","completion_per_token":"0.0000007","per_input_token":1.5e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0007,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0007,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":583},"qwen3.8-27b:thinking":{"totalParams":27,"name":"Qwen3.8 27B Thinking","model":"qwen/qwen3.8-27b:thinking","description":"Qwen3.8 27B is an open-weight multimodal model from Alibaba for reasoning, coding, visual understanding, tool use, and structured output. This variant enables thinking by default. Requests containing video cost $0.32 per million input tokens and $2.50 per million output tokens.","cost":"Non-ZDR Auto: Input $0.15/m, Cached input $0.04/m, Output $0.70/m. ZDR Auto: Input $0.20/m, Cached input $0.04/m, Output $1.40/m","costEstimate":0.0007,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-08-16","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","tags":["Thinking","chat","reasoning","coding","multimodal","long context"],"capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"api":"chat","input_price":1.5e-7,"output_price":7e-7,"input_price_per_million":0.15,"output_price_per_million":0.7,"input":0.15,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000007","input":0.15,"output":0.7,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.15,"completion_per_million":0.7,"prompt_per_token":"0.00000015","completion_per_token":"0.0000007","per_input_token":1.5e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0007,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0007,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":1774.1},"gemma-4-12b-it":{"totalParams":12,"name":"Gemma 4 12B Instruct","model":"gemma-4-12b-it","description":"Google's Gemma 4 12B Instruct is an open-weight multimodal model for text and image understanding, with tool calling and structured output support.","cost":"Input $0.05/m, Cached input $0.025/m, Output $0.25/m","costEstimate":0.00025,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-08-01","maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","tags":["chat","multimodal","long context"],"capabilities":["vision","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":2.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.25,"input":0.05,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000025","input":0.05,"output":0.25,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.25,"prompt_per_token":"0.00000005","completion_per_token":"0.00000025","per_input_token":5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.353Z"},"avgOutputTokens":162.3},"celeris-1":{"name":"Celeris 1","model":"celeris-1","description":"Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.","cost":"Input $2/m, Output $6/m","costEstimate":0.006,"provider":"celeris","visible":true,"dateAdded":"2026-07-25","maxInputTokens":8192,"maxOutputTokens":8192,"category":"More","toolCallingUnsupported":true,"tags":["chat","fast","structured output"],"defaultSettings":{"stream":true,"temperature":0,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"maxTokens":2048},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"}},"deepseek/deepseek-v4.1-flash-uncensored":{"name":"DeepSeek V4.1 Flash Uncensored","model":"deepseek/deepseek-v4.1-flash-uncensored","description":"A lower-refusal finetune of DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. Supports a context window of up to 1M tokens.","cost":"Input $0.50/m, Cached input $0.275/m, Output $1.50/m","costEstimate":0.0015,"provider":"deepseek","visible":true,"disabled":false,"isOpenSource":true,"dateAdded":"2026-10-01","maxInputTokens":1048576,"maxOutputTokens":65536,"category":"Uncensored","tags":["uncensored","chat","reasoning","coding","tools","long context"],"capabilities":["reasoning","tool-calling"],"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none"},"api":"chat","input_price":3.3e-7,"output_price":0.00000132,"input_price_per_million":0.33,"output_price_per_million":1.32,"input":0.33,"output":1.32,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000033","completion":"0.00000132","input":0.33,"output":1.32,"cacheReadInputPer1kTokens":0.00000825,"prompt_per_million":0.33,"completion_per_million":1.32,"prompt_per_token":"0.00000033","completion_per_token":"0.00000132","per_input_token":3.3e-7,"per_output_token":0.00000132},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00033,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.00000825},"effective_price":{"inputPer1kTokens":0.00033,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.00000825},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":643.1},"deepseek/deepseek-v4.1-flash-uncensored:thinking":{"name":"DeepSeek V4.1 Flash Uncensored Thinking","model":"deepseek/deepseek-v4.1-flash-uncensored:thinking","description":"A lower-refusal finetune of DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. Supports a context window of up to 1M tokens.","cost":"Input $0.50/m, Cached input $0.275/m, Output $1.50/m","costEstimate":0.0015,"provider":"deepseek","visible":true,"disabled":false,"isOpenSource":true,"dateAdded":"2026-10-01","maxInputTokens":1048576,"maxOutputTokens":65536,"category":"Uncensored","tags":["uncensored","chat","reasoning","coding","tools","long context"],"capabilities":["reasoning","tool-calling"],"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"api":"chat","input_price":3.3e-7,"output_price":0.00000132,"input_price_per_million":0.33,"output_price_per_million":1.32,"input":0.33,"output":1.32,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000033","completion":"0.00000132","input":0.33,"output":1.32,"cacheReadInputPer1kTokens":0.00000825,"prompt_per_million":0.33,"completion_per_million":1.32,"prompt_per_token":"0.00000033","completion_per_token":"0.00000132","per_input_token":3.3e-7,"per_output_token":0.00000132},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00033,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.00000825},"effective_price":{"inputPer1kTokens":0.00033,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.00000825},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":796.8},"heabsy/cyberheabsy":{"name":"CyberHeabsy","model":"heabsy/cyberheabsy","description":"A low-refusal text model for authorized security research, roleplay, and creative writing. It preserves tool calling after refusal removal, supports optional reasoning, and has a 1M-token context window.","cost":"Input $1.50/m, Cached input $0.275/m, Output $4.50/m","costEstimate":0.0045,"provider":"heabsy","visible":true,"isOpenSource":false,"dateAdded":"2026-09-27","maxInputTokens":1048576,"maxOutputTokens":65536,"category":"Uncensored","tags":["uncensored","chat","reasoning","coding","tools","long context"],"capabilities":["reasoning","tool-calling"],"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000015,"output_price":0.0000045,"input_price_per_million":1.5,"output_price_per_million":4.5,"input":1.5,"output":4.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.0000045","input":1.5,"output":4.5,"cacheReadInputPer1kTokens":0.000275,"prompt_per_million":1.5,"completion_per_million":4.5,"prompt_per_token":"0.0000015","completion_per_token":"0.0000045","per_input_token":0.0000015,"per_output_token":0.0000045},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.0045,"cacheReadInputPer1kTokens":0.000275},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.0045,"cacheReadInputPer1kTokens":0.000275},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":1334.1},"heabsy/qwen3.8-27b-uncensored-fast":{"totalParams":27,"name":"Qwen 3.8 27B Uncensored Fast by Heabsy","model":"heabsy/qwen3.8-27b-uncensored-fast","description":"Heabsy's NVFP4 build of Qwen3.8-27B by Alibaba Cloud, with refusal removal based on huihui-ai's Huihui-Qwen3.8-27B-abliterated. Quantized and calibrated by Heabsy, with unpublished weights under the Heabsy Model License. Supports text and image input, tools, and optional reasoning capped at 16,384 tokens within the output budget. This named build is separate from Qwen 3.8 27B Uncensored.","cost":"Input $1.00/m, Cached input $0.22/m, Output $3.00/m","costEstimate":0.003,"provider":"heabsy","visible":true,"isOpenSource":false,"dateAdded":"2026-10-16","maxInputTokens":524288,"maxOutputTokens":235929,"category":"Uncensored","capabilities":["vision","reasoning","tool-calling"],"unsupportedResponseFormatTypes":["json_object","json_schema"],"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["uncensored","chat","reasoning","vision","tools","long context"],"api":"chat","input_price":0.000001,"output_price":0.000003,"input_price_per_million":1,"output_price_per_million":3,"input":1,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000003","input":1,"output":3,"cacheReadInputPer1kTokens":0.00022,"prompt_per_million":1,"completion_per_million":3,"prompt_per_token":"0.000001","completion_per_token":"0.000003","per_input_token":0.000001,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00022},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00022},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":1472.6},"xiaomi/mimo-v2.6-flash-uncensored":{"totalParams":309,"activeParams":15,"name":"MiMo V2.6 Flash Uncensored","model":"xiaomi/mimo-v2.6-flash-uncensored","description":"A lower-refusal MiMo V2.6 Flash finetune with a 1M-token context window, separate reasoning output, and tool calling. Supports image input and adjustable thinking effort.","cost":"Input $0.50/m, Cached input $0.1995/m, Output $1.50/m","costEstimate":0.0015,"provider":"xiaomi","visible":true,"isOpenSource":true,"dateAdded":"2026-09-25","maxInputTokens":1048576,"maxOutputTokens":65536,"category":"Uncensored","tags":["uncensored","chat","reasoning","coding","vision","tools","long context"],"capabilities":["reasoning","vision","tool-calling"],"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.0000015,"input_price_per_million":0.5,"output_price_per_million":1.5,"input":0.5,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000015","input":0.5,"output":1.5,"cacheReadInputPer1kTokens":0.0001995,"prompt_per_million":0.5,"completion_per_million":1.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000015","per_input_token":5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.0001995},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.0001995},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":1155.2},"xiaomi/mimo-v2.6-flash-uncensored:thinking":{"totalParams":309,"activeParams":15,"name":"MiMo V2.6 Flash Uncensored Thinking","model":"xiaomi/mimo-v2.6-flash-uncensored:thinking","description":"MiMo V2.6 Flash Uncensored with maximum thinking enabled. Supports a 1M-token context window and tool calling.","cost":"Input $0.50/m, Cached input $0.1995/m, Output $1.50/m","costEstimate":0.0015,"provider":"xiaomi","visible":true,"isOpenSource":true,"dateAdded":"2026-09-26","maxInputTokens":1048576,"maxOutputTokens":65536,"category":"Uncensored","tags":["Thinking","uncensored","chat","reasoning","coding","vision","tools","long context"],"capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["max"]}},"api":"chat","input_price":5e-7,"output_price":0.0000015,"input_price_per_million":0.5,"output_price_per_million":1.5,"input":0.5,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000015","input":0.5,"output":1.5,"cacheReadInputPer1kTokens":0.0001995,"prompt_per_million":0.5,"completion_per_million":1.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000015","per_input_token":5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.0001995},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.0001995},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":1227.4},"xiaomi/mimo-v2.6-flash-abliterated":{"totalParams":309,"activeParams":15,"name":"MiMo V2.6 Flash Abliterated","model":"xiaomi/mimo-v2.6-flash-abliterated","description":"A MiMo V2.6 Flash finetune with refusal-direction ablation, image input, a 1M-token context window, separate reasoning output, and tool calling.","cost":"Input $0.50/m, Cached input $0.275/m, Output $1.50/m","costEstimate":0.0015,"provider":"xiaomi","visible":true,"isOpenSource":true,"dateAdded":"2026-09-25","maxInputTokens":1048576,"maxOutputTokens":65536,"category":"Uncensored","tags":["abliterated","uncensored","chat","reasoning","coding","vision","tools","long context"],"capabilities":["reasoning","vision","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":5e-7,"output_price":0.0000015,"input_price_per_million":0.5,"output_price_per_million":1.5,"input":0.5,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000015","input":0.5,"output":1.5,"cacheReadInputPer1kTokens":0.000275,"prompt_per_million":0.5,"completion_per_million":1.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000015","per_input_token":5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000275},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000275},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":1262.7},"pokee-isaac":{"totalParams":28,"name":"Pokee-Isaac 28B","model":"pokee-isaac","description":"Pokee-Isaac is a 28B agentic model with a roughly 10-million-token context window, function calling, and OpenAI-compatible structured output. Pokee bills in $0.01 increments, rounding each non-zero request up to the next cent.","cost":"Input $0.15/m, Output $1/m, $0.01 minimum/request","costEstimate":0.01,"provider":"pokee","visible":true,"dateAdded":"2026-08-04","maxInputTokens":10000000,"maxOutputTokens":60000,"category":"More","tags":["chat","reasoning","agents","long context"],"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":0.000001,"input_price_per_million":0.15,"output_price_per_million":1,"input":0.15,"output":1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.000001","input":0.15,"output":1,"prompt_per_million":0.15,"completion_per_million":1,"prompt_per_token":"0.00000015","completion_per_token":"0.000001","per_input_token":1.5e-7,"per_output_token":0.000001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.001},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.357Z"},"avgOutputTokens":901.5},"abliteration-ai/abliterated-model":{"name":"Abliterated Model","model":"abliteration-ai/abliterated-model","description":"Abliteration.ai's unrestricted multimodal reasoning model is weight-modified to reduce refusals and answer prompts the original model might reject. It supports text and image input, structured output, automatic prompt caching, and a 262K-token context window.","cost":"Input/output $3/m, cached input $0.30/m","costEstimate":0.003,"provider":"abliteration","visible":true,"isOpenSource":false,"dateAdded":"2026-08-27","maxInputTokens":262144,"maxOutputTokens":262134,"category":"Uncensored","toolCallingUnsupported":true,"tags":["uncensored","chat","multimodal","reasoning","long context"],"capabilities":["vision","reasoning","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high","xhigh","max"]}},"defaultThinkingEnabled":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000003,"input_price_per_million":1,"output_price_per_million":3,"input":1,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000003","input":1,"output":3,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":1,"completion_per_million":3,"prompt_per_token":"0.000001","completion_per_token":"0.000003","per_input_token":0.000001,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":1395.2},"abliteration-ai/abliterated-model-large":{"name":"Abliterated Model Large","model":"abliteration-ai/abliterated-model-large","description":"Abliteration.ai's unrestricted large text reasoning model is derived from GLM-5.2 and weight-modified to reduce refusals compared with the base model. It supports native tool calling, structured output, automatic prompt caching, and a one-million-token context window.","cost":"Input/output $5/m, cached input $0.50/m","costEstimate":0.005,"provider":"abliteration","visible":true,"isOpenSource":false,"dateAdded":"2026-08-27","maxInputTokens":1000000,"maxOutputTokens":999990,"category":"Uncensored","tags":["uncensored","chat","reasoning","agents","long context"],"capabilities":["reasoning","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high","xhigh","max"]}},"defaultThinkingEnabled":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000003,"output_price":0.000005,"input_price_per_million":3,"output_price_per_million":5,"input":3,"output":5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000005","input":3,"output":5,"cacheReadInputPer1kTokens":0.0003,"prompt_per_million":3,"completion_per_million":5,"prompt_per_token":"0.000003","completion_per_token":"0.000005","per_input_token":0.000003,"per_output_token":0.000005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":467},"abliteration-ai/abliterated-model-large-v2":{"name":"Abliterated Model Large V2","model":"abliteration-ai/abliterated-model-large-v2","description":"Abliteration.ai's default unrestricted large text reasoning model is derived from GLM-5.3 and weight-modified to reduce refusals compared with the base model. It supports native tool calling, structured output, automatic prompt caching, and a one-million-token context window.","cost":"Input/output $5/m, cached input $0.50/m","costEstimate":0.005,"provider":"abliteration","visible":true,"isOpenSource":false,"dateAdded":"2026-08-31","maxInputTokens":1000000,"maxOutputTokens":999990,"category":"Uncensored","tags":["uncensored","chat","reasoning","agents","long context"],"capabilities":["reasoning","tool-calling","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000003,"output_price":0.000005,"input_price_per_million":3,"output_price_per_million":5,"input":3,"output":5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000005","input":3,"output":5,"cacheReadInputPer1kTokens":0.0003,"prompt_per_million":3,"completion_per_million":5,"prompt_per_token":"0.000003","completion_per_token":"0.000005","per_input_token":0.000003,"per_output_token":0.000005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":844.1},"abliteration-ai/abliterated-model-large-flash":{"name":"Abliterated Large Flash","model":"abliteration-ai/abliterated-model-large-flash","description":"Abliterated Large Flash is an uncensored reasoning model based on DeepSeek V4.1-Flash-1017. It accepts text and images and returns text, with tool calling, JSON mode, JSON Schema output, and automatic prompt caching. Its shared input/output context is 1,048,576 tokens, with up to 262,144 output tokens when space permits. Reasoning defaults to high and can be turned off or set to low, high, or max. Supports up to four images across the request history.","cost":"Input $1/m, Output $2/m, Cached input $0.10/m","costEstimate":0.0015,"provider":"abliteration","visible":true,"isOpenSource":false,"dateAdded":"2026-10-23","maxInputTokens":1048576,"maxOutputTokens":262144,"maxImageInputs":4,"category":"Uncensored","tags":["uncensored","chat","multimodal","reasoning","agents","long context"],"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high","xhigh","max"]}},"defaultThinkingEnabled":true,"defaultReasoningEffort":"high","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000002,"input_price_per_million":1,"output_price_per_million":2,"input":1,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000002","input":1,"output":2,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":1,"completion_per_million":2,"prompt_per_token":"0.000001","completion_per_token":"0.000002","per_input_token":0.000001,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":1087.7},"poolside/laguna-s-2.1":{"totalParams":118,"activeParams":8,"name":"Laguna S 2.1","model":"poolside/laguna-s-2.1","description":"Poolside's open-weights agentic coding model with 118B total parameters and 8B activated per token. It is designed for long-horizon software engineering and tool use, with a context window of up to 1M tokens. This variant keeps thinking disabled for faster direct responses.","cost":"Input $0.10/m, Output $0.20/m, Cached input $0.01/m","costEstimate":0.0003,"provider":"poolside","visible":true,"dateAdded":"2026-07-21","maxInputTokens":1048576,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","capabilities":["reasoning","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"tags":["coding","agent","reasoning","tools","long-context"],"api":"chat","input_price":1e-7,"output_price":2e-7,"input_price_per_million":0.1,"output_price_per_million":0.2,"input":0.1,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000002","input":0.1,"output":0.2,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.2,"prompt_per_token":"0.0000001","completion_per_token":"0.0000002","per_input_token":1e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":183.3},"poolside/laguna-s-2.1:thinking":{"totalParams":118,"activeParams":8,"name":"Laguna S 2.1 Thinking","model":"poolside/laguna-s-2.1:thinking","description":"Poolside's open-weights agentic coding model with 118B total parameters and 8B activated per token, with thinking enabled for harder long-horizon software engineering, tool use, and extended reasoning. It supports a context window of up to 1M tokens.","cost":"Input $0.10/m, Output $0.20/m, Cached input $0.01/m","costEstimate":0.0003,"provider":"poolside","visible":true,"dateAdded":"2026-07-21","maxInputTokens":1048576,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","capabilities":["reasoning","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled"}},"tags":["Thinking","coding","agent","reasoning","tools","long-context"],"api":"chat","input_price":1e-7,"output_price":2e-7,"input_price_per_million":0.1,"output_price_per_million":0.2,"input":0.1,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000002","input":0.1,"output":0.2,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.2,"prompt_per_token":"0.0000001","completion_per_token":"0.0000002","per_input_token":1e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":917.7},"nvidia/nemotron-3.5-super-vl":{"totalParams":120,"activeParams":12,"name":"Nvidia Nemotron 3.5 Super VL","model":"nvidia/nemotron-3.5-super-vl","description":"NVIDIA’s open-weight 120B model (12B active) for reasoning, coding, tool use, document and GUI understanding, and video understanding. Text, images and video in; text out. A 262,144-token shared context window with responses limited to 16,384 tokens. OpenMDW 1.1 license.","cost":"Input $0.15/m, Cached input $0.02/m, Output $0.50/m","costEstimate":0.000325,"dateAdded":"2026-10-15","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":16384,"labelVariant":"outline","category":"More","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","medium","high"]}},"api":"chat","input_price":1.5e-7,"output_price":5e-7,"input_price_per_million":0.15,"output_price_per_million":0.5,"input":0.15,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000005","input":0.15,"output":0.5,"cacheReadInputPer1kTokens":0.00002,"prompt_per_million":0.15,"completion_per_million":0.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000005","per_input_token":1.5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.00002},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.00002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":1078.8},"nvidia/nemotron-3.5-lightning":{"totalParams":30,"activeParams":3,"name":"Nvidia Nemotron 3.5 Lightning","model":"nvidia/nemotron-3.5-lightning","description":"Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant.","cost":"Input $0.05/m, Cached input $0.01/m, Output $0.20/m","costEstimate":0.000125,"dateAdded":"2026-08-12","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":1000000,"maxOutputTokens":65536,"labelVariant":"outline","category":"More","capabilities":["reasoning","tool-calling","parallel-tool-calls"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"},"reasoning_effort":"none"},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":5e-8,"output_price":2e-7,"input_price_per_million":0.05,"output_price_per_million":0.2,"input":0.05,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.0000002","input":0.05,"output":0.2,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.05,"completion_per_million":0.2,"prompt_per_token":"0.00000005","completion_per_token":"0.0000002","per_input_token":5e-8,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":227.8},"nvidia/nemotron-3.5-lightning:thinking":{"totalParams":30,"activeParams":3,"name":"Nvidia Nemotron 3.5 Lightning Thinking","model":"nvidia/nemotron-3.5-lightning:thinking","description":"Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace.","cost":"Input $0.05/m, Cached input $0.01/m, Output $0.20/m","costEstimate":0.000125,"dateAdded":"2026-08-12","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":1000000,"maxOutputTokens":65536,"labelVariant":"outline","category":"More","tags":["Thinking"],"capabilities":["reasoning","tool-calling","parallel-tool-calls"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled"},"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":5e-8,"output_price":2e-7,"input_price_per_million":0.05,"output_price_per_million":0.2,"input":0.05,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.0000002","input":0.05,"output":0.2,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.05,"completion_per_million":0.2,"prompt_per_token":"0.00000005","completion_per_token":"0.0000002","per_input_token":5e-8,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":6071.8},"nvidia/nemotron-3-ultra-550b-a55b":{"totalParams":550,"activeParams":55,"name":"Nvidia Nemotron 3 Ultra 550B","model":"nvidia/nemotron-3-ultra-550b-a55b","description":"Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.","cost":"Average cost: $0.0015","costEstimate":0.0015,"dateAdded":"2026-06-04","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":1000000,"maxOutputTokens":65536,"labelVariant":"outline","category":"More","capabilities":["reasoning","tool-calling","parallel-tool-calls"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"},"reasoning_effort":"none"},"api":"chat","input_price":5e-7,"output_price":0.0000025,"input_price_per_million":0.5,"output_price_per_million":2.5,"input":0.5,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000025","input":0.5,"output":2.5,"prompt_per_million":0.5,"completion_per_million":2.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000025","per_input_token":5e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":55.7},"nvidia/nemotron-3-ultra-550b-a55b:thinking":{"totalParams":550,"activeParams":55,"name":"Nvidia Nemotron 3 Ultra 550B Thinking","model":"nvidia/nemotron-3-ultra-550b-a55b:thinking","description":"Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context. Thinking enabled.","cost":"Average cost: $0.0015","costEstimate":0.0015,"dateAdded":"2026-06-04","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":1000000,"maxOutputTokens":65536,"labelVariant":"outline","category":"More","tags":["Thinking"],"capabilities":["reasoning","tool-calling","parallel-tool-calls"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.0000025,"input_price_per_million":0.5,"output_price_per_million":2.5,"input":0.5,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000025","input":0.5,"output":2.5,"prompt_per_million":0.5,"completion_per_million":2.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000025","per_input_token":5e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":653.8},"TEE/qwen3.8-27b":{"totalParams":27,"name":"Qwen3.8 27B TEE","model":"TEE/qwen3.8-27b","description":"Qwen3.8 27B is an open-weight dense vision-language model from Alibaba for reasoning, coding, professional workflows, multimodal interaction, tool use, and structured output. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Input $0.40/m, Cached input $0.15/m, Output $3/m","costEstimate":0.0017,"label":"TEE","labelColor":"green","provider":"qwen","visible":true,"isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":262144,"category":"Private/TEE","dateAdded":"2026-08-24","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.000003,"input_price_per_million":0.4,"output_price_per_million":3,"input":0.4,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.000003","input":0.4,"output":3,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":0.4,"completion_per_million":3,"prompt_per_token":"0.0000004","completion_per_token":"0.000003","per_input_token":4e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":300.6},"TEE/qwen3.6-27b":{"totalParams":27,"name":"Qwen3.6 27B TEE","model":"TEE/qwen3.6-27b","description":"Qwen3.6 27B is a dense language model from Alibaba's Qwen team with text and image input, configurable thinking/reasoning behavior, and a native 262K context window. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0015","costEstimate":0.00151,"label":"TEE","labelColor":"green","provider":"qwen","visible":true,"isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-06-04","capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.2e-7,"output_price":0.0000027,"input_price_per_million":0.32,"output_price_per_million":2.7,"input":0.32,"output":2.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000032","completion":"0.0000027","input":0.32,"output":2.7,"prompt_per_million":0.32,"completion_per_million":2.7,"prompt_per_token":"0.00000032","completion_per_token":"0.0000027","per_input_token":3.2e-7,"per_output_token":0.0000027},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00032,"outputPer1kTokens":0.0027},"effective_price":{"inputPer1kTokens":0.00032,"outputPer1kTokens":0.0027},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":244.7},"elorian/glimpse":{"name":"Elorian Glimpse","model":"elorian/glimpse","description":"Glimpse is Elorian's visual reasoning model for understanding images and video and answering in text. It can analyze charts, count objects, follow events over time, and reason about spatial relationships and physical cause and effect. It supports tool calling and structured output across a shared 262,144-token context window, with up to 256,000 output tokens within the remaining context.","provider":"elorian","visible":true,"dateAdded":"2026-10-17","cost":"Input $0.63/m, Cached input $0.063/m, Output $3.15/m","costEstimate":0.00315,"maxInputTokens":262144,"maxOutputTokens":256000,"category":"More","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"tags":["vision","video","reasoning"],"defaultSettings":{"stream":true},"api":"chat","input_price":6.3e-7,"output_price":0.00000315,"input_price_per_million":0.63,"output_price_per_million":3.15,"input":0.63,"output":3.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000063","completion":"0.00000315","input":0.63,"output":3.15,"cacheReadInputPer1kTokens":0.000063,"prompt_per_million":0.63,"completion_per_million":3.15,"prompt_per_token":"0.00000063","completion_per_token":"0.00000315","per_input_token":6.3e-7,"per_output_token":0.00000315},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00063,"outputPer1kTokens":0.00315,"cacheReadInputPer1kTokens":0.000063},"effective_price":{"inputPer1kTokens":0.00063,"outputPer1kTokens":0.00315,"cacheReadInputPer1kTokens":0.000063},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":2771.1},"liquid/lfm-2.5-24b-a2b":{"name":"LFM2.5 24B A2B","label":"Data Used for Training","labelColor":"red","labelVariant":"outline","model":"liquid/lfm-2.5-24b-a2b","description":"Liquid AI's text-only mixture-of-experts model for reasoning and tool-using agents, with 24B total and 2.45B active parameters. It always thinks before answering and supports structured output. Pair it with retrieval for knowledge-heavy tasks. Open weights use the LFM Open License v1.0, with a $10M annual-revenue commercial threshold; hosted API use is subject to separate service terms that permit retention and use of prompts and responses for model training.","provider":"liquid","totalParams":24,"activeParams":2.45,"visible":true,"dateAdded":"2026-10-14","cost":"Input $0.05/m, Cached input $0.025/m, Output $0.70/m","costEstimate":0.0007,"maxInputTokens":128000,"maxOutputTokens":8192,"category":"More","capabilities":["reasoning","tool-calling","structured-output"],"defaultThinkingEnabled":true,"tags":["reasoning","tools"],"defaultSettings":{"stream":true,"temperature":0.1,"topK":50,"repetitionPenalty":1.05},"api":"chat","input_price":5e-8,"output_price":7e-7,"input_price_per_million":0.05,"output_price_per_million":0.7,"input":0.05,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.0000007","input":0.05,"output":0.7,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.05,"completion_per_million":0.7,"prompt_per_token":"0.00000005","completion_per_token":"0.0000007","per_input_token":5e-8,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0007,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0007,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":5081.9},"liquid/lfm-2.5-2.6b":{"totalParams":2.6,"name":"LFM2.5 2.6B","model":"liquid/lfm-2.5-2.6b:free","description":"Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.","cost":"Input $0.10/m, Output $0.20/m","costEstimate":0.0002,"provider":"other","visible":true,"dateAdded":"2026-08-12","maxInputTokens":128000,"maxOutputTokens":32768,"isOpenSource":true,"category":"More","label":"Data Used for Training","labelColor":"red","labelVariant":"outline","capabilities":["reasoning","tool-calling","structured-output"],"tags":["chat","reasoning","tools","long context","training opt-in"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"api":"chat","input_price":1e-7,"output_price":2e-7,"input_price_per_million":0.1,"output_price_per_million":0.2,"input":0.1,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000002","input":0.1,"output":0.2,"prompt_per_million":0.1,"completion_per_million":0.2,"prompt_per_token":"0.0000001","completion_per_token":"0.0000002","per_input_token":1e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":458.8},"meta/muse-glimmer-30b":{"totalParams":30,"name":"Muse Glimmer 30B","model":"meta/muse-glimmer-30b","description":"Meta's Muse Glimmer 30B is a dense, open-weight multimodal model distilled from Muse Spark for long-horizon agents and coding workflows. It supports multi-step reasoning, reliable tool use, failure recovery, image understanding, and more than 100 languages.","cost":"Input $0.35/m, Cached input $0.04/m, Output $1.50/m","costEstimate":0.0015,"provider":"meta","isOpenSource":true,"visible":true,"category":"More","dateAdded":"2026-08-11","maxInputTokens":131072,"maxOutputTokens":131072,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","coding","agents","multilingual"],"api":"chat","input_price":3.5e-7,"output_price":0.0000015,"input_price_per_million":0.35,"output_price_per_million":1.5,"input":0.35,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000035","completion":"0.0000015","input":0.35,"output":1.5,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.35,"completion_per_million":1.5,"prompt_per_token":"0.00000035","completion_per_token":"0.0000015","per_input_token":3.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":682.4},"meta/muse-spark-1.2-contributor":{"name":"Muse Spark 1.2 Contributor","model":"meta/muse-spark-1.2-contributor","description":"A much cheaper opt-in version of Muse Spark 1.2 with the same multimodal coding and agentic capabilities. Prompts and outputs sent to this Contributor model may be used by Meta for training and to improve its products; use the standard Muse Spark 1.2 model if you do not want your data used for training.","cost":"Input $0.10/m, Cached input $0.002/m, Output $0.20/m","costEstimate":0.0002,"provider":"meta","visible":true,"dateAdded":"2026-08-05","maxInputTokens":1000000,"maxOutputTokens":65536,"maxImageInputs":50,"category":"More","label":"Training Opt-In","labelColor":"red","labelVariant":"outline","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","parallel-tool-calls","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","coding","agents","long context","training opt-in"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":2e-7,"input_price_per_million":0.1,"output_price_per_million":0.2,"input":0.1,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000002","input":0.1,"output":0.2,"cacheReadInputPer1kTokens":0.000002,"prompt_per_million":0.1,"completion_per_million":0.2,"prompt_per_token":"0.0000001","completion_per_token":"0.0000002","per_input_token":1e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000002},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":2774.5},"meta/muse-spark-1.2":{"name":"Muse Spark 1.2","model":"meta/muse-spark-1.2","description":"Meta's Muse Spark 1.2 is a multimodal reasoning model for complex agentic and coding tasks, with tool calling, structured output, and a one-million-token context window.","cost":"Input $1.25/m, Cached input $0.15/m, Output $4.25/m","costEstimate":0.00425,"provider":"meta","visible":true,"dateAdded":"2026-08-05","maxInputTokens":1000000,"maxOutputTokens":65536,"maxImageInputs":50,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","parallel-tool-calls","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","coding","agents","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00000125,"output_price":0.00000425,"input_price_per_million":1.25,"output_price_per_million":4.25,"input":1.25,"output":4.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00000425","input":1.25,"output":4.25,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":1.25,"completion_per_million":4.25,"prompt_per_token":"0.00000125","completion_per_token":"0.00000425","per_input_token":0.00000125,"per_output_token":0.00000425},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":172},"meta/muse-spark-1.1":{"name":"Muse Spark 1.1","model":"meta/muse-spark-1.1","description":"Meta's Muse Spark 1.1 is a long-context multimodal reasoning model served by the Meta Model API.","cost":"Input $1.25/m, Cached input $0.15/m, Output $4.25/m","costEstimate":0.00425,"provider":"meta","visible":true,"dateAdded":"2026-07-09","maxInputTokens":1000000,"maxOutputTokens":65536,"maxImageInputs":50,"category":"More","capabilities":["vision","reasoning","video-input","audio-input"],"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"tags":["chat","reasoning","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00000125,"output_price":0.00000425,"input_price_per_million":1.25,"output_price_per_million":4.25,"input":1.25,"output":4.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00000425","input":1.25,"output":4.25,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":1.25,"completion_per_million":4.25,"prompt_per_token":"0.00000125","completion_per_token":"0.00000425","per_input_token":0.00000125,"per_output_token":0.00000425},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.00425,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":460},"longcat-2.5-preview":{"name":"LongCat 2.5 Preview","model":"meituan/longcat-2.5-preview","description":"LongCat 2.5 Preview is Meituan's multimodal model for long-context analysis, coding, and agent workflows. It supports image input, tool calling, optional extended thinking, a 1M-token context window, and up to 128K output tokens.","cost":"Input $0.75/m, cached input $0.015/m, output $2.95/m","costEstimate":0.00295,"provider":"longcat","visible":true,"dateAdded":"2026-09-27","maxInputTokens":1000000,"maxOutputTokens":131072,"category":"More","capabilities":["vision","reasoning","tool-calling"],"tags":["chat","reasoning","coding","agents","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled"}},"additionalParams":{"thinking":{"type":"enabled","supportsBudget":false}},"api":"chat","input_price":7.5e-7,"output_price":0.00000295,"input_price_per_million":0.75,"output_price_per_million":2.95,"input":0.75,"output":2.95,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.00000295","input":0.75,"output":2.95,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.75,"completion_per_million":2.95,"prompt_per_token":"0.00000075","completion_per_token":"0.00000295","per_input_token":7.5e-7,"per_output_token":0.00000295},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00295,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00295,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":2008.7},"longcat-2.0":{"totalParams":1600,"activeParams":48,"name":"LongCat 2.0","model":"longcat-2.0","description":"Meituan's LongCat 2.0 is an open-weight agentic model for coding, tool use, and long-context workflow automation, with reasoning disabled for faster direct answers.","cost":"Input $0.75/m, Output $3/m","costEstimate":0.001875,"provider":"longcat","visible":true,"dateAdded":"2026-06-30","maxInputTokens":1000000,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","capabilities":["tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":7.5e-7,"output_price":0.000003,"input_price_per_million":0.75,"output_price_per_million":3,"input":0.75,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.000003","input":0.75,"output":3,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.75,"completion_per_million":3,"prompt_per_token":"0.00000075","completion_per_token":"0.000003","per_input_token":7.5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":367.8},"longcat-2.0:thinking":{"totalParams":1600,"activeParams":48,"name":"LongCat 2.0 Thinking","model":"longcat-2.0:thinking","description":"Meituan's LongCat 2.0 Thinking is the reasoning-enabled variant for harder coding, tool use, multi-step reasoning, and long-context agent workflows.","cost":"Input $0.75/m, Output $3/m","costEstimate":0.001875,"provider":"longcat","visible":true,"dateAdded":"2026-07-21","maxInputTokens":1000000,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","capabilities":["reasoning","tool-calling"],"tags":["Thinking"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"enabled"}},"api":"chat","input_price":7.5e-7,"output_price":0.000003,"input_price_per_million":0.75,"output_price_per_million":3,"input":0.75,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.000003","input":0.75,"output":3,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.75,"completion_per_million":3,"prompt_per_token":"0.00000075","completion_per_token":"0.000003","per_input_token":7.5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":1078.6},"stepfun/step-5-preview":{"totalParams":600,"activeParams":27,"name":"Step 5 Preview","model":"stepfun/step-5-preview","description":"Step 5 Preview is StepFun's 600B sparse MoE frontier model for production-scale agents, activating 27B parameters per token. It is built for software engineering, long-horizon tool use, research, professional knowledge work, and finance, with native text, image, and video understanding and a 1M-token context window. ⚠️ Note: This model routes through StepFun, so privacy and logging guarantees may be limited.","cost":"Input $1/m, Cached input $0.05/m, Output $2.70/m","costEstimate":0.00185,"provider":"stepfun","visible":true,"dateAdded":"2026-09-20","isOpenSource":false,"maxInputTokens":1000000,"maxOutputTokens":65536,"maxImageInputs":60,"capabilities":["vision","video-input","reasoning","tool-calling","parallel-tool-calls","structured-output"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"tags":["chat","reasoning","coding","agents","finance","vision","video","tools","long context"],"api":"chat","input_price":0.000001,"output_price":0.0000027,"input_price_per_million":1,"output_price_per_million":2.7,"input":1,"output":2.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.0000027","input":1,"output":2.7,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":1,"completion_per_million":2.7,"prompt_per_token":"0.000001","completion_per_token":"0.0000027","per_input_token":0.000001,"per_output_token":0.0000027},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0027,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0027,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":1476.9},"stepfun/step-3.7-flash:thinking":{"totalParams":198,"activeParams":11,"name":"Step 3.7 Flash Thinking","model":"stepfun/step-3.7-flash:thinking","description":"Step 3.7 Flash Thinking is StepFun's high-efficiency multimodal MoE model with visible reasoning enabled for deeper agentic coding, long-context reasoning, tool use, and native image/video understanding. ⚠️ Note: This model routes through StepFun, so privacy and logging guarantees may be limited.","cost":"Input $0.20/m, Output $1.15/m","costEstimate":0.00115,"provider":"stepfun","visible":true,"dateAdded":"2026-05-29","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":256000,"capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":2e-7,"output_price":0.00000115,"input_price_per_million":0.2,"output_price_per_million":1.15,"input":0.2,"output":1.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.00000115","input":0.2,"output":1.15,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.2,"completion_per_million":1.15,"prompt_per_token":"0.0000002","completion_per_token":"0.00000115","per_input_token":2e-7,"per_output_token":0.00000115},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00115,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00115,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":7058.1},"perceptron/perceptron-mk1.5":{"name":"Perceptron Mk1.5","model":"perceptron/perceptron-mk1.5","description":"Perceptron Mk1.5 is a multimodal reasoning model for visual analysis and physical agents. It accepts text, images, video, and audio, supports tool calling and structured output, and can return spatial annotations such as points, boxes, polygons, and tracks.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"perceptron","visible":true,"category":"More","dateAdded":"2026-09-25","maxInputTokens":36864,"maxOutputTokens":8192,"capabilities":["vision","video-input","audio-input","tool-calling","reasoning","structured-output"],"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"api":"chat","input_price":1.5e-7,"output_price":0.0000015,"input_price_per_million":0.15,"output_price_per_million":1.5,"input":0.15,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000015","input":0.15,"output":1.5,"prompt_per_million":0.15,"completion_per_million":1.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000015","per_input_token":1.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"},"avgOutputTokens":81.2},"perceptron/perceptron-mk1":{"name":"Perceptron Mk1","model":"perceptron/perceptron-mk1","description":"Perceptron Mk1 is Perceptron's vision-language model for image and video understanding, OCR, document parsing, object detection, counting, spatial localization, and embodied visual reasoning.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"perceptron","visible":true,"category":"More","dateAdded":"2026-05-12","maxInputTokens":32768,"maxOutputTokens":8192,"capabilities":["vision","video-input","reasoning","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":0.0000015,"input_price_per_million":0.15,"output_price_per_million":1.5,"input":0.15,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000015","input":0.15,"output":1.5,"prompt_per_million":0.15,"completion_per_million":1.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000015","per_input_token":1.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.358Z"}},"reka/reka-edge-2603":{"name":"Reka Edge 2603","model":"reka/reka-edge-2603","description":"Reka's compact multimodal model for visual understanding and tool use, served directly by Reka.","cost":"Input $0.105/m, Output $0.105/m","costEstimate":0.000105,"provider":"reka-direct","visible":true,"dateAdded":"2026-10-15","category":"More","maxInputTokens":16384,"maxOutputTokens":16384,"capabilities":["vision","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["chat","vision","tools"],"api":"chat","input_price":1.05e-7,"output_price":1.05e-7,"input_price_per_million":0.105,"output_price_per_million":0.105,"input":0.105,"output":0.105,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000105","completion":"0.000000105","input":0.105,"output":0.105,"prompt_per_million":0.105,"completion_per_million":0.105,"prompt_per_token":"0.000000105","completion_per_token":"0.000000105","per_input_token":1.05e-7,"per_output_token":1.05e-7,"cacheReadInputPer1kTokens":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000105,"outputPer1kTokens":0.000105,"cacheReadInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000105,"outputPer1kTokens":0.000105,"cacheReadInputPer1kTokens":0},"pricing_type":"observed","currency":"USD","unit":"per_1k_tokens","source":"provider_catalog"},"avgOutputTokens":29.8,"disabled":false},"reka/reka-flash-3":{"name":"Reka Flash 3","model":"reka/reka-flash-3","description":"Reka's 21B reasoning model for chat and coding, served directly by Reka.","cost":"Input $0.105/m, Output $0.21/m","costEstimate":0.00021,"provider":"reka-direct","visible":true,"isOpenSource":true,"dateAdded":"2026-10-15","category":"More","maxInputTokens":65536,"maxOutputTokens":65536,"toolCallingUnsupported":true,"capabilities":["reasoning","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["chat","reasoning","coding"],"api":"chat","input_price":1.05e-7,"output_price":2.1e-7,"input_price_per_million":0.105,"output_price_per_million":0.21,"input":0.105,"output":0.21,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000105","completion":"0.00000021","input":0.105,"output":0.21,"prompt_per_million":0.105,"completion_per_million":0.21,"prompt_per_token":"0.000000105","completion_per_token":"0.00000021","per_input_token":1.05e-7,"per_output_token":2.1e-7,"cacheReadInputPer1kTokens":0},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000105,"outputPer1kTokens":0.00021,"cacheReadInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000105,"outputPer1kTokens":0.00021,"cacheReadInputPer1kTokens":0},"pricing_type":"observed","currency":"USD","unit":"per_1k_tokens","source":"provider_catalog"},"avgOutputTokens":2715.3,"disabled":false},"sakana/fugu-ultra":{"name":"Fugu Ultra","model":"sakana/fugu-ultra","description":"Sakana AI's higher-quality Fugu model. It coordinates a deeper pool of expert agents for hard, high-stakes reasoning and coding tasks.","cost":"Input $5/m, Output $30/m, Cached input $0.50/m","costEstimate":0.03,"provider":"sakana","visible":true,"maxInputTokens":1000000,"maxOutputTokens":16384,"category":"More","dateAdded":"2026-06-22","capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["high","xhigh","max"]}},"tags":["chat","reasoning","agent"],"api":"chat","input_price":0.000005,"output_price":0.00003,"input_price_per_million":5,"output_price_per_million":30,"input":5,"output":30,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.00003","input":5,"output":30,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":30,"prompt_per_token":"0.000005","completion_per_token":"0.00003","per_input_token":0.000005,"per_output_token":0.00003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.03,"inputPer1kTokensAbove200k":0.01,"outputPer1kTokensAbove200k":0.045,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.03,"inputPer1kTokensAbove200k":0.01,"outputPer1kTokensAbove200k":0.045,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"},"avgOutputTokens":32.9},"sakana/fugu-ultra-v1.1":{"name":"Fugu Ultra v1.1","model":"sakana/fugu-ultra-v1.1","description":"Sakana AI's upgraded Fugu Ultra release with stronger coding, agentic task execution, and advanced reasoning through dynamic orchestration of frontier models.","cost":"Input $5/m, Output $30/m, Cached input $0.50/m","costEstimate":0.03,"provider":"sakana","visible":true,"maxInputTokens":1000000,"maxOutputTokens":16384,"category":"More","dateAdded":"2026-07-24","capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["high","xhigh","max"]}},"tags":["chat","reasoning","agent","coding"],"api":"chat","input_price":0.000005,"output_price":0.00003,"input_price_per_million":5,"output_price_per_million":30,"input":5,"output":30,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.00003","input":5,"output":30,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":30,"prompt_per_token":"0.000005","completion_per_token":"0.00003","per_input_token":0.000005,"per_output_token":0.00003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.03,"inputPer1kTokensAbove200k":0.01,"outputPer1kTokensAbove200k":0.045,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.03,"inputPer1kTokensAbove200k":0.01,"outputPer1kTokensAbove200k":0.045,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"}},"sakana/fugu-max":{"name":"Fugu Max","model":"sakana/fugu-max","description":"Sakana AI's cost-performance Fugu model uses learned multi-agent orchestration to route tasks across expert models for reasoning, coding, and tool use.","cost":"Input $2/m, Output $6/m, Cached input $0.25/m","costEstimate":0.006,"provider":"sakana","visible":true,"maxInputTokens":1000000,"maxOutputTokens":128000,"category":"More","dateAdded":"2026-09-11","capabilities":["vision","pdf-upload","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["high","xhigh","max"]}},"tags":["chat","reasoning","agent","coding"],"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"},"avgOutputTokens":2164.6},"bytedance/doubao-seed-character":{"name":"Doubao Seed Character","model":"bytedance/doubao-seed-character","description":"ByteDance's character-focused Doubao Seed model for roleplay, persona consistency, dialogue, and creative character interactions. It supports text and image input with a 128k context window. Requests route through ZenMux to ByteDance; ZenMux does not publish a model-API zero-retention or training guarantee, so avoid sensitive data.","cost":"Input $0.15/m, Cached input $0.03/m, Output $0.37/m; above 32k input: $0.22/m, Output $1.10/m","costEstimate":0.00037,"provider":"doubao","visible":true,"maxInputTokens":128000,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","dateAdded":"2026-07-18","capabilities":["vision","reasoning"],"toolCallingUnsupported":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning":{"enabled":true,"exclude":false,"effort":"high"}},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"tags":["chat","roleplay","character","reasoning"],"api":"chat","input_price":1.5e-7,"output_price":3.7e-7,"input_price_per_million":0.15,"output_price_per_million":0.37,"input":0.15,"output":0.37,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000037","input":0.15,"output":0.37,"cacheReadInputPer1kTokens":0.00003,"prompt_per_million":0.15,"completion_per_million":0.37,"prompt_per_token":"0.00000015","completion_per_token":"0.00000037","per_input_token":1.5e-7,"per_output_token":3.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00037,"inputPer1kTokensAbove200k":0.00022,"outputPer1kTokensAbove200k":0.0011,"highContextThresholdTokens":32000,"cacheReadInputPer1kTokens":0.00003,"cacheWriteInputPer1kTokens":0.000003},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00037,"inputPer1kTokensAbove200k":0.00022,"outputPer1kTokensAbove200k":0.0011,"highContextThresholdTokens":32000,"cacheReadInputPer1kTokens":0.00003,"cacheWriteInputPer1kTokens":0.000003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"},"avgOutputTokens":214.7},"reflection/beam-1.0":{"name":"Beam 1.0 501B A23B","defaultThinkingEnabled":true,"defaultReasoningEffort":"max","model":"reflection/beam-1.0","description":"Reflection's Apache 2.0 open-weight text model with 501.3B total and 23.4B active parameters, built for coding, reasoning and tool use. It supports a shared 1,048,576-token context window, up to 131,072 output tokens, JSON mode and structured output. Reasoning is always enabled with low, medium, high, xhigh and max effort; NanoGPT defaults to max. Knowledge cutoff: June 30, 2026.","totalParams":501.3,"activeParams":23.4,"cost":"Input $0.50/m, Output $1.50/m, Cached input $0.05/m","costEstimate":0.0015,"provider":"nanogpt","visible":true,"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","dateAdded":"2026-10-16","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"isOpenSource":true,"tags":["chat","coding","reasoning","agent"],"api":"chat","input_price":5e-7,"output_price":0.0000015,"input_price_per_million":0.5,"output_price_per_million":1.5,"input":0.5,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000015","input":0.5,"output":1.5,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.5,"completion_per_million":1.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000015","per_input_token":5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"},"avgOutputTokens":2041.9},"thinkingmachines/inkling":{"totalParams":975,"activeParams":41,"name":"Inkling","model":"thinkingmachines/inkling","description":"The non-thinking version of Thinking Machines' 975B-parameter open-weights Mixture-of-Experts generalist with 41B active parameters. It gives faster direct answers across text, images, and audio, and is built for agentic coding, tool use, detailed instruction following, and long-context work.","cost":"Input $1.70/m, Output $6.89/m, Cached input $0.29/m","costEstimate":0.006885,"provider":"baseten","visible":true,"maxInputTokens":1048000,"maxOutputTokens":32768,"category":"More","dateAdded":"2026-07-15","capabilities":["vision","audio-input","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"isOpenSource":true,"tags":["chat","vision","audio","coding","agent"],"api":"chat","input_price":0.000001,"output_price":0.00000405,"input_price_per_million":1,"output_price_per_million":4.05,"input":1,"output":4.05,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.00000405","input":1,"output":4.05,"cacheReadInputPer1kTokens":0.00017,"prompt_per_million":1,"completion_per_million":4.05,"prompt_per_token":"0.000001","completion_per_token":"0.00000405","per_input_token":0.000001,"per_output_token":0.00000405},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.00405,"cacheReadInputPer1kTokens":0.00017},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.00405,"cacheReadInputPer1kTokens":0.00017},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"},"avgOutputTokens":596},"thinkingmachines/inkling:thinking":{"totalParams":975,"activeParams":41,"name":"Inkling Thinking","model":"thinkingmachines/inkling:thinking","description":"The thinking version of Thinking Machines' 975B-parameter open-weights Mixture-of-Experts generalist with 41B active parameters. It reasons natively over text, images, and audio, and is built for agentic coding, tool use, detailed instruction following, long-context work, and controllable thinking effort.","cost":"Input $1.70/m, Output $6.89/m, Cached input $0.29/m","costEstimate":0.006885,"provider":"baseten","visible":true,"maxInputTokens":1048000,"maxOutputTokens":32768,"category":"More","dateAdded":"2026-07-15","capabilities":["vision","audio-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","xhigh"]}},"isOpenSource":true,"tags":["chat","reasoning","vision","audio","coding","agent"],"api":"chat","input_price":0.000001,"output_price":0.00000405,"input_price_per_million":1,"output_price_per_million":4.05,"input":1,"output":4.05,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.00000405","input":1,"output":4.05,"cacheReadInputPer1kTokens":0.00017,"prompt_per_million":1,"completion_per_million":4.05,"prompt_per_token":"0.000001","completion_per_token":"0.00000405","per_input_token":0.000001,"per_output_token":0.00000405},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.00405,"cacheReadInputPer1kTokens":0.00017},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.00405,"cacheReadInputPer1kTokens":0.00017},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"},"avgOutputTokens":1176.7},"claw-high":{"name":"Claw High","model":"claw-high","description":"Currently points to GLM 5.3. OpenClaw compatibility alias for long-horizon agent, coding, and engineering workflows.","cost":"Input $1.00/m, Output $3.20/m","costEstimate":0.0042,"category":"More","labelVariant":"outline","provider":"nanogpt","maxInputTokens":1048576,"maxOutputTokens":131072,"visible":true,"dateAdded":"2026-05-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"}},"claw-medium":{"name":"Claw Medium","model":"claw-medium","description":"Currently points to GLM 5.3. OpenClaw compatibility alias for long-horizon agent, coding, and engineering workflows.","cost":"Input $1.00/m, Output $3.20/m","costEstimate":0.0042,"category":"More","labelVariant":"outline","provider":"nanogpt","maxInputTokens":1048576,"maxOutputTokens":131072,"visible":true,"dateAdded":"2026-05-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"}},"claw-low":{"name":"Claw Low","model":"claw-low","description":"Currently points to GLM 5.3. OpenClaw compatibility alias for long-horizon agent, coding, and engineering workflows.","cost":"Input $1.00/m, Output $3.20/m","costEstimate":0.0042,"category":"More","labelVariant":"outline","provider":"nanogpt","maxInputTokens":1048576,"maxOutputTokens":131072,"visible":true,"dateAdded":"2026-05-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.359Z"}},"hermes-high":{"name":"Hermes High","model":"hermes-high","description":"Currently points to GLM 5.3. Hermes compatibility alias for long-horizon agent, coding, and engineering workflows.","cost":"Input $1.00/m, Output $3.20/m","costEstimate":0.0042,"category":"More","labelVariant":"outline","provider":"nanogpt","maxInputTokens":1048576,"maxOutputTokens":131072,"visible":true,"dateAdded":"2026-05-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"}},"hermes-medium":{"name":"Hermes Medium","model":"hermes-medium","description":"Currently points to GLM 5.3. Hermes compatibility alias for long-horizon agent, coding, and engineering workflows.","cost":"Input $1.00/m, Output $3.20/m","costEstimate":0.0042,"category":"More","labelVariant":"outline","provider":"nanogpt","maxInputTokens":1048576,"maxOutputTokens":131072,"visible":true,"dateAdded":"2026-05-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"}},"hermes-low":{"name":"Hermes Low","model":"hermes-low","description":"Currently points to GLM 5.3. Hermes compatibility alias for long-horizon agent, coding, and engineering workflows.","cost":"Input $1.00/m, Output $3.20/m","costEstimate":0.0042,"category":"More","labelVariant":"outline","provider":"nanogpt","maxInputTokens":1048576,"maxOutputTokens":131072,"visible":true,"dateAdded":"2026-05-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"}},"fastgpt":{"name":"Web Answer","model":"fastgpt","description":"Fast web answers with citations, tuned for factual questions and quick summaries.","cost":"Fixed cost: $0.015","costEstimate":0.015,"dateAdded":"2025-12-23","provider":"kagi","category":"More","visible":true,"maxOutputTokens":32768,"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000075,"output_price":0.0000075,"input_price_per_million":7.5,"output_price_per_million":7.5,"input":7.5,"output":7.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000075","completion":"0.0000075","input":7.5,"output":7.5,"prompt_per_million":7.5,"completion_per_million":7.5,"prompt_per_token":"0.0000075","completion_per_token":"0.0000075","per_input_token":0.0000075,"per_output_token":0.0000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0075,"outputPer1kTokens":0.0075},"effective_price":{"inputPer1kTokens":0.0075,"outputPer1kTokens":0.0075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"}},"universal-summarizer":{"name":"Universal Summarizer","model":"universal-summarizer","description":"Summarizes long-form text or URLs across formats with large context support.","cost":"Estimated cost: $0.03 / 1K tokens","costEstimate":0.03,"dateAdded":"2025-12-23","provider":"kagi","category":"More","visible":true,"maxOutputTokens":32768,"defaultSettings":{"stream":false,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00003,"output_price":0.00003,"input_price_per_million":30,"output_price_per_million":30,"input":30,"output":30,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00003","completion":"0.00003","input":30,"output":30,"prompt_per_million":30,"completion_per_million":30,"prompt_per_token":"0.00003","completion_per_token":"0.00003","per_input_token":0.00003,"per_output_token":0.00003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.03,"outputPer1kTokens":0.03},"effective_price":{"inputPer1kTokens":0.03,"outputPer1kTokens":0.03},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"}},"openai/gpt-oss-120b":{"totalParams":120,"activeParams":5.1,"name":"GPT OSS 120B","model":"openai/gpt-oss-120b","description":"An open-weight, 117B-parameter Mixture-of-Experts (MoE) language model designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","cost":"Average cost: $0.0018","costEstimate":0.0018,"dateAdded":"2026-02-03","provider":"openai","visible":true,"isOpenSource":true,"category":"More","capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":16384,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.5e-7,"output_price":7.5e-7,"input_price_per_million":0.35,"output_price_per_million":0.75,"input":0.35,"output":0.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000035","completion":"0.00000075","input":0.35,"output":0.75,"prompt_per_million":0.35,"completion_per_million":0.75,"prompt_per_token":"0.00000035","completion_per_token":"0.00000075","per_input_token":3.5e-7,"per_output_token":7.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.00075},"effective_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.00075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":1114.6},"openai/gpt-oss-safeguard-20b":{"totalParams":20,"activeParams":3.6,"name":"GPT OSS Safeguard 20B","model":"openai/gpt-oss-safeguard-20b","description":"gpt-oss-safeguard is a first open weight reasoning model specifically trained for safety classification tasks to help classify text content based on customizable policies. As a fine-tuned version of gpt-oss, gpt-oss-safeguard is designed to follow explicit written policies that you provide. This enables bring-your-own-policy Trust & Safety AI, where your own taxonomy, definitions, and thresholds guide classification decisions. Well crafted policies unlock gpt-oss-safeguard's reasoning capabilities, enabling it to handle nuanced content, explain borderline decisions, and adapt to contextual factors.","cost":"Average cost: $0.001","costEstimate":0.001,"dateAdded":"2026-02-23","provider":"openai","visible":true,"category":"More","isOpenSource":true,"capabilities":["reasoning"],"maxInputTokens":128000,"maxOutputTokens":16384,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.5e-8,"output_price":3e-7,"input_price_per_million":0.075,"output_price_per_million":0.3,"input":0.075,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000075","completion":"0.0000003","input":0.075,"output":0.3,"prompt_per_million":0.075,"completion_per_million":0.3,"prompt_per_token":"0.000000075","completion_per_token":"0.0000003","per_input_token":7.5e-8,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":98},"openai/gpt-oss-20b":{"totalParams":20,"activeParams":3.6,"name":"GPT OSS 20B","model":"openai/gpt-oss-20b","description":"An open-weight 21B parameter model released under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI's Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"openai","category":"More","isOpenSource":true,"visible":true,"dateAdded":"2025-08-05","capabilities":["reasoning"],"maxInputTokens":128000,"maxOutputTokens":16384,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":3e-7,"input_price_per_million":0.2,"output_price_per_million":0.3,"input":0.2,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000003","input":0.2,"output":0.3,"prompt_per_million":0.2,"completion_per_million":0.3,"prompt_per_token":"0.0000002","completion_per_token":"0.0000003","per_input_token":2e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":1921.9},"anthropic/claude-sonnet-5.5":{"name":"Claude Sonnet 5.5","model":"anthropic/claude-sonnet-5.5","description":"Claude Sonnet 5.5 handles everyday coding, tool-based workflows, visual analysis, and polished writing with a 1M-token context window. This version skips up-front thinking and can reason between tool calls for faster responses; use Thinking for deeper planning and complex problems.","cost":"Average cost: $0.0175","costEstimate":0.0175,"labelVariant":"outline","provider":"anthropic","visible":true,"dateAdded":"2026-09-28","category":"More","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"minP":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"between_tools"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]},"thinking":{"type":"between_tools"},"output_config":{"effort":"high"}},"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":523.2},"anthropic/claude-sonnet-5.5:thinking":{"name":"Claude Sonnet 5.5 Thinking","model":"anthropic/claude-sonnet-5.5:thinking","description":"Claude Sonnet 5.5 with adaptive thinking for complex coding, multi-step tool use, visual analysis, and detailed planning. Supports a 1M-token context window and five reasoning effort levels, with stronger thinking available when a task needs it.","cost":"Average cost: $0.0267","costEstimate":0.0267,"provider":"anthropic","visible":true,"dateAdded":"2026-09-28","category":"More","labelVariant":"outline","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"minP":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"adaptive"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","disabledType":"between_tools"},"output_config":{"effort":"high"}},"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":2978.2},"anthropic/claude-sonnet-5":{"name":"Claude Sonnet 5","model":"anthropic/claude-sonnet-5","description":"Claude Sonnet 5 supports coding, agentic workflows, long-context reasoning, computer use, and practical knowledge work.","cost":"Average cost: $0.0175","costEstimate":0.0175,"labelVariant":"outline","provider":"anthropic","visible":true,"dateAdded":"2026-06-30","category":"More","capabilities":["vision","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":291.1},"anthropic/claude-sonnet-5:thinking":{"name":"Claude Sonnet 5 Thinking","model":"anthropic/claude-sonnet-5:thinking","description":"Claude Sonnet 5 with adaptive thinking enabled for complex coding, planning, and agentic work.","cost":"Average cost: $0.0267","costEstimate":0.0267,"provider":"anthropic","visible":true,"dateAdded":"2026-06-30","category":"More","labelVariant":"outline","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive"},"output_config":{"effort":"high"}},"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":2610.9},"anthropic/claude-sonnet-latest":{"name":"Claude Sonnet Latest","model":"anthropic/claude-sonnet-latest","description":"Compatibility alias that routes to the newest version of Claude Sonnet. Currently routes to Claude Sonnet 5.5 Thinking.","cost":"Average cost: $0.0267","costEstimate":0.0267,"dateAdded":"2026-03-01","provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"minP":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"adaptive"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","disabledType":"between_tools"},"output_config":{"effort":"high"}},"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":1030.5},"claude-sonnet-4-5-20250929":{"name":"Claude Sonnet 4.5","model":"anthropic/claude-sonnet-4.5","description":"Frontier‑level coding and agentic performance. Claude Sonnet 4.5 leads on real‑world coding tasks and shows substantial gains in computer use, reasoning, and math. Designed for long‑horizon, multi‑step work across IDE + terminal workflows, large codebases, and complex agents — a drop‑in upgrade over previous Sonnet versions.","cost":"Average cost: $0.0263","costEstimate":0.0263,"dateAdded":"2025-09-29","labelVariant":"outline","provider":"anthropic","visible":true,"category":"More","capabilities":["vision","pdf-upload","tool-calling","structured-output","reasoning"],"maxInputTokens":200000,"maxOutputTokens":64000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000003,"output_price":0.000015,"input_price_per_million":3,"output_price_per_million":15,"input":3,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000015","input":3,"output":15,"cacheReadInputPer1kTokens":0.00030000000000000003,"prompt_per_million":3,"completion_per_million":15,"prompt_per_token":"0.000003","completion_per_token":"0.000015","per_input_token":0.000003,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":237.4},"claude-sonnet-4-5-20250929-thinking":{"name":"Claude Sonnet 4.5 Thinking","model":"anthropic/claude-sonnet-4.5:thinking","description":"Adds extended, step‑by‑step reasoning for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows, complex problem solving, and scenarios that benefit from explicit thinking traces.","cost":"Average cost: $0.04","costEstimate":0.04,"dateAdded":"2025-09-29","provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":64000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000003,"output_price":0.000015,"input_price_per_million":3,"output_price_per_million":15,"input":3,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000015","input":3,"output":15,"cacheReadInputPer1kTokens":0.00030000000000000003,"prompt_per_million":3,"completion_per_million":15,"prompt_per_token":"0.000003","completion_per_token":"0.000015","per_input_token":0.000003,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":1066},"soob3123/amoral-gemma3-27B-v2":{"totalParams":27,"name":"Amoral Gemma3 27B v2","model":"soob3123/amoral-gemma3-27B-v2","description":"Amoral Gemma3 27B v2 is a 27B parameter model that is a more advanced version of Gemma3 27B.","cost":"Average cost: $0.0010","maxInputTokens":32768,"maxOutputTokens":8192,"costEstimate":0.001,"category":"Roleplay/storytelling models","provider":"gemini","visible":true,"dateAdded":"2025-05-23","isOpenSource":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":3e-7,"input_price_per_million":0.3,"output_price_per_million":0.3,"input":0.3,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000003","input":0.3,"output":0.3,"prompt_per_million":0.3,"completion_per_million":0.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000003","per_input_token":3e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":22},"mistralai/Devstral-Small-2505":{"totalParams":24,"name":"Mistral Devstral Small 2505","model":"mistralai/devstral-small-2505","description":"OpenHands+Devstral is 100% local 100% open, and is SOTA for the category on SWE-Bench Verified: 46.8% accuracy.","cost":"Average cost: $0.0010","costEstimate":0.001,"category":"More","maxInputTokens":32768,"maxOutputTokens":8192,"provider":"mistral","visible":true,"dateAdded":"2025-08-02","isOpenSource":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-8,"output_price":6e-8,"input_price_per_million":0.06,"output_price_per_million":0.06,"input":0.06,"output":0.06,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000006","completion":"0.00000006","input":0.06,"output":0.06,"prompt_per_million":0.06,"completion_per_million":0.06,"prompt_per_token":"0.00000006","completion_per_token":"0.00000006","per_input_token":6e-8,"per_output_token":6e-8},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":125.4},"soob3123/Veiled-Calla-12B":{"totalParams":12,"name":"Veiled Calla 12B","model":"soob3123/Veiled-Calla-12B","description":"Veiled Calla 12B is a 12B parameter model that is a more advanced version of Calla 12B.","cost":"Average cost: $0.0012","costEstimate":0.0012,"maxInputTokens":32768,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","visible":true,"dateAdded":"2025-04-13","isOpenSource":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":3e-7,"input_price_per_million":0.3,"output_price_per_million":0.3,"input":0.3,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000003","input":0.3,"output":0.3,"prompt_per_million":0.3,"completion_per_million":0.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000003","per_input_token":3e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":174.5},"openai/gpt-5.6-sol":{"name":"GPT 5.6 Sol","model":"openai/gpt-5.6-sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, agentic workflows, command-line work, and multi-step professional tasks.","cost":"Average cost: $0.012","costEstimate":0.012,"dateAdded":"2026-07-09","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","sol"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.360Z"},"avgOutputTokens":576.1},"openai/gpt-5.6-terra":{"name":"GPT 5.6 Terra","model":"openai/gpt-5.6-terra","description":"GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 series, positioned between flagship Sol and cost-efficient Luna. It is suited for everyday coding, reasoning, agentic work, and general professional tasks.","cost":"Average cost: $0.014","costEstimate":0.014,"dateAdded":"2026-07-09","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","terra"],"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":556.3},"openai/gpt-5.6-terra-pro":{"name":"GPT 5.6 Terra Pro","model":"openai/gpt-5.6-terra-pro","description":"GPT-5.6 Terra with Pro reasoning mode. Pro mode performs more model work for difficult tasks; reasoning effort remains independently configurable and defaults to medium.","cost":"Average cost: $0.014","costEstimate":0.014,"dateAdded":"2026-07-09","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","terra","pro"],"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":830.8},"openai/gpt-5.6-luna":{"name":"GPT 5.6 Luna","model":"openai/gpt-5.6-luna","description":"GPT-5.6 Luna is the fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume chat, classification, lightweight agentic workflows, and latency-sensitive reasoning tasks.","cost":"Average cost: $0.0014","costEstimate":0.0014,"dateAdded":"2026-07-09","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","luna"],"api":"chat","input_price":2e-7,"output_price":0.0000012,"input_price_per_million":0.2,"output_price_per_million":1.2,"input":0.2,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000012","input":0.2,"output":1.2,"cacheReadInputPer1kTokens":0.00002,"prompt_per_million":0.2,"completion_per_million":1.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000012","per_input_token":2e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0012,"inputPer1kTokensAbove200k":0.0004,"outputPer1kTokensAbove200k":0.0018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokensAbove200k":0.0005},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0012,"inputPer1kTokensAbove200k":0.0004,"outputPer1kTokensAbove200k":0.0018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokensAbove200k":0.0005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":281.1},"openai/gpt-5.6-luna-pro":{"name":"GPT 5.6 Luna Pro","model":"openai/gpt-5.6-luna-pro","description":"GPT-5.6 Luna with Pro reasoning mode. Pro mode performs more model work for difficult tasks; reasoning effort remains independently configurable and defaults to medium.","cost":"Average cost: $0.0014","costEstimate":0.0014,"dateAdded":"2026-07-09","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","luna","pro"],"api":"chat","input_price":2e-7,"output_price":0.0000012,"input_price_per_million":0.2,"output_price_per_million":1.2,"input":0.2,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000012","input":0.2,"output":1.2,"cacheReadInputPer1kTokens":0.00002,"prompt_per_million":0.2,"completion_per_million":1.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000012","per_input_token":2e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0012,"inputPer1kTokensAbove200k":0.0004,"outputPer1kTokensAbove200k":0.0018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokensAbove200k":0.0005},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0012,"inputPer1kTokensAbove200k":0.0004,"outputPer1kTokensAbove200k":0.0018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokensAbove200k":0.0005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":1549.1},"openai/gpt-5.6-sol-pro":{"name":"GPT 5.6 Sol Pro","model":"openai/gpt-5.6-sol-pro","description":"GPT-5.6 Sol with Pro reasoning mode. Pro mode performs more model work for difficult tasks; reasoning effort remains independently configurable and defaults to medium.","cost":"Average cost: $0.012","costEstimate":0.012,"dateAdded":"2026-07-09","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","sol","pro"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":4745.1},"openai/gpt-6-astra":{"name":"GPT 6 Astra","model":"openai/gpt-6-astra","description":"OpenAI's most capable model for the hardest end-to-end work, with state-of-the-art performance in computer use, browsing, software engineering, science, and professional tasks. Astra is designed to carry long, multistep workflows across code, browsers, and professional software through to a finished result.","cost":"Average cost: $0.06","costEstimate":0.06,"dateAdded":"2026-09-03","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","cybersecurity","gpt-6","astra"],"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.001,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":768.2},"openai/gpt-6-astra-pro":{"name":"GPT 6 Astra Pro","model":"openai/gpt-6-astra-pro","description":"GPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.","cost":"Average cost: $0.06","costEstimate":0.06,"dateAdded":"2026-09-04","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","cybersecurity","gpt-6","astra","pro"],"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.001,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":1427.9},"openai/gpt-6-luna":{"name":"GPT 6 Luna","model":"openai/gpt-6-luna","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, suited for high-volume chat, classification, and lightweight agent workflows.","cost":"Input $0.10/M, Cached input $0.01/M, Output $0.50/M; at 272K+ input tokens: Input $0.20/M, Cached input $0.02/M, Output $0.75/M","costEstimate":0.0006,"dateAdded":"2026-09-22","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"none","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["fast","reasoning","chat","agentic","gpt-6","luna"],"api":"chat","input_price":1e-7,"output_price":5e-7,"input_price_per_million":0.1,"output_price_per_million":0.5,"input":0.1,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000005","input":0.1,"output":0.5,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.5,"prompt_per_token":"0.0000001","completion_per_token":"0.0000005","per_input_token":1e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.00075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAbove200k":0.00002,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.00075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAbove200k":0.00002,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":119.9},"openai/gpt-6-luna-pro":{"name":"GPT 6 Luna Pro","model":"openai/gpt-6-luna-pro","description":"GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna with Pro reasoning mode enabled for higher-quality responses on complex tasks.","cost":"Input $0.10/M, Cached input $0.01/M, Output $0.50/M; at 272K+ input tokens: Input $0.20/M, Cached input $0.02/M, Output $0.75/M","costEstimate":0.0006,"dateAdded":"2026-09-22","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["fast","reasoning","chat","agentic","gpt-6","luna","pro"],"api":"chat","input_price":1e-7,"output_price":5e-7,"input_price_per_million":0.1,"output_price_per_million":0.5,"input":0.1,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000005","input":0.1,"output":0.5,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.5,"prompt_per_token":"0.0000001","completion_per_token":"0.0000005","per_input_token":1e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.00075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAbove200k":0.00002,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.00075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAbove200k":0.00002,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":2841.5},"openai/gpt-6.1-sol":{"name":"GPT 6.1 Sol","model":"openai/gpt-6.1-sol","description":"GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It supports text and image input, tool calling, structured outputs, and reasoning from low through max.","cost":"Input $2.00/M, Cached input $0.10/M, Output $10.00/M","costEstimate":0.012,"dateAdded":"2026-09-29","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"none","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","agentic","gpt-6","sol"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0001,"cacheReadInputPer1kTokensAbove200k":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0001,"cacheReadInputPer1kTokensAbove200k":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":387.8},"openai/gpt-6.1-sol-pro":{"name":"GPT 6.1 Sol Pro","model":"openai/gpt-6.1-sol-pro","description":"GPT-6.1 Sol Pro uses the same underlying model as GPT-6.1 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.","cost":"Input $2.00/M, Cached input $0.10/M, Output $10.00/M","costEstimate":0.012,"dateAdded":"2026-09-29","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","agentic","gpt-6","sol","pro"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0001,"cacheReadInputPer1kTokensAbove200k":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0001,"cacheReadInputPer1kTokensAbove200k":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":1165.9},"openai/gpt-6-sol":{"name":"GPT 6 Sol","model":"openai/gpt-6-sol","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, reasoning, coding, and agentic workflows.","cost":"Input $2.00/M, Cached input $0.20/M, Output $10.00/M","costEstimate":0.012,"dateAdded":"2026-09-22","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"none","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","agentic","gpt-6","sol"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":315.4},"openai/gpt-6-sol-pro":{"name":"GPT 6 Sol Pro","model":"openai/gpt-6-sol-pro","description":"GPT-6 Sol Pro uses the same underlying model as GPT-6 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.","cost":"Input $2.00/M, Cached input $0.20/M, Output $10.00/M","costEstimate":0.012,"dateAdded":"2026-09-22","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","agentic","gpt-6","sol","pro"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":134.6},"openai/gpt-5.5":{"name":"GPT 5.5","model":"openai/gpt-5.5","description":"GPT-5.5 is an OpenAI model, built for agentic coding, computer use, and professional knowledge work with stronger reasoning and token efficiency.","cost":"Average cost: $0.035","costEstimate":0.035,"dateAdded":"2026-04-23","provider":"openai","visible":true,"maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","agentic","5.5"],"api":"chat","input_price":0.000005,"output_price":0.00003,"input_price_per_million":5,"output_price_per_million":30,"input":5,"output":30,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.00003","input":5,"output":30,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":30,"prompt_per_token":"0.000005","completion_per_token":"0.00003","per_input_token":0.000005,"per_output_token":0.00003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.03,"inputPer1kTokensAbove200k":0.01,"outputPer1kTokensAbove200k":0.045,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.03,"inputPer1kTokensAbove200k":0.01,"outputPer1kTokensAbove200k":0.045,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":489.9},"openai/gpt-5.4":{"name":"GPT 5.4","model":"openai/gpt-5.4","description":"GPT-5.4 is an OpenAI model for professional work with stronger reasoning, coding, and tool use.","cost":"Average cost: $0.0175","costEstimate":0.0175,"dateAdded":"2026-03-05","provider":"openai","visible":true,"maxInputTokens":922000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","logic","multi-step","5.4"],"api":"chat","input_price":0.0000025,"output_price":0.000015,"input_price_per_million":2.5,"output_price_per_million":15,"input":2.5,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.000015","input":2.5,"output":15,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":15,"prompt_per_token":"0.0000025","completion_per_token":"0.000015","per_input_token":0.0000025,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.015,"inputPer1kTokensAbove200k":0.005,"outputPer1kTokensAbove200k":0.0225,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00025,"cacheReadInputPer1kTokensAbove200k":0.0005},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.015,"inputPer1kTokensAbove200k":0.005,"outputPer1kTokensAbove200k":0.0225,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00025,"cacheReadInputPer1kTokensAbove200k":0.0005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.361Z"},"avgOutputTokens":408.8},"openai/gpt-5.4-mini":{"name":"GPT 5.4 Mini","model":"openai/gpt-5.4-mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","cost":"Average cost: $0.00525","costEstimate":0.00525,"dateAdded":"2026-03-17","provider":"openai","visible":true,"category":"More","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["efficient","reasoning","coding","5.4","mini"],"api":"chat","input_price":7.5e-7,"output_price":0.0000045,"input_price_per_million":0.75,"output_price_per_million":4.5,"input":0.75,"output":4.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.0000045","input":0.75,"output":4.5,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.75,"completion_per_million":4.5,"prompt_per_token":"0.00000075","completion_per_token":"0.0000045","per_input_token":7.5e-7,"per_output_token":0.0000045},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.0045,"cacheReadInputPer1kTokens":0.000075},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.0045,"cacheReadInputPer1kTokens":0.000075},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":171.8},"openai/gpt-5.4-nano":{"name":"GPT 5.4 Nano","model":"openai/gpt-5.4-nano","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.","cost":"Average cost: $0.00145","costEstimate":0.00145,"dateAdded":"2026-03-17","provider":"openai","visible":true,"category":"More","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["fast","low-latency","efficient","5.4","nano"],"api":"chat","input_price":2e-7,"output_price":0.00000125,"input_price_per_million":0.2,"output_price_per_million":1.25,"input":0.2,"output":1.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.00000125","input":0.2,"output":1.25,"cacheReadInputPer1kTokens":0.00002,"prompt_per_million":0.2,"completion_per_million":1.25,"prompt_per_token":"0.0000002","completion_per_token":"0.00000125","per_input_token":2e-7,"per_output_token":0.00000125},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00125,"cacheReadInputPer1kTokens":0.00002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00125,"cacheReadInputPer1kTokens":0.00002},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":515.3},"openai/gpt-5.4-pro":{"name":"GPT 5.4 Pro","model":"openai/gpt-5.4-pro","description":"Disabled because it is incredibly slow. This was the highest-performing GPT-5.4 variant from OpenAI for complex reasoning and demanding professional tasks.","cost":"Average cost: $0.21","costEstimate":0.21,"dateAdded":"2026-03-05","provider":"openai","visible":true,"disabled":true,"maxInputTokens":922000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","reasoning_summary":"detailed","verbosity":"high"},"additionalParams":{"reasoning_effort":{"levels":["medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","logic","multi-step","pro","5.4"],"api":"chat","input_price":0.00003,"output_price":0.00018,"input_price_per_million":30,"output_price_per_million":180,"input":30,"output":180,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00003","completion":"0.00018","input":30,"output":180,"cacheReadInputPer1kTokens":0.003,"prompt_per_million":30,"completion_per_million":180,"prompt_per_token":"0.00003","completion_per_token":"0.00018","per_input_token":0.00003,"per_output_token":0.00018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.03,"outputPer1kTokens":0.18,"inputPer1kTokensAbove200k":0.06,"outputPer1kTokensAbove200k":0.27,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.003},"effective_price":{"inputPer1kTokens":0.03,"outputPer1kTokens":0.18,"inputPer1kTokensAbove200k":0.06,"outputPer1kTokensAbove200k":0.27,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.003},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"}},"openai/gpt-latest":{"name":"GPT Latest","model":"openai/gpt-latest","description":"Compatibility alias that routes to GPT 6 Astra, the newest GPT flagship for complex reasoning, coding, and agentic workflows.","cost":"Average cost: $0.06","costEstimate":0.06,"dateAdded":"2026-03-29","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","latest"],"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.001,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":310.9},"openai/gpt-chat-latest":{"name":"GPT Chat Latest","model":"openai/gpt-chat-latest","description":"Compatibility chat alias that routes to GPT 5.6 Sol, the flagship GPT-5.6 tier for complex reasoning, coding, and agentic workflows.","cost":"Average cost: $0.012","costEstimate":0.012,"dateAdded":"2026-05-03","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["chat","assistant","latest","reasoning"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":408.3},"openai/gpt-5.2":{"name":"GPT 5.2","model":"openai/gpt-5.2","description":"GPT-5.2 is an OpenAI GPT-5-series model with strong reasoning and long-context performance.","cost":"Average cost: $0.016","costEstimate":0.016,"provider":"openai","visible":true,"dateAdded":"2025-12-11","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","5.2"],"api":"chat","input_price":0.00000175,"output_price":0.000014,"input_price_per_million":1.75,"output_price_per_million":14,"input":1.75,"output":14,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000175","completion":"0.000014","input":1.75,"output":14,"cacheReadInputPer1kTokens":0.00017500000000000003,"prompt_per_million":1.75,"completion_per_million":14,"prompt_per_token":"0.00000175","completion_per_token":"0.000014","per_input_token":0.00000175,"per_output_token":0.000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.014,"cacheReadInputPer1kTokens":0.00017500000000000003},"effective_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.014,"cacheReadInputPer1kTokens":0.00017500000000000003},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":171.8},"openai/gpt-5.2-codex":{"name":"GPT 5.2 Codex","model":"openai/gpt-5.2-codex","description":"Coding-focused GPT-5.2 variant with optimized routing.","cost":"Average cost: $0.016","costEstimate":0.016,"dateAdded":"2026-01-14","provider":"openai","visible":true,"maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["coding","5.2"],"api":"chat","input_price":0.00000175,"output_price":0.000014,"input_price_per_million":1.75,"output_price_per_million":14,"input":1.75,"output":14,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000175","completion":"0.000014","input":1.75,"output":14,"cacheReadInputPer1kTokens":0.00017500000000000003,"prompt_per_million":1.75,"completion_per_million":14,"prompt_per_token":"0.00000175","completion_per_token":"0.000014","per_input_token":0.00000175,"per_output_token":0.000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.014,"cacheReadInputPer1kTokens":0.00017500000000000003},"effective_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.014,"cacheReadInputPer1kTokens":0.00017500000000000003},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":41.1},"openai/gpt-5.3-codex":{"name":"GPT 5.3 Codex","model":"openai/gpt-5.3-codex","description":"Coding-focused GPT-5.3 variant with optimized routing.","cost":"Average cost: $0.0436","costEstimate":0.0436,"dateAdded":"2026-02-24","provider":"openai","visible":true,"maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["coding","5.3"],"api":"chat","input_price":0.00000175,"output_price":0.000014,"input_price_per_million":1.75,"output_price_per_million":14,"input":1.75,"output":14,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000175","completion":"0.000014","input":1.75,"output":14,"cacheReadInputPer1kTokens":0.00017500000000000003,"prompt_per_million":1.75,"completion_per_million":14,"prompt_per_token":"0.00000175","completion_per_token":"0.000014","per_input_token":0.00000175,"per_output_token":0.000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.014,"cacheReadInputPer1kTokens":0.00017500000000000003},"effective_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.014,"cacheReadInputPer1kTokens":0.00017500000000000003},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":280.6},"openai/gpt-5.2-pro":{"name":"GPT 5.2 Pro","model":"openai/gpt-5.2-pro","description":"The highest performing version of GPT 5.2 by OpenAI.","cost":"Average cost: $0.19","costEstimate":0.19,"provider":"openai","visible":true,"dateAdded":"2025-12-11","disabled":true,"maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","reasoning_summary":"detailed","verbosity":"high"},"additionalParams":{"reasoning_effort":{"levels":["medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","pro","5.2"],"api":"chat","input_price":0.000021,"output_price":0.000168,"input_price_per_million":21,"output_price_per_million":168,"input":21,"output":168,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000021","completion":"0.000168","input":21,"output":168,"cacheReadInputPer1kTokens":0.0021000000000000003,"prompt_per_million":21,"completion_per_million":168,"prompt_per_token":"0.000021","completion_per_token":"0.000168","per_input_token":0.000021,"per_output_token":0.000168},"effective_pricing":{"list_price":{"inputPer1kTokens":0.021,"outputPer1kTokens":0.168,"cacheReadInputPer1kTokens":0.0021000000000000003},"effective_price":{"inputPer1kTokens":0.021,"outputPer1kTokens":0.168,"cacheReadInputPer1kTokens":0.0021000000000000003},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"}},"openai/gpt-5":{"name":"GPT 5","model":"openai/gpt-5","description":"GPT-5 is OpenAI's most advanced model, offering major improvements in reasoning, code quality, and user experience. It handles complex coding tasks with minimal prompting, provides clear explanations, and introduces enhanced agentic capabilities. Designed for logic and multi-step tasks.","cost":"Average cost: $0.0164","costEstimate":0.0164,"provider":"openai","visible":true,"dateAdded":"2025-08-07","maxInputTokens":400000,"maxOutputTokens":128000,"preferredProviders":["Azure"],"labelVariant":"filled","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","logic","multi-step"],"api":"chat","input_price":0.00000125,"output_price":0.00001,"input_price_per_million":1.25,"output_price_per_million":10,"input":1.25,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00001","input":1.25,"output":10,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":1.25,"completion_per_million":10,"prompt_per_token":"0.00000125","completion_per_token":"0.00001","per_input_token":0.00000125,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":410.8},"openai/gpt-5.1":{"name":"GPT 5.1","model":"openai/gpt-5.1","description":"Optimized GPT-5.1 routing for lower latency and higher availability.","cost":"Average cost: $0.0164","costEstimate":0.0164,"provider":"openai","visible":true,"dateAdded":"2025-11-13","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding"],"api":"chat","input_price":0.00000125,"output_price":0.00001,"input_price_per_million":1.25,"output_price_per_million":10,"input":1.25,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00001","input":1.25,"output":10,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":1.25,"completion_per_million":10,"prompt_per_token":"0.00000125","completion_per_token":"0.00001","per_input_token":0.00000125,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":294.4},"openai/gpt-5.1-codex":{"name":"GPT 5.1 Codex","model":"openai/gpt-5.1-codex","description":"Coding-focused GPT-5.1 variant with optimized routing.","cost":"Average cost: $0.0164","costEstimate":0.0164,"provider":"openai","visible":true,"dateAdded":"2025-11-13","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":true,"reasoning_summary":true,"verbosity":true},"tags":["coding"],"api":"chat","input_price":0.00000125,"output_price":0.00001,"input_price_per_million":1.25,"output_price_per_million":10,"input":1.25,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00001","input":1.25,"output":10,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":1.25,"completion_per_million":10,"prompt_per_token":"0.00000125","completion_per_token":"0.00001","per_input_token":0.00000125,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":22.3},"openai/gpt-5.1-codex-max":{"name":"GPT 5.1 Codex Max","model":"openai/gpt-5.1-codex-max","description":"Top-tier GPT-5.1 Codex route used when direct OpenAI is unavailable.","cost":"Average cost: $0.0872","costEstimate":0.0872,"provider":"openai","visible":true,"dateAdded":"2025-12-04","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high","xhigh"]},"reasoning_summary":true,"verbosity":true},"tags":["coding","advanced","max"],"api":"chat","input_price":0.0000025,"output_price":0.00002,"input_price_per_million":2.5,"output_price_per_million":20,"input":2.5,"output":20,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00002","input":2.5,"output":20,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":20,"prompt_per_token":"0.0000025","completion_per_token":"0.00002","per_input_token":0.0000025,"per_output_token":0.00002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.00025},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"}},"openai/gpt-5.1-codex-mini":{"name":"GPT 5.1 Codex Mini","model":"openai/gpt-5.1-codex-mini","description":"Lightweight GPT-5.1 Codex path.","cost":"Average cost: $0.0045","costEstimate":0.0045,"provider":"openai","visible":true,"dateAdded":"2025-11-13","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":true,"reasoning_summary":true,"verbosity":true},"tags":["coding","lightweight"],"api":"chat","input_price":2.5e-7,"output_price":0.000002,"input_price_per_million":0.25,"output_price_per_million":2,"input":0.25,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.000002","input":0.25,"output":2,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.25,"completion_per_million":2,"prompt_per_token":"0.00000025","completion_per_token":"0.000002","per_input_token":2.5e-7,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.000025},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":136.1},"openai/gpt-5-pro":{"name":"GPT 5 Pro","model":"openai/gpt-5-pro","description":"The highest performing version of the flagship model GPT 5 by OpenAI.","cost":"Average cost: $0.135","costEstimate":0.135,"provider":"openai","visible":true,"dateAdded":"2025-10-06","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["high"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","logic","multi-step"],"api":"chat","input_price":0.000015,"output_price":0.00012,"input_price_per_million":15,"output_price_per_million":120,"input":15,"output":120,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.00012","input":15,"output":120,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":120,"prompt_per_token":"0.000015","completion_per_token":"0.00012","per_input_token":0.000015,"per_output_token":0.00012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.12,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.12,"cacheReadInputPer1kTokens":0.0015},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":90.3},"openai/gpt-5-mini":{"name":"GPT 5 Mini","model":"openai/gpt-5-mini","description":"A lightweight version of GPT-5 for cost-sensitive applications. Balances advanced capabilities with efficient resource usage.","cost":"Average cost: $0.004","costEstimate":0.004,"provider":"openai","visible":true,"dateAdded":"2025-08-07","category":"More","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]},"reasoning_summary":true,"verbosity":true},"tags":["efficient","cost-effective","lightweight"],"api":"chat","input_price":2.5e-7,"output_price":0.000002,"input_price_per_million":0.25,"output_price_per_million":2,"input":0.25,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.000002","input":0.25,"output":2,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.25,"completion_per_million":2,"prompt_per_token":"0.00000025","completion_per_token":"0.000002","per_input_token":2.5e-7,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.000025},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":890.9},"openai/gpt-5-nano":{"name":"GPT 5 Nano","model":"openai/gpt-5-nano","description":"Optimized for speed and ideal for applications requiring low latency. The fastest and most efficient GPT-5 variant.","cost":"Average cost: $0.0081","costEstimate":0.0081,"provider":"openai","visible":true,"dateAdded":"2025-08-07","category":"More","maxInputTokens":400000,"maxOutputTokens":128000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]},"reasoning_summary":true,"verbosity":true},"tags":["fast","low-latency","efficient","speed-optimized"],"api":"chat","input_price":5e-8,"output_price":4e-7,"input_price_per_million":0.05,"output_price_per_million":0.4,"input":0.05,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.0000004","input":0.05,"output":0.4,"cacheReadInputPer1kTokens":0.000005,"prompt_per_million":0.05,"completion_per_million":0.4,"prompt_per_token":"0.00000005","completion_per_token":"0.0000004","per_input_token":5e-8,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.000005},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.000005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.362Z"},"avgOutputTokens":322.1},"z-ai/glm-4.5v":{"totalParams":106,"activeParams":12,"isOpenSource":true,"name":"GLM 4.5V","model":"z-ai/glm-4.5v","description":"Multimodal GLM 4.5V that handles images alongside text while keeping the balanced reasoning strength of the GLM 4.5 family.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"zhipu","visible":true,"dateAdded":"2025-11-22","category":"More","maxInputTokens":64000,"maxOutputTokens":96000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000018,"input_price_per_million":0.6,"output_price_per_million":1.8,"input":0.6,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000018","input":0.6,"output":1.8,"prompt_per_million":0.6,"completion_per_million":1.8,"prompt_per_token":"0.0000006","completion_per_token":"0.0000018","per_input_token":6e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":731.6},"z-ai/glm-4.5v:thinking":{"totalParams":106,"activeParams":12,"isOpenSource":true,"name":"GLM 4.5V Thinking","model":"z-ai/glm-4.5v:thinking","description":"Thinking-enabled GLM 4.5V that surfaces structured reasoning before its final answer. Great for image-grounded analysis, OCR, charts, and deliberate step-by-step responses.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"zhipu","visible":true,"dateAdded":"2025-11-22","category":"More","maxInputTokens":64000,"maxOutputTokens":96000,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000018,"input_price_per_million":0.6,"output_price_per_million":1.8,"input":0.6,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000018","input":0.6,"output":1.8,"prompt_per_million":0.6,"completion_per_million":1.8,"prompt_per_token":"0.0000006","completion_per_token":"0.0000018","per_input_token":6e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":534.2},"z-ai/glm-5-turbo":{"totalParams":744,"activeParams":40,"name":"GLM 5 Turbo","model":"z-ai/glm-5-turbo","description":"Fast GLM 5 Turbo variant from Z-AI for general chat, coding, and tool use.","cost":"Average cost: $0.0042","costEstimate":0.00416,"provider":"zhipu","isOpenSource":true,"visible":true,"dateAdded":"2026-03-15","category":"More","maxInputTokens":202800,"maxOutputTokens":131072,"capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000012,"output_price":0.000004,"input_price_per_million":1.2,"output_price_per_million":4,"input":1.2,"output":4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000012","completion":"0.000004","input":1.2,"output":4,"cacheReadInputPer1kTokens":0.00024,"prompt_per_million":1.2,"completion_per_million":4,"prompt_per_token":"0.0000012","completion_per_token":"0.000004","per_input_token":0.0000012,"per_output_token":0.000004},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00024},"effective_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00024},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":556.5},"z-ai/glm-5v-turbo":{"name":"GLM 5V Turbo","model":"z-ai/glm-5v-turbo","description":"Z.ai's native multimodal agent model for vision-based coding and agent workflows. This is the standard non-thinking variant for image, video, and text inputs, tuned for perceive-plan-execute loops, complex coding, and tool-driven task execution.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"zhipu","isOpenSource":true,"visible":true,"dateAdded":"2026-04-01","category":"More","maxInputTokens":202800,"maxOutputTokens":131072,"capabilities":["vision","tool-calling","structured-output","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000012,"output_price":0.000004,"input_price_per_million":1.2,"output_price_per_million":4,"input":1.2,"output":4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000012","completion":"0.000004","input":1.2,"output":4,"cacheReadInputPer1kTokens":0.00024,"prompt_per_million":1.2,"completion_per_million":4,"prompt_per_token":"0.0000012","completion_per_token":"0.000004","per_input_token":0.0000012,"per_output_token":0.000004},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00024},"effective_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00024},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":213.8},"z-ai/glm-5v-turbo:thinking":{"name":"GLM 5V Turbo Thinking","model":"z-ai/glm-5v-turbo:thinking","description":"Thinking-enabled GLM 5V Turbo for image, video, and text inputs. Uses the same multimodal foundation model with more deliberate vision-grounded analysis, planning, and tool use.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"zhipu","isOpenSource":true,"visible":true,"dateAdded":"2026-04-02","category":"More","maxInputTokens":202800,"maxOutputTokens":131072,"capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000012,"output_price":0.000004,"input_price_per_million":1.2,"output_price_per_million":4,"input":1.2,"output":4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000012","completion":"0.000004","input":1.2,"output":4,"cacheReadInputPer1kTokens":0.00024,"prompt_per_million":1.2,"completion_per_million":4,"prompt_per_token":"0.0000012","completion_per_token":"0.000004","per_input_token":0.0000012,"per_output_token":0.000004},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00024},"effective_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00024},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":942.2},"gemini-2.0-pro-exp-02-05":{"name":"Gemini 2.0 Pro 0205","model":"gemini-2.0-pro-exp-02-05","description":"Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement.","cost":"Average cost: $0.0198","costEstimate":0.0198,"provider":"gemini","visible":true,"dateAdded":"2025-02-05","category":"More","capabilities":["vision"],"maxInputTokens":2097152,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001989,"output_price":0.000007956,"input_price_per_million":1.989,"output_price_per_million":7.956,"input":1.989,"output":7.956,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001989","completion":"0.000007956","input":1.989,"output":7.956,"cacheReadInputPer1kTokens":0.00049725,"prompt_per_million":1.989,"completion_per_million":7.956,"prompt_per_token":"0.000001989","completion_per_token":"0.000007956","per_input_token":0.000001989,"per_output_token":0.000007956},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001989,"outputPer1kTokens":0.007956,"cacheReadInputPer1kTokens":0.00049725},"effective_price":{"inputPer1kTokens":0.001989,"outputPer1kTokens":0.007956,"cacheReadInputPer1kTokens":0.00049725},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"}},"gemini-2.5-flash-preview-05-20":{"name":"Gemini 2.5 Flash 0520","model":"gemini-2.5-flash-preview-05-20","description":"Deprecated. Mapped to Gemini 2.5 Flash because this model is deprecated","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"gemini","visible":true,"dateAdded":"2025-05-20","label":"Deprecated","category":"More","maxInputTokens":1048000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000014999999999999999,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000014999999999999999},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000014999999999999999},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"}},"gemini-2.5-flash-preview-05-20:thinking":{"name":"Gemini 2.5 Flash 0520 Thinking","model":"gemini-2.5-flash-preview-05-20:thinking","description":"Deprecated. Mapped to Gemini 2.5 Flash because this model is deprecated","cost":"Average cost: $0.0033","costEstimate":0.0033,"provider":"gemini","visible":true,"dateAdded":"2025-05-20","label":"Deprecated","category":"More","capabilities":["vision","reasoning"],"maxInputTokens":1048000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1.5e-7,"output_price":0.0000035,"input_price_per_million":0.15,"output_price_per_million":3.5,"input":0.15,"output":3.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000035","input":0.15,"output":3.5,"cacheReadInputPer1kTokens":0.000014999999999999999,"prompt_per_million":0.15,"completion_per_million":3.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000035","per_input_token":1.5e-7,"per_output_token":0.0000035},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0035,"cacheReadInputPer1kTokens":0.000014999999999999999},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0035,"cacheReadInputPer1kTokens":0.000014999999999999999},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"}},"gemini-exp-1206":{"name":"Gemini 2.0 Pro 1206","model":"gemini-exp-1206","description":"Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement.","cost":"Average cost: $0.0233","costEstimate":0.0233,"dateAdded":"2024-12-06","category":"More","provider":"gemini","visible":true,"capabilities":["vision"],"maxInputTokens":2097152,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001258,"output_price":0.000004998,"input_price_per_million":1.258,"output_price_per_million":4.998,"input":1.258,"output":4.998,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001258","completion":"0.000004998","input":1.258,"output":4.998,"cacheReadInputPer1kTokens":0.000629,"prompt_per_million":1.258,"completion_per_million":4.998,"prompt_per_token":"0.000001258","completion_per_token":"0.000004998","per_input_token":0.000001258,"per_output_token":0.000004998},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001258,"outputPer1kTokens":0.004998,"cacheReadInputPer1kTokens":0.000629},"effective_price":{"inputPer1kTokens":0.001258,"outputPer1kTokens":0.004998,"cacheReadInputPer1kTokens":0.000629},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"}},"ernie-5.0-thinking-preview":{"name":"Ernie 5.0 Thinking Preview","model":"ernie-5.0-thinking-preview","description":"ERNIE 5.0 Thinking is Baidu's next-generation step-by-step reasoning model, providing stronger logical thinking, code generation, and tool-use capabilities with explicit thinking traces. ⚠️ Note: This model routes through Baidu, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.0016","costEstimate":0.0016,"category":"More","provider":"baidu","visible":true,"dateAdded":"2025-11-18","capabilities":["vision","reasoning"],"maxInputTokens":128000,"maxOutputTokens":16384,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.0000035,"input_price_per_million":1,"output_price_per_million":3.5,"input":1,"output":3.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.0000035","input":1,"output":3.5,"prompt_per_million":1,"completion_per_million":3.5,"prompt_per_token":"0.000001","completion_per_token":"0.0000035","per_input_token":0.000001,"per_output_token":0.0000035},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0035},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0035},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":1112.4},"qvq-max":{"name":"Qwen: QvQ Max","model":"qvq-max","description":"QvQ Max is the top model of the Qwen series. QvQ Max is capable of thinking and reasoning, can achieve significantly enhanced performance especially on hard problems.","cost":"Average cost: $0.0355","costEstimate":0.03546,"category":"More","provider":"qwen","visible":true,"dateAdded":"2025-03-28","capabilities":["vision"],"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000012,"output_price":0.0000048,"input_price_per_million":1.2,"output_price_per_million":4.8,"input":1.2,"output":4.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000012","completion":"0.0000048","input":1.2,"output":4.8,"prompt_per_million":1.2,"completion_per_million":4.8,"prompt_per_token":"0.0000012","completion_per_token":"0.0000048","per_input_token":0.0000012,"per_output_token":0.0000048},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.0048},"effective_price":{"inputPer1kTokens":0.0012,"outputPer1kTokens":0.0048},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"}},"qwq-32b":{"totalParams":32,"name":"Qwen: QwQ 32B","model":"qwq-32b","description":"QwQ is the reasoning model of the Qwen series. QwQ is capable of thinking and reasoning, can achieve significantly enhanced performance especially on hard problems.","cost":"Average cost: $0.0013","category":"More","costEstimate":0.0013,"provider":"qwen","visible":true,"disabled":true,"dateAdded":"2025-04-15","isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.56e-7,"output_price":3.05e-7,"input_price_per_million":0.256,"output_price_per_million":0.305,"input":0.256,"output":0.305,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000256","completion":"0.000000305","input":0.256,"output":0.305,"prompt_per_million":0.256,"completion_per_million":0.305,"prompt_per_token":"0.000000256","completion_per_token":"0.000000305","per_input_token":2.56e-7,"per_output_token":3.05e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000255999991,"outputPer1kTokens":0.000304999992},"effective_price":{"inputPer1kTokens":0.000255999991,"outputPer1kTokens":0.000304999992},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"}},"moonshotai/kimi-k3.1-pro":{"name":"Kimi K3.1 Pro","model":"moonshotai/kimi-k3.1-pro","description":"Kimi K3.1 Pro is a multimodal reasoning model for coding, 3D creation, document analysis and multi-step tool use. It supports a 1M-token context window and text, image and video inputs. Reasoning is always enabled, with low, high and max effort levels.","cost":"Input $2.00/m, Cached input $0.20/m, Output $10.00/m","costEstimate":0.01,"provider":"moonshot","visible":true,"dateAdded":"2026-10-24","isOpenSource":false,"category":"More","maxInputTokens":1048576,"maxOutputTokens":1048576,"capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["chat","reasoning","vision","video","agent"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.002,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.002,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":978.5},"moonshotai/kimi-k3.1-pro-highspeed":{"name":"Kimi K3.1 Pro Highspeed","model":"moonshotai/kimi-k3.1-pro-highspeed","description":"Kimi K3.1 Pro Highspeed is the faster variant of K3.1 Pro, a multimodal reasoning model for coding, 3D creation, document analysis and multi-step tool use. It supports a 1M-token context window and text, image and video inputs. Reasoning is always enabled, with low, high and max effort levels.","cost":"Input $4.00/m, Cached input $0.20/m, Output $20.00/m","costEstimate":0.02,"provider":"moonshot","visible":true,"dateAdded":"2026-10-24","isOpenSource":false,"category":"More","maxInputTokens":1048576,"maxOutputTokens":1048576,"capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["chat","reasoning","vision","video","agent"],"api":"chat","input_price":0.000004,"output_price":0.00002,"input_price_per_million":4,"output_price_per_million":20,"input":4,"output":20,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000004","completion":"0.00002","input":4,"output":20,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":4,"completion_per_million":20,"prompt_per_token":"0.000004","completion_per_token":"0.00002","per_input_token":0.000004,"per_output_token":0.00002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.004,"cacheWriteInputPer1kTokens1h":0.008},"effective_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.004,"cacheWriteInputPer1kTokens1h":0.008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":1304.1},"moonshotai/kimi-k3":{"name":"Kimi K3","model":"moonshotai/kimi-k3","description":"Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image/video understanding.","cost":"Auto and provider-specific prices can differ. See pricing details for current input, output, and cached-input rates.","costEstimate":0.01,"provider":"moonshot","visible":true,"dateAdded":"2026-07-16","isOpenSource":true,"category":"More","maxInputTokens":1048576,"maxOutputTokens":1048576,"capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["chat","reasoning","vision","video","agent"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":1124.8},"stepfun-ai/step-3.5-flash-2603":{"totalParams":196,"activeParams":11,"name":"Step 3.5 Flash 2603","model":"stepfun-ai/step-3.5-flash-2603","description":"Step 3.5 Flash 2603 is optimized for high-frequency agentic and coding workflows with improved token efficiency and faster reasoning. NOTE: This model runs via StepFun, which may log and train on your prompts.","cost":"Average cost: $0.0009","costEstimate":0.0009,"provider":"stepfun","visible":true,"dateAdded":"2026-04-14","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":256000,"capabilities":["reasoning"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.363Z"},"avgOutputTokens":2996},"stepfun-ai/step-3.5-flash":{"totalParams":196,"activeParams":11,"name":"Step 3.5 Flash","model":"stepfun-ai/step-3.5-flash","description":"StepFun's most capable open-source reasoning model with visible reasoning traces. Built on a sparse Mixture-of-Experts architecture with 196B total parameters and only 11B active per token, it achieves frontier-level performance in math, logic, and agentic coding while reaching up to 350 tokens/sec. Supports 256K context. NOTE: This model runs via StepFun, which may log and train on your prompts.","cost":"Average cost: $0.0009","costEstimate":0.0009,"provider":"stepfun","visible":true,"dateAdded":"2026-02-02","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":256000,"capabilities":["reasoning"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":2425.7},"gemini-2.5-flash-preview-04-17":{"name":"Gemini 2.5 Flash Preview","model":"gemini-2.5-flash-preview-04-17","description":"Deprecated. This model now routes to stable Gemini 2.5 Flash.","cost":"Average cost: $0.0017","costEstimate":0.0017,"provider":"gemini","visible":true,"dateAdded":"2025-04-17","category":"More","labelVariant":"destructive","label":"Old","capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000014999999999999999,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000014999999999999999},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000014999999999999999},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"}},"google/gemini-3.1-pro-preview":{"name":"Gemini 3.1 Pro (Preview)","model":"google/gemini-3.1-pro-preview","description":"Gemini 3.1 Pro preview is built for tasks where simple answers are not enough. Stronger core reasoning for complex coding, math, and long-context workflows, with multimodal support and a reported 77.1% verified score on ARC-AGI-2. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.","cost":"Average cost: $0.04721","costEstimate":0.04721,"dateAdded":"2026-02-19","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":698.5},"google/gemini-3.1-pro-preview-customtools":{"name":"Gemini 3.1 Pro (Preview Custom Tools)","model":"google/gemini-3.1-pro-preview-customtools","description":"Gemini 3.1 Pro preview variant tuned for better tool selection behavior in coding agents and multi-tool workflows. It reduces overuse of generic bash tools and improves function-calling reliability while retaining Gemini 3.1 Pro's multimodal reasoning and 1M-token context. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.","cost":"Average cost: $0.04721","costEstimate":0.04721,"dateAdded":"2026-02-27","labelVariant":"outline","provider":"gemini","visible":true,"category":"More","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":903.1},"google/gemini-3.1-pro-preview-high":{"name":"Gemini 3.1 Pro (Preview High)","model":"google/gemini-3.1-pro-preview-high","description":"Gemini 3.1 Pro preview high-reasoning variant.","cost":"Average cost: $0.04721","costEstimate":0.04721,"dateAdded":"2026-02-21","labelVariant":"outline","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":1516.1},"google/gemini-3.1-pro-preview-low":{"name":"Gemini 3.1 Pro (Preview Low)","model":"google/gemini-3.1-pro-preview-low","description":"Gemini 3.1 Pro preview low-reasoning variant.","cost":"Average cost: $0.04721","costEstimate":0.04721,"dateAdded":"2026-02-21","labelVariant":"outline","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":1561.8},"gemini-2.5-flash-preview-04-17:thinking":{"name":"Gemini 2.5 Flash Preview Thinking","model":"gemini-2.5-flash-preview-04-17:thinking","description":"Deprecated. This model now routes to stable Gemini 2.5 Flash.","cost":"Average cost: $0.0153","costEstimate":0.0153,"dateAdded":"2025-04-17","category":"More","label":"Old","labelVariant":"destructive","provider":"gemini","visible":true,"capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled","budget_tokens":8000}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":8000},"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1.5e-7,"output_price":0.0000035,"input_price_per_million":0.15,"output_price_per_million":3.5,"input":0.15,"output":3.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000035","input":0.15,"output":3.5,"cacheReadInputPer1kTokens":0.000014999999999999999,"prompt_per_million":0.15,"completion_per_million":3.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000035","per_input_token":1.5e-7,"per_output_token":0.0000035},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0035,"cacheReadInputPer1kTokens":0.000014999999999999999},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0035,"cacheReadInputPer1kTokens":0.000014999999999999999},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"}},"gemini-2.5-pro-exp-03-25":{"name":"Gemini 2.5 Pro Experimental 0325","model":"gemini-2.5-pro-exp-03-25","description":"Gemini 2.5 Pro Exp 0325. Google's experimental model from March 2025.","cost":"Average cost: $0.0092","costEstimate":0.0092,"dateAdded":"2025-03-25","label":"Old","category":"More","labelVariant":"destructive","provider":"gemini","visible":true,"capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"}},"gemini-2.5-pro-preview-03-25":{"name":"Gemini 2.5 Pro Preview 0325","model":"gemini-2.5-pro-preview-03-25","description":"Gemini 2.5 Pro Preview 0325. Google's model from March 2025.","cost":"Average cost: $0.0160","costEstimate":0.016,"dateAdded":"2025-03-25","labelVariant":"destructive","provider":"gemini","visible":true,"category":"More","label":"Old","capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":1326.2},"gemini-2.5-pro-preview-05-06":{"name":"Gemini 2.5 Pro Preview 0506","model":"gemini-2.5-pro-preview-05-06","description":"Gemini 2.5 Pro Preview 0506. Google's model from May 2025.","cost":"Average cost: $0.0225","costEstimate":0.0225,"dateAdded":"2025-05-06","label":"Old","labelVariant":"destructive","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"}},"gemini-2.5-pro-preview-06-05":{"name":"Gemini 2.5 Pro Preview 0605","model":"gemini-2.5-pro-preview-06-05","description":"Note: This preview is mapped to Gemini 2.5 Pro (stable).","cost":"Average cost: $0.0303","costEstimate":0.0303,"dateAdded":"2025-06-05","category":"More","label":"Old","labelVariant":"destructive","provider":"gemini","visible":true,"capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":727},"gemini-2.5-pro":{"name":"Gemini 2.5 Pro","model":"gemini-2.5-pro","description":"Gemini 2.5 Pro stable release. Google's most capable generalist model with strong performance across a wide range of tasks.","cost":"Average cost: $0.0443","costEstimate":0.0443,"dateAdded":"2025-06-05","category":"More","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","tool-calling","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.00000125,"output_price":0.00001,"input_price_per_million":1.25,"output_price_per_million":10,"input":1.25,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00001","input":1.25,"output":10,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":1.25,"completion_per_million":10,"prompt_per_token":"0.00000125","completion_per_token":"0.00001","per_input_token":0.00000125,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.0025,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.000125,"cacheReadInputPer1kTokensAbove200k":0.00025,"cacheWriteInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.0025,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.000125,"cacheReadInputPer1kTokensAbove200k":0.00025,"cacheWriteInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":1071.7},"gemini-2.5-flash":{"name":"Gemini 2.5 Flash","model":"gemini-2.5-flash","description":"Fast, cost efficient performance on complex tasks. The workhorse of the Gemini series. Stable release with improved capabilities. Audio input costs $1.00 per million audio tokens.","cost":"Average cost: $0.0049","costEstimate":0.0049,"category":"More","dateAdded":"2025-06-05","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","tool-calling","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"cacheReadInputPer1kTokens":0.000029999999999999997,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":368.1},"gemini-2.5-flash-lite":{"name":"Gemini 2.5 Flash Lite","model":"gemini-2.5-flash-lite","description":"Ultra-lightweight and fast variant of Gemini 2.5 Flash. Stable release optimized for speed and efficiency. Audio input costs $0.30 per million audio tokens.","cost":"Average cost: $0.0013","costEstimate":0.0013,"category":"More","dateAdded":"2025-06-17","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","tool-calling","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":42.2},"gemini-2.5-flash-lite-preview-06-17":{"name":"Gemini 2.5 Flash Lite Preview","model":"gemini-2.5-flash-lite-preview-06-17","description":"Ultra-lightweight and fast variant of Gemini 2.5 Flash. Preview release optimized for speed and efficiency.","cost":"Average cost: $0.0013","costEstimate":0.0013,"category":"More","dateAdded":"2025-06-17","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000014999999999999999,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000014999999999999999},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000014999999999999999},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"}},"gemini-2.5-flash-nothinking":{"name":"Gemini 2.5 Flash (No Thinking)","model":"gemini-2.5-flash-nothinking","description":"Fast, cost efficient performance on complex tasks. The workhorse of the Gemini series. Stable release with thinking mode disabled. Audio input costs $1.00 per million audio tokens.","cost":"Average cost: $0.0016","costEstimate":0.0016,"dateAdded":"2025-06-05","provider":"gemini","category":"More","visible":true,"capabilities":["vision","pdf-upload","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"cacheReadInputPer1kTokens":0.000029999999999999997,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"},"avgOutputTokens":523.3},"google/gemini-flash-latest":{"name":"Gemini Flash Latest","model":"google/gemini-flash-latest","description":"Compatibility alias that routes to the newest version of Gemini Flash. Currently routes to Gemini 3.8 Flash.","cost":"Input $0.75/m, Output $3.75/m","costEstimate":0.0032625,"dateAdded":"2026-03-29","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":7.5e-7,"output_price":0.00000375,"input_price_per_million":0.75,"output_price_per_million":3.75,"input":0.75,"output":3.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.00000375","input":0.75,"output":3.75,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.75,"completion_per_million":3.75,"prompt_per_token":"0.00000075","completion_per_token":"0.00000375","per_input_token":7.5e-7,"per_output_token":0.00000375},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.364Z"}},"google/gemini-pro-latest":{"name":"Gemini Pro Latest","model":"google/gemini-pro-latest","description":"Compatibility alias that routes to the newest version of Gemini Pro. Currently routes to Gemini 3.1 Pro Preview High.","cost":"Average cost: $0.04721","costEstimate":0.04721,"dateAdded":"2026-03-29","labelVariant":"outline","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"gemini-3-pro-image-preview":{"name":"Gemini 3 Pro Image","model":"gemini-3-pro-image-preview","description":"Gemini 3 Pro with native image generation support. Can generate images inline from text prompts.","cost":"Average cost: $0.04721","costEstimate":0.04721,"dateAdded":"2025-11-18","category":"More","labelVariant":"outline","provider":"gemini","visible":true,"apiOnly":true,"capabilities":["vision","image-generation"],"maxInputTokens":65536,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"google/gemini-3-flash-preview":{"name":"Gemini 3 Flash (Preview)","model":"google/gemini-3-flash-preview","description":"Google's Gemini 3 Flash preview model optimized for speed while maintaining high capability. Features sub-second response times with strong multimodal understanding and reasoning. Audio input costs $1.00 per million audio tokens.","cost":"Average cost: $0.00261","costEstimate":0.00261,"dateAdded":"2025-12-17","category":"More","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":5e-7,"output_price":0.000003,"input_price_per_million":0.5,"output_price_per_million":3,"input":0.5,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.000003","input":0.5,"output":3,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.5,"completion_per_million":3,"prompt_per_token":"0.0000005","completion_per_token":"0.000003","per_input_token":5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":592},"google/gemini-3-flash-preview-thinking":{"name":"Gemini 3 Flash Thinking","model":"google/gemini-3-flash-preview-thinking","description":"Google's Gemini 3 Flash preview model with thinking mode enabled for enhanced reasoning and chain-of-thought capabilities. Audio input costs $1.00 per million audio tokens.","cost":"Average cost: $0.00321","costEstimate":0.00321,"dateAdded":"2025-12-17","category":"More","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled","budget_tokens":16000}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":5e-7,"output_price":0.000003,"input_price_per_million":0.5,"output_price_per_million":3,"input":0.5,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.000003","input":0.5,"output":3,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.5,"completion_per_million":3,"prompt_per_token":"0.0000005","completion_per_token":"0.000003","per_input_token":5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":1749.1},"google/gemini-3.5-flash":{"name":"Gemini 3.5 Flash","model":"google/gemini-3.5-flash","description":"Google's speed-focused Gemini Flash model for frontier multimodal intelligence across text, images, audio, video, PDFs, and code. Built for agentic coding, reliable tool use, structured outputs, and long-context workflows. Audio input costs $3.00 per million audio tokens.","cost":"Input $1.50/m, Output $9.00/m","costEstimate":0.00783,"dateAdded":"2026-05-19","category":"More","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","tool-calling","structured-output","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"disabled"}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":0.0000015,"output_price":0.000009,"input_price_per_million":1.5,"output_price_per_million":9,"input":1.5,"output":9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.000009","input":1.5,"output":9,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":1.5,"completion_per_million":9,"prompt_per_token":"0.0000015","completion_per_token":"0.000009","per_input_token":0.0000015,"per_output_token":0.000009},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.009,"cacheReadInputPer1kTokens":0.00015,"cacheWriteInputPer1kTokens":0.0000833333333333333},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.009,"cacheReadInputPer1kTokens":0.00015,"cacheWriteInputPer1kTokens":0.0000833333333333333},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":321.5},"google/gemini-3.5-flash-thinking":{"name":"Gemini 3.5 Flash Thinking","model":"google/gemini-3.5-flash-thinking","description":"Gemini 3.5 Flash with higher thinking enabled for harder reasoning, agentic coding, tool use, multimodal analysis, and long-context workflows. Audio input costs $3.00 per million audio tokens.","cost":"Input $1.50/m, Output $9.00/m","costEstimate":0.00783,"dateAdded":"2026-05-19","category":"More","labelVariant":"outline","provider":"gemini","visible":true,"capabilities":["vision","reasoning","video-input"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled","budget_tokens":16000}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":0.0000015,"output_price":0.000009,"input_price_per_million":1.5,"output_price_per_million":9,"input":1.5,"output":9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.000009","input":1.5,"output":9,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":1.5,"completion_per_million":9,"prompt_per_token":"0.0000015","completion_per_token":"0.000009","per_input_token":0.0000015,"per_output_token":0.000009},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.009,"cacheReadInputPer1kTokens":0.00015,"cacheWriteInputPer1kTokens":0.0000833333333333333},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.009,"cacheReadInputPer1kTokens":0.00015,"cacheWriteInputPer1kTokens":0.0000833333333333333},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":1660.2},"gemini-2.5-flash-preview-09-2025":{"name":"Gemini 2.5 Flash Preview (09/2025)","model":"gemini-2.5-flash-preview-09-2025","description":"State-of-the-art Gemini 2.5 Flash checkpoint tuned for advanced reasoning, coding, math, and scientific tasks. Built-in thinking for higher accuracy and nuanced context handling. Routed to Gemini 2.5 Flash (stable).","cost":"Average cost: $0.0022","costEstimate":0.0022,"category":"More","dateAdded":"2025-09-25","provider":"gemini","visible":true,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"cacheReadInputPer1kTokens":0.000029999999999999997,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"gemini-2.5-flash-preview-09-2025-thinking":{"name":"Gemini 2.5 Flash Preview (09/2025) – Thinking","model":"gemini-2.5-flash-preview-09-2025-thinking","description":"Same checkpoint with thinking enabled by default for deeper reasoning and stepwise analysis on complex tasks. Routed to Gemini 2.5 Flash Thinking (stable).","cost":"Average cost: $0.0022","costEstimate":0.0025,"dateAdded":"2025-09-25","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled","budget_tokens":16000}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"cacheReadInputPer1kTokens":0.000029999999999999997,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.000029999999999999997},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"gemini-2.5-flash-lite-preview-09-2025":{"name":"Gemini 2.5 Flash Lite Preview (09/2025)","model":"gemini-2.5-flash-lite-preview-09-2025","description":"Deprecated compatibility alias. Requests route to the stable Gemini 2.5 Flash Lite model.","cost":"Average cost: $0.0013","costEstimate":0.0013,"dateAdded":"2025-09-25","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"gemini-2.5-flash-lite-preview-09-2025-thinking":{"name":"Gemini 2.5 Flash Lite Preview (09/2025) – Thinking","model":"gemini-2.5-flash-lite-preview-09-2025-thinking","description":"Deprecated compatibility alias. Requests route to Gemini 2.5 Flash Lite with the stable thinking path.","cost":"Average cost: $0.0003","costEstimate":0.0003,"dateAdded":"2025-09-25","provider":"gemini","visible":true,"category":"More","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled","budget_tokens":12000}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":12000},"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.00001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"google/gemini-3.1-flash-lite":{"name":"Gemini 3.1 Flash Lite","model":"google/gemini-3.1-flash-lite","description":"Google's Gemini 3.1 Flash Lite. Optimized for high-volume, cost-efficient reasoning and multimodal workloads.","cost":"Input $0.25/m, Output $1.50/m","costEstimate":0.0013,"dateAdded":"2026-03-03","provider":"gemini","visible":true,"category":"More","capabilities":["vision","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":2.5e-7,"output_price":0.0000015,"input_price_per_million":0.25,"output_price_per_million":1.5,"input":0.25,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000015","input":0.25,"output":1.5,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.25,"completion_per_million":1.5,"prompt_per_token":"0.00000025","completion_per_token":"0.0000015","per_input_token":2.5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000025,"cacheWriteInputPer1kTokens":0.00008333},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0015,"cacheReadInputPer1kTokens":0.000025,"cacheWriteInputPer1kTokens":0.00008333},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":669},"google/gemini-3.5-flash-lite":{"name":"Gemini 3.5 Flash Lite","model":"google/gemini-3.5-flash-lite","description":"Google's cost-efficient Gemini 3.5 Flash Lite model for high-volume multimodal reasoning, tool use, and structured-output workloads.","cost":"Input $0.30/m, Output $2.50/m","costEstimate":0.0022,"dateAdded":"2026-07-21","provider":"gemini","visible":true,"category":"More","capabilities":["vision","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"cacheReadInputPer1kTokens":0.00003,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00003,"cacheWriteInputPer1kTokens":0.00008333},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00003,"cacheWriteInputPer1kTokens":0.00008333},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":177.9},"google/gemini-3.6-flash":{"name":"Gemini 3.6 Flash","model":"google/gemini-3.6-flash","description":"Google's GA Flash model delivers near-Pro coding and agentic capability at Flash-tier speed and cost, with improved token efficiency over Gemini 3.5 Flash. It is optimized for multi-step orchestration, full-stack code refactoring, general reasoning, and multimodal workflows.","cost":"Input $0.75/m, Output $3.75/m","costEstimate":0.0032625,"dateAdded":"2026-07-21","provider":"gemini","visible":true,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":7.5e-7,"output_price":0.00000375,"input_price_per_million":0.75,"output_price_per_million":3.75,"input":0.75,"output":3.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.00000375","input":0.75,"output":3.75,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.75,"completion_per_million":3.75,"prompt_per_token":"0.00000075","completion_per_token":"0.00000375","per_input_token":7.5e-7,"per_output_token":0.00000375},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":932.2},"google/gemini-3.7-flash":{"name":"Gemini 3.7 Flash","model":"google/gemini-3.7-flash","description":"Google's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.","cost":"Input $0.75/m, Output $3.75/m","costEstimate":0.0032625,"dateAdded":"2026-08-13","provider":"gemini","visible":true,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":7.5e-7,"output_price":0.00000375,"input_price_per_million":0.75,"output_price_per_million":3.75,"input":0.75,"output":3.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.00000375","input":0.75,"output":3.75,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.75,"completion_per_million":3.75,"prompt_per_token":"0.00000075","completion_per_token":"0.00000375","per_input_token":7.5e-7,"per_output_token":0.00000375},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":850.2},"google/gemini-3.8-flash":{"name":"Gemini 3.8 Flash","model":"google/gemini-3.8-flash","description":"Google's fast multimodal model for agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Its capabilities, limits, reasoning behavior, and pricing currently mirror Gemini 3.7 Flash.","cost":"Input $0.75/m, Output $3.75/m","costEstimate":0.0032625,"dateAdded":"2026-09-02","provider":"gemini","visible":true,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":7.5e-7,"output_price":0.00000375,"input_price_per_million":0.75,"output_price_per_million":3.75,"input":0.75,"output":3.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.00000375","input":0.75,"output":3.75,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.75,"completion_per_million":3.75,"prompt_per_token":"0.00000075","completion_per_token":"0.00000375","per_input_token":7.5e-7,"per_output_token":0.00000375},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.00375,"cacheReadInputPer1kTokens":0.000075,"cacheWriteInputPer1kTokens":0.0000416666666666667},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"},"avgOutputTokens":1236.8},"google/gemini-4-argon":{"name":"Gemini 4 Argon","model":"google/gemini-4-argon","description":"Google's Gemini 4 Argon is a flagship reasoning model for complex software engineering, mathematical and scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDFs, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output; synchronous output is capped at 65,536 tokens.","cost":"Input $2/m, Cached input $0.10/m, Output $10/m, Cache write $0.1875/m (launch pricing through Nov 30, 2026; all rates double from Dec 1)","costEstimate":0.0055,"dateAdded":"2026-10-13","provider":"gemini","visible":true,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0001875},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0001,"cacheWriteInputPer1kTokens":0.0001875},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"valid_until":"2026-12-01T08:00:00.000Z","source":"schedule","updated_at":"2026-10-26T14:49:05.349Z"},"avgOutputTokens":1570.1},"nex-agi/deepseek-v3.1-nex-n1":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3.1 Nex N1","model":"nex-agi/deepseek-v3.1-nex-n1","description":"Currently unavailable because no providers host this model anymore. Nex-AGI's flagship 671B agentic model was built on DeepSeek V3.1 and optimized for programming, tool use, web search, multi-hop reasoning, and mini-app development.","cost":"Average cost: $0.00035","costEstimate":0.00035,"dateAdded":"2025-12-10","provider":"deepseek","visible":true,"disabled":true,"isOpenSource":true,"category":"More","maxInputTokens":128000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.8e-7,"output_price":4.2e-7,"input_price_per_million":0.28,"output_price_per_million":0.42,"input":0.28,"output":0.42,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000028","completion":"0.00000042","input":0.28,"output":0.42,"prompt_per_million":0.28,"completion_per_million":0.42,"prompt_per_token":"0.00000028","completion_per_token":"0.00000042","per_input_token":2.8e-7,"per_output_token":4.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"effective_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.365Z"}},"nex-agi/nex-n2.5-mini":{"totalParams":35,"activeParams":3,"name":"Nex N2.5 Mini","model":"nex-agi/nex-n2.5-mini","description":"Nex N2.5 Mini is an open-source multimodal agentic model for coding and long-horizon workflows. It supports image input, structured output, configurable reasoning, a 262K-token context window, and up to 235K output tokens.","cost":"Input $0.025/m, Cached input $0.0025/m, Output $0.10/m","costEstimate":0.0000625,"dateAdded":"2026-09-22","provider":"nex-agi","visible":true,"isOpenSource":true,"category":"More","maxInputTokens":262144,"capabilities":["vision","reasoning","structured-output"],"labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","medium","high"]}},"tags":["chat","reasoning","coding","multimodal","long context"],"api":"chat","input_price":2.5e-8,"output_price":1e-7,"input_price_per_million":0.025,"output_price_per_million":0.1,"input":0.025,"output":0.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000025","completion":"0.0000001","input":0.025,"output":0.1,"cacheReadInputPer1kTokens":0.0000025,"prompt_per_million":0.025,"completion_per_million":0.1,"prompt_per_token":"0.000000025","completion_per_token":"0.0000001","per_input_token":2.5e-8,"per_output_token":1e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000025,"outputPer1kTokens":0.0001,"cacheReadInputPer1kTokens":0.0000025},"effective_price":{"inputPer1kTokens":0.000025,"outputPer1kTokens":0.0001,"cacheReadInputPer1kTokens":0.0000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":2498.7},"nex-agi/nex-n2.5-pro":{"totalParams":397,"activeParams":17,"name":"Nex N2.5 Pro","model":"nex-agi/nex-n2.5-pro","description":"Nex N2.5 Pro is an open-source multimodal agentic model for coding, tool use, and long-horizon workflows. It supports image input, structured output, configurable reasoning, a 262K-token context window, and up to 235K output tokens.","cost":"Input $0.075/m, Cached input $0.015/m, Output $0.25/m","costEstimate":0.0001625,"dateAdded":"2026-09-22","provider":"nex-agi","visible":true,"isOpenSource":true,"category":"More","maxInputTokens":262144,"capabilities":["vision","reasoning","tool-calling","structured-output"],"labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","medium","high"]}},"tags":["chat","reasoning","coding","tools","multimodal","long context"],"api":"chat","input_price":7.5e-8,"output_price":2.5e-7,"input_price_per_million":0.075,"output_price_per_million":0.25,"input":0.075,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000075","completion":"0.00000025","input":0.075,"output":0.25,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.075,"completion_per_million":0.25,"prompt_per_token":"0.000000075","completion_per_token":"0.00000025","per_input_token":7.5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00025,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":1425},"openai/o1-pro":{"name":"OpenAI o1 Pro","model":"openai/o1-pro","description":"OpenAI's flagship series of reasoning models for solving hard problems. The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers. o1 pro comes with a massive 100,000 word output window.","cost":"Average cost: $1.5208","costEstimate":1.5208,"dateAdded":"2025-01-25","provider":"openai","labelVariant":"outline","visible":true,"category":"More","capabilities":["pdf-upload"],"maxInputTokens":200000,"maxOutputTokens":100000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00015,"output_price":0.0006,"input_price_per_million":150,"output_price_per_million":600,"input":150,"output":600,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00015","completion":"0.0006","input":150,"output":600,"cacheReadInputPer1kTokens":0.075,"prompt_per_million":150,"completion_per_million":600,"prompt_per_token":"0.00015","completion_per_token":"0.0006","per_input_token":0.00015,"per_output_token":0.0006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.15,"outputPer1kTokens":0.6,"cacheReadInputPer1kTokens":0.075},"effective_price":{"inputPer1kTokens":0.15,"outputPer1kTokens":0.6,"cacheReadInputPer1kTokens":0.075},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":33.9},"qwen/qwen3-coder":{"totalParams":480,"activeParams":35,"name":"Qwen 3 Coder 480B","model":"qwen/qwen3-coder","description":"Qwen 3 Coder 480B, a 480 billion total parameter model with 35B active, and 160 total experts with 8 active. Performs similar to Claude 4 Sonnet in coding benchmarks, but does so at a much lower price.","cost":"Average cost: $0.003","costEstimate":0.003,"dateAdded":"2026-03-17","category":"More","provider":"qwen","labelVariant":"outline","visible":true,"isOpenSource":true,"capabilities":["tool-calling","structured-output"],"maxInputTokens":262000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.3e-7,"output_price":5e-7,"input_price_per_million":0.13,"output_price_per_million":0.5,"input":0.13,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000013","completion":"0.0000005","input":0.13,"output":0.5,"prompt_per_million":0.13,"completion_per_million":0.5,"prompt_per_token":"0.00000013","completion_per_token":"0.0000005","per_input_token":1.3e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":315.1},"google/gemini-flash-lite-latest":{"name":"Gemini Flash Lite Latest","model":"google/gemini-flash-lite-latest","description":"Compatibility alias that routes to the newest version of Gemini Flash Lite. Currently routes to Gemini 3.5 Flash Lite.","cost":"Input $0.30/m, Output $2.50/m","costEstimate":0.0022,"category":"More","provider":"gemini","labelVariant":"outline","visible":true,"dateAdded":"2026-03-29","capabilities":["vision","video-input","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high"]}},"api":"chat","input_price":3e-7,"output_price":0.0000025,"input_price_per_million":0.3,"output_price_per_million":2.5,"input":0.3,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000025","input":0.3,"output":2.5,"cacheReadInputPer1kTokens":0.00003,"prompt_per_million":0.3,"completion_per_million":2.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000025","per_input_token":3e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00003,"cacheWriteInputPer1kTokens":0.00008333},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00003,"cacheWriteInputPer1kTokens":0.00008333},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"}},"qwen/qwen3-coder-flash":{"name":"Qwen3 Coder Flash","model":"qwen/qwen3-coder-flash","description":"A speed‑optimized and budget‑friendly sibling to Coder Plus. Excellent at code generation and agentic workflows (tool use, environment interaction) with solid general‑purpose ability.","cost":"Average cost: $0.0009","costEstimate":0.0009,"category":"More","provider":"qwen","labelVariant":"outline","visible":true,"dateAdded":"2025-09-17","isOpenSource":false,"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000015,"input_price_per_million":0.3,"output_price_per_million":1.5,"input":0.3,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000015","input":0.3,"output":1.5,"prompt_per_million":0.3,"completion_per_million":1.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000015","per_input_token":3e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"}},"meta-llama/llama-4-maverick":{"totalParams":400,"activeParams":17,"name":"Llama 4 Maverick","model":"meta-llama/llama-4-maverick","description":"Llama 4 Maverick, a 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding—at less than half the active parameters. Llama 4 Maverick offers a best-in-class performance to cost ratio with an experimental chat version scoring ELO of 1417 on LMArena.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"meta","labelVariant":"outline","visible":true,"dateAdded":"2025-09-05","isOpenSource":true,"category":"More","preferredProviders":["DeepInfra"],"capabilities":["structured-output","vision"],"maxInputTokens":1048576,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":114.2},"x-ai/grok-4.3":{"name":"Grok 4.3","model":"x-ai/grok-4.3","description":"Grok 4.3 is SpaceXAI's reasoning model for text and image inputs, built for agentic workflows, instruction following, factual accuracy, long-document analysis, and deep research. Reasoning is always active and requests above 200k total tokens are charged at the higher long-context rate. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Average cost: $0.001875","costEstimate":0.001875,"provider":"x-ai","labelVariant":"outline","visible":true,"dateAdded":"2026-04-30","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":1000000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00000125,"output_price":0.0000025,"input_price_per_million":1.25,"output_price_per_million":2.5,"input":1.25,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.0000025","input":1.25,"output":2.5,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":1.25,"completion_per_million":2.5,"prompt_per_token":"0.00000125","completion_per_token":"0.0000025","per_input_token":0.00000125,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":465.9},"x-ai/grok-4.5":{"name":"Grok 4.5","model":"x-ai/grok-4.5","description":"Grok 4.5 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Average cost: $0.004","costEstimate":0.004,"provider":"x-ai","labelVariant":"outline","visible":true,"dateAdded":"2026-07-08","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":500000,"maxOutputTokens":500000,"preferredProviders":["xai/zdr"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":1032.1},"x-ai/grok-4.6":{"name":"Grok 4.6","model":"x-ai/grok-4.6","description":"Grok 4.6 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active, and requests above 200k input tokens use higher long-context rates. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Input $2/M, Output $6/M; above 200k input: $4/M, Output $12/M","costEstimate":0.004,"provider":"x-ai","visible":true,"dateAdded":"2026-08-12","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":500000,"maxOutputTokens":500000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.012,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.012,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":1827},"x-ai/grok-4.7":{"name":"Grok 4.7","model":"x-ai/grok-4.7","description":"Grok 4.7 is SpaceXAI's flagship reasoning model for coding, long-running agentic tasks, and knowledge work. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active, and requests above 200k input tokens use higher long-context rates. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Input $2/M, Output $6/M; above 200k input: $4/M, Output $12/M","costEstimate":0.004,"provider":"x-ai","visible":true,"dateAdded":"2026-09-21","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":500000,"maxOutputTokens":500000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.012,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.012,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":1300.5},"x-ai/grok-build-0.1":{"name":"Grok Build 0.1","model":"x-ai/grok-build-0.1","description":"Grok Build 0.1 is SpaceXAI's fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. Currently in early access. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"x-ai","labelVariant":"outline","visible":true,"dateAdded":"2026-05-20","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":256000,"maxOutputTokens":256000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000002,"input_price_per_million":1,"output_price_per_million":2,"input":1,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000002","input":1,"output":2,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":1,"completion_per_million":2,"prompt_per_token":"0.000001","completion_per_token":"0.000002","per_input_token":0.000001,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.002,"inputPer1kTokensAbove200k":0.002,"outputPer1kTokensAbove200k":0.004,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.002,"inputPer1kTokensAbove200k":0.002,"outputPer1kTokensAbove200k":0.004,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":2960.1},"x-ai/grok-latest":{"name":"Grok Latest","model":"x-ai/grok-latest","description":"Compatibility alias that routes to the newest Grok model. Currently routes to Grok 4.7. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Input $2/M, Output $6/M; above 200k input: $4/M, Output $12/M","costEstimate":0.004,"provider":"x-ai","labelVariant":"outline","visible":true,"dateAdded":"2026-05-03","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":500000,"maxOutputTokens":500000,"tags":["latest"],"preferredProviders":["xai/zdr"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.012,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.012,"highContextThresholdTokens":200000,"cacheReadInputPer1kTokens":0.0005,"cacheReadInputPer1kTokensAbove200k":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"}},"x-ai/grok-4.20":{"name":"Grok 4.20","model":"x-ai/grok-4.20","description":"SpaceXAI's Grok 4.20 flagship release with tool calling, multimodal input support, and a 2M-token context window. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Average cost: $0.004","costEstimate":0.004,"provider":"x-ai","labelVariant":"outline","visible":true,"dateAdded":"2026-03-31","category":"More","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":2000000,"maxOutputTokens":131072,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":678.9},"x-ai/grok-4.20-multi-agent":{"name":"Grok 4.20 Multi-Agent","model":"x-ai/grok-4.20-multi-agent","description":"Grok 4.20 Multi-Agent is tuned for collaborative agentic workflows while keeping the same 2M-token context window and multimodal support. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.","cost":"Average cost: $0.004","costEstimate":0.004,"provider":"x-ai","labelVariant":"outline","visible":true,"dateAdded":"2026-03-31","category":"More","capabilities":["vision","reasoning","structured-output"],"maxInputTokens":2000000,"maxOutputTokens":131072,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":3303.3},"openai/gpt-4.1-nano":{"name":"GPT 4.1 Nano","model":"openai/gpt-4.1-nano","description":"Cheapest model in the GPT-4.1 series. Huge context window with fast throughput and low latency.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"openai","labelVariant":"outline","visible":true,"category":"More","capabilities":["pdf-upload"],"maxInputTokens":1047576,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":49.1},"openai/gpt-4.1-mini":{"name":"GPT 4.1 Mini","model":"openai/gpt-4.1-mini","description":"Mid-sized GPT 4.1, comparable to GPT4o with a far higher context window, at lower cost and with higher speed.","cost":"Average cost: $0.0022","costEstimate":0.0022,"provider":"openai","labelVariant":"outline","visible":true,"dateAdded":"2025-09-10","category":"More","maxInputTokens":1047576,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000016,"input_price_per_million":0.4,"output_price_per_million":1.6,"input":0.4,"output":1.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000016","input":0.4,"output":1.6,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":0.4,"completion_per_million":1.6,"prompt_per_token":"0.0000004","completion_per_token":"0.0000016","per_input_token":4e-7,"per_output_token":0.0000016},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0016,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0016,"cacheReadInputPer1kTokens":0.0001},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.366Z"},"avgOutputTokens":18.5},"mistralai/mistral-medium-3":{"name":"Mistral Medium 3","model":"mistralai/mistral-medium-3","description":"Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost. On performance, Mistral Medium 3 also surpasses leading open models such as Llama 4 Maverick and enterprise models such as Cohere Command A. On pricing, the model beats cost leaders such as DeepSeek v3, both in API and self-deployed systems.","cost":"Average cost: $0.0026","costEstimate":0.0026,"provider":"mistral","labelVariant":"outline","visible":true,"dateAdded":"2025-09-25","isOpenSource":false,"category":"More","maxInputTokens":131072,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.000002,"input_price_per_million":0.4,"output_price_per_million":2,"input":0.4,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.000002","input":0.4,"output":2,"prompt_per_million":0.4,"completion_per_million":2,"prompt_per_token":"0.0000004","completion_per_token":"0.000002","per_input_token":4e-7,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.002},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":682.7},"mistralai/mistral-medium-3.1":{"name":"Mistral Medium 3.1","model":"mistralai/mistral-medium-3.1","description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across deployment environments.","cost":"Average cost: $0.0026","costEstimate":0.0026,"provider":"mistral","labelVariant":"outline","visible":true,"dateAdded":"2025-09-05","isOpenSource":false,"category":"More","maxInputTokens":131072,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.000002,"input_price_per_million":0.4,"output_price_per_million":2,"input":0.4,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.000002","input":0.4,"output":2,"prompt_per_million":0.4,"completion_per_million":2,"prompt_per_token":"0.0000004","completion_per_token":"0.000002","per_input_token":4e-7,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.002},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":59.8},"mistralai/codestral-2508":{"name":"Codestral 2508","model":"mistralai/codestral-2508","description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"mistral","visible":true,"dateAdded":"2025-08-01","isOpenSource":false,"category":"More","maxInputTokens":256000,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":9e-7,"input_price_per_million":0.3,"output_price_per_million":0.9,"input":0.3,"output":0.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000009","input":0.3,"output":0.9,"prompt_per_million":0.3,"completion_per_million":0.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000009","per_input_token":3e-7,"per_output_token":9e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0009},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0009},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":124.1},"openai/gpt-4.1":{"name":"GPT 4.1","model":"openai/gpt-4.1","description":"GPT 4.1 is the new flagship model from OpenAI. Huge context window (1 mln tokens), outperforms GPT-4o and GPT 4.5 across coding and does very well at understanding large contexts.","cost":"Average cost: $0.0044","costEstimate":0.0044,"provider":"openai","category":"More","labelVariant":"outline","visible":true,"dateAdded":"2025-09-10","capabilities":["pdf-upload","tool-calling","structured-output"],"maxInputTokens":1047576,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000008,"input_price_per_million":2,"output_price_per_million":8,"input":2,"output":8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000008","input":2,"output":8,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2,"completion_per_million":8,"prompt_per_token":"0.000002","completion_per_token":"0.000008","per_input_token":0.000002,"per_output_token":0.000008},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.008,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.008,"cacheReadInputPer1kTokens":0.0005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":29.2},"openai/o3":{"name":"OpenAI o3","model":"openai/o3","description":"OpenAI o3 is a reasoning model for complex analytical, coding, mathematical, and scientific tasks.","cost":"Average cost: $0.0044","costEstimate":0.0044,"provider":"openai","labelVariant":"outline","visible":true,"dateAdded":"2025-04-16","capabilities":["reasoning"],"maxInputTokens":200000,"maxOutputTokens":100000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000002,"output_price":0.000008,"input_price_per_million":2,"output_price_per_million":8,"input":2,"output":8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000008","input":2,"output":8,"cacheReadInputPer1kTokens":0.001,"prompt_per_million":2,"completion_per_million":8,"prompt_per_token":"0.000002","completion_per_token":"0.000008","per_input_token":0.000002,"per_output_token":0.000008},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.008,"cacheReadInputPer1kTokens":0.001},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.008,"cacheReadInputPer1kTokens":0.001},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":204.6},"openai/o4-mini":{"name":"OpenAI o4-mini","model":"openai/o4-mini","description":"OpenAI o4-mini. The next generation of OpenAI models.","cost":"Average cost: $0.01","costEstimate":0.01,"provider":"openai","labelVariant":"outline","visible":true,"dateAdded":"2025-04-16","maxInputTokens":200000,"maxOutputTokens":100000,"capabilities":["vision-by-description","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000044,"input_price_per_million":1.1,"output_price_per_million":4.4,"input":1.1,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000044","input":1.1,"output":4.4,"cacheReadInputPer1kTokens":0.00055,"prompt_per_million":1.1,"completion_per_million":4.4,"prompt_per_token":"0.0000011","completion_per_token":"0.0000044","per_input_token":0.0000011,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":65.6},"openai/o4-mini-high":{"name":"OpenAI o4-mini high","model":"openai/o4-mini-high","description":"The maximum/high version of the o4-mini model. The next generation of OpenAI models.","cost":"Average cost: $0.01","costEstimate":0.01,"dateAdded":"2025-12-04","provider":"openai","labelVariant":"outline","visible":true,"maxInputTokens":200000,"maxOutputTokens":100000,"capabilities":["vision-by-description","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000044,"input_price_per_million":1.1,"output_price_per_million":4.4,"input":1.1,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000044","input":1.1,"output":4.4,"cacheReadInputPer1kTokens":0.00055,"prompt_per_million":1.1,"completion_per_million":4.4,"prompt_per_token":"0.0000011","completion_per_token":"0.0000044","per_input_token":0.0000011,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":74.5},"meta-llama/llama-4-scout":{"totalParams":109,"activeParams":17,"name":"Llama 4 Scout","model":"meta-llama/llama-4-scout","description":"Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout offers an industry-leading context window of 10M and delivers better results than Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 across a broad range of widely reported benchmarks.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"meta","labelVariant":"outline","visible":true,"dateAdded":"2025-09-05","isOpenSource":true,"category":"More","preferredProviders":["DeepInfra"],"capabilities":["tool-calling","structured-output","vision"],"maxInputTokens":328000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":8.5e-8,"output_price":4.6e-7,"input_price_per_million":0.085,"output_price_per_million":0.46,"input":0.085,"output":0.46,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000085","completion":"0.00000046","input":0.085,"output":0.46,"prompt_per_million":0.085,"completion_per_million":0.46,"prompt_per_token":"0.000000085","completion_per_token":"0.00000046","per_input_token":8.5e-8,"per_output_token":4.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000085,"outputPer1kTokens":0.00046},"effective_price":{"inputPer1kTokens":0.000085,"outputPer1kTokens":0.00046},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":78.9},"deepseek-ai/DeepSeek-R1-0528":{"totalParams":671,"activeParams":37,"name":"DeepSeek R1 0528","model":"deepseek-ai/DeepSeek-R1-0528","description":"The new (May 28th) Deepseek R1 model.","cost":"Average cost: $0.0041","costEstimate":0.0041,"category":"More","provider":"deepseek","labelVariant":"outline","visible":true,"dateAdded":"2025-05-28","capabilities":["reasoning"],"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":163840,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.00000215,"input_price_per_million":0.5,"output_price_per_million":2.15,"input":0.5,"output":2.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.00000215","input":0.5,"output":2.15,"cacheReadInputPer1kTokens":0.00035,"prompt_per_million":0.5,"completion_per_million":2.15,"prompt_per_token":"0.0000005","completion_per_token":"0.00000215","per_input_token":5e-7,"per_output_token":0.00000215},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.00215,"cacheReadInputPer1kTokens":0.00035},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.00215,"cacheReadInputPer1kTokens":0.00035},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":1046.4},"moonshotai/Kimi-K2-Instruct-0905":{"totalParams":1000,"activeParams":32,"name":"Kimi K2 0905","model":"moonshotai/Kimi-K2-Instruct-0905","description":"Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.","category":"More","cost":"Average cost: $0.006","costEstimate":0.006,"provider":"moonshot","visible":true,"dateAdded":"2025-09-25","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":262144,"capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000018,"input_price_per_million":0.4,"output_price_per_million":1.8,"input":0.4,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000018","input":0.4,"output":1.8,"prompt_per_million":0.4,"completion_per_million":1.8,"prompt_per_token":"0.0000004","completion_per_token":"0.0000018","per_input_token":4e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":676.5},"moonshotai/kimi-k2-thinking":{"totalParams":1000,"activeParams":32,"name":"Kimi K2 Thinking","model":"moonshotai/kimi-k2-thinking","description":"Moonshot AI's distinct Kimi K2 Thinking checkpoint is a mandatory-reasoning model for long-horizon agentic workflows and multi-step tool use.","category":"More","cost":"Average cost: $0.0039","costEstimate":0.0039,"provider":"moonshot","visible":true,"isOpenSource":true,"dateAdded":"2025-11-06","capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":262144,"maxOutputTokens":98304,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000025,"input_price_per_million":0.6,"output_price_per_million":2.5,"input":0.6,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000025","input":0.6,"output":2.5,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":0.6,"completion_per_million":2.5,"prompt_per_token":"0.0000006","completion_per_token":"0.0000025","per_input_token":6e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":1888.5},"moonshotai/kimi-k2.5":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.5","model":"moonshotai/kimi-k2.5","description":"Kimi K2.5 is Moonshot AI's native multimodal model built on Kimi K2 with ~15T mixed visual and text tokens, delivering strong general reasoning, visual coding, and agentic tool-calling. This route uses instant (non-thinking) mode for faster responses.","visible":true,"provider":"moonshot","dateAdded":"2026-01-26","isOpenSource":true,"capabilities":["vision","tool-calling"],"maxInputTokens":256000,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":0.6,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"cost":"Average cost: $0.0039","costEstimate":0.0039,"api":"chat","input_price":3e-7,"output_price":0.0000019,"input_price_per_million":0.3,"output_price_per_million":1.9,"input":0.3,"output":1.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000019","input":0.3,"output":1.9,"prompt_per_million":0.3,"completion_per_million":1.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000019","per_input_token":3e-7,"per_output_token":0.0000019},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":437.3},"moonshotai/kimi-k2.5:thinking":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.5 Thinking","model":"moonshotai/kimi-k2.5:thinking","description":"Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.","visible":true,"provider":"moonshot","dateAdded":"2026-01-26","isOpenSource":true,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls"],"maxInputTokens":256000,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"cost":"Average cost: $0.0039","costEstimate":0.0039,"api":"chat","input_price":3e-7,"output_price":0.0000019,"input_price_per_million":0.3,"output_price_per_million":1.9,"input":0.3,"output":1.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000019","input":0.3,"output":1.9,"prompt_per_million":0.3,"completion_per_million":1.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000019","per_input_token":3e-7,"per_output_token":0.0000019},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":2359.4},"moonshotai/kimi-k2.6":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.6","model":"moonshotai/kimi-k2.6","description":"Kimi K2.6 is an open-source, native multimodal agentic model built for long-horizon coding, coding-driven design, and large-scale task orchestration. It can turn simple prompts and visual inputs into production-ready interfaces and full-stack workflows, and is designed to coordinate complex multi-agent plans with thousands of steps across code, documents, and spreadsheets.","visible":true,"provider":"moonshot","dateAdded":"2026-04-16","isOpenSource":true,"capabilities":["vision","tool-calling"],"maxInputTokens":256000,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":0.6,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"cost":"Average cost: $0.0064","costEstimate":0.0064,"api":"chat","input_price":5e-7,"output_price":0.0000026,"input_price_per_million":0.5,"output_price_per_million":2.6,"input":0.5,"output":2.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000026","input":0.5,"output":2.6,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":0.5,"completion_per_million":2.6,"prompt_per_token":"0.0000005","completion_per_token":"0.0000026","per_input_token":5e-7,"per_output_token":0.0000026},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.000125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":593.6},"moonshotai/kimi-latest":{"name":"Kimi Latest","model":"moonshotai/kimi-latest","description":"Always points to the newest recommended Kimi model, currently Kimi K3.1 Pro. Reasoning is always enabled. Select Kimi K3 explicitly to retain its checkpoint and pricing; K3.1 Pro Highspeed is available separately.","visible":true,"provider":"moonshot","dateAdded":"2026-05-03","isOpenSource":false,"capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":1048576,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"cost":"Auto and provider-specific prices can differ. See pricing details for current input, output, and cached-input rates.","costEstimate":0.01,"tags":["latest"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.002,"cacheWriteInputPer1kTokens1h":0.004},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.002,"cacheWriteInputPer1kTokens1h":0.004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"}},"moonshotai/kimi-k2.7-code":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.7 Code","model":"moonshotai/kimi-k2.7-code","description":"Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode; instant/non-thinking mode is not supported.","visible":true,"provider":"moonshot","dateAdded":"2026-06-12","isOpenSource":true,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls"],"maxInputTokens":262144,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"cost":"Average cost: $0.0084","costEstimate":0.0084,"api":"chat","input_price":9.5e-7,"output_price":0.000004,"input_price_per_million":0.95,"output_price_per_million":4,"input":0.95,"output":4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000095","completion":"0.000004","input":0.95,"output":4,"cacheReadInputPer1kTokens":0.00019,"prompt_per_million":0.95,"completion_per_million":4,"prompt_per_token":"0.00000095","completion_per_token":"0.000004","per_input_token":9.5e-7,"per_output_token":0.000004},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00095,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00019},"effective_price":{"inputPer1kTokens":0.00095,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00019},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":1780.3},"moonshotai/kimi-k2.7-code-highspeed":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.7 Code High-Speed","model":"moonshotai/kimi-k2.7-code-highspeed","description":"Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.","visible":true,"provider":"moonshot","dateAdded":"2026-06-15","isOpenSource":true,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls"],"maxInputTokens":262144,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"cost":"Average cost: $0.0179","costEstimate":0.0179,"api":"chat","input_price":0.0000019,"output_price":0.000008,"input_price_per_million":1.9,"output_price_per_million":8,"input":1.9,"output":8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000019","completion":"0.000008","input":1.9,"output":8,"cacheReadInputPer1kTokens":0.00032,"prompt_per_million":1.9,"completion_per_million":8,"prompt_per_token":"0.0000019","completion_per_token":"0.000008","per_input_token":0.0000019,"per_output_token":0.000008},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0019,"outputPer1kTokens":0.008,"cacheReadInputPer1kTokens":0.00032},"effective_price":{"inputPer1kTokens":0.0019,"outputPer1kTokens":0.008,"cacheReadInputPer1kTokens":0.00032},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":491.1},"moonshotai/kimi-k2.6:thinking":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.6 Thinking","model":"moonshotai/kimi-k2.6:thinking","description":"Kimi K2.6 Thinking is the reasoning-optimized K2.6 variant for deeper multi-step planning and execution. It is tuned for long-horizon coding and design workflows, including complex orchestration across many specialized sub-agents and autonomous end-to-end output generation.","visible":true,"provider":"moonshot","dateAdded":"2026-04-16","isOpenSource":true,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls"],"maxInputTokens":256000,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"cost":"Average cost: $0.0064","costEstimate":0.0064,"api":"chat","input_price":5e-7,"output_price":0.0000026,"input_price_per_million":0.5,"output_price_per_million":2.6,"input":0.5,"output":2.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000026","input":0.5,"output":2.6,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":0.5,"completion_per_million":2.6,"prompt_per_token":"0.0000005","completion_per_token":"0.0000026","per_input_token":5e-7,"per_output_token":0.0000026},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.000125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":3981.8},"moonshotai/kimi-k2-instruct":{"totalParams":1000,"activeParams":32,"name":"Kimi K2 Instruct","model":"moonshotai/kimi-k2-instruct","description":"Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.","visible":true,"provider":"moonshot","maxInputTokens":256000,"maxOutputTokens":8192,"category":"More","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"isOpenSource":true,"cost":"Average cost: $0.006","costEstimate":0.006,"api":"chat","input_price":4e-7,"output_price":0.0000018,"input_price_per_million":0.4,"output_price_per_million":1.8,"input":0.4,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000018","input":0.4,"output":1.8,"prompt_per_million":0.4,"completion_per_million":1.8,"prompt_per_token":"0.0000004","completion_per_token":"0.0000018","per_input_token":4e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.367Z"},"avgOutputTokens":564.2},"moonshotai/kimi-k2-instruct-0711":{"totalParams":1000,"activeParams":32,"name":"Kimi K2 0711","model":"moonshotai/kimi-k2-instruct-0711","description":"Kimi K2 0711 version. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.","visible":true,"provider":"moonshot","maxInputTokens":128000,"maxOutputTokens":8192,"category":"More","capabilities":["tool-calling"],"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"isOpenSource":true,"cost":"Average cost: $0.006","costEstimate":0.006,"api":"chat","input_price":4e-7,"output_price":0.0000018,"input_price_per_million":0.4,"output_price_per_million":1.8,"input":0.4,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000018","input":0.4,"output":1.8,"prompt_per_million":0.4,"completion_per_million":1.8,"prompt_per_token":"0.0000004","completion_per_token":"0.0000018","per_input_token":4e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":734.5},"mistralai/ministral-14b-instruct-2512":{"totalParams":14,"name":"Ministral 3 14B","model":"mistralai/ministral-14b-instruct-2512","description":"Ministral 3 14B is a balanced model in the Ministral 3 family, designed for edge deployment. A powerful, efficient language model with vision capabilities, fine-tuned for instruction tasks. Features multilingual support, strong system prompt adherence, and native function calling. Apache 2.0 licensed.","cost":"Average cost: $0.0005","costEstimate":0.0005,"provider":"mistral","visible":true,"dateAdded":"2025-12-02","category":"More","isOpenSource":true,"capabilities":["vision"],"maxInputTokens":262144,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":203.3},"mistralai/mistral-small-4-119b-2603":{"totalParams":119,"activeParams":6,"name":"Mistral Small 4 119B","model":"mistralai/mistral-small-4-119b-2603","description":"Mistral Small 4 is a hybrid MoE model that unifies instruct, reasoning, and coding behavior in a single multimodal model. It supports text and image input, native function calling, JSON output, and per-request reasoning effort controls.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"mistral","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-03-16","maxInputTokens":262144,"maxOutputTokens":16384,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000014,"input_price_per_million":0.4,"output_price_per_million":1.4,"input":0.4,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000014","input":0.4,"output":1.4,"prompt_per_million":0.4,"completion_per_million":1.4,"prompt_per_token":"0.0000004","completion_per_token":"0.0000014","per_input_token":4e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":92},"mistralai/mistral-small-4-119b-2603:thinking":{"totalParams":119,"activeParams":6,"name":"Mistral Small 4 119B Thinking","model":"mistralai/mistral-small-4-119b-2603:thinking","description":"Mistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"mistral","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-03-17","maxInputTokens":262144,"maxOutputTokens":16384,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4e-7,"output_price":0.0000014,"input_price_per_million":0.4,"output_price_per_million":1.4,"input":0.4,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000014","input":0.4,"output":1.4,"prompt_per_million":0.4,"completion_per_million":1.4,"prompt_per_token":"0.0000004","completion_per_token":"0.0000014","per_input_token":4e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":996.6},"mistralai/devstral-2-123b-instruct-2512":{"totalParams":123,"name":"Devstral 2 123B","model":"mistralai/devstral-2-123b-instruct-2512","description":"Devstral 2 123B is a 123 billion parameter model from Mistral AI optimized for coding and development tasks. Features advanced reasoning capabilities for software engineering workflows.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"mistral","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2025-12-09","maxInputTokens":262144,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000014,"input_price_per_million":0.4,"output_price_per_million":1.4,"input":0.4,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000014","input":0.4,"output":1.4,"prompt_per_million":0.4,"completion_per_million":1.4,"prompt_per_token":"0.0000004","completion_per_token":"0.0000014","per_input_token":4e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":119.8},"mistralai/mixtral-8x22b-instruct-v0.1":{"totalParams":141,"activeParams":39,"name":"Mixtral 8x22B","model":"mistralai/mixtral-8x22b-instruct-v0.1","description":"Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.","cost":"Average cost: $0.008","costEstimate":0.008,"provider":"mistral","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2025-12-11","maxInputTokens":65536,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":292.1},"nousresearch/hermes-4-405b:thinking":{"totalParams":405,"name":"Hermes 4 Large (Thinking)","model":"nousresearch/hermes-4-405b:thinking","visible":true,"category":"More","isOpenSource":true,"capabilities":["structured-output"],"maxInputTokens":128000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"description":"Hermes 4 Large with thinking enabled. Streams visible reasoning before the final answer and supports structured outputs.","cost":"Average cost: $0.002","costEstimate":0.002,"api":"chat","input_price":3e-7,"output_price":0.0000012,"input_price_per_million":0.3,"output_price_per_million":1.2,"input":0.3,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000012","input":0.3,"output":1.2,"prompt_per_million":0.3,"completion_per_million":1.2,"prompt_per_token":"0.0000003","completion_per_token":"0.0000012","per_input_token":3e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":1019.6},"doubao-seed-2-0-code-preview-260215":{"name":"Doubao Seed 2.0 Code Preview","model":"doubao-seed-2-0-code-preview-260215","description":"Code-focused preview model in the Doubao Seed 2.0 family. Supports a 256k context window and up to 128k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.0030","costEstimate":0.003,"category":"More","provider":"doubao","visible":true,"dateAdded":"2026-02-14","maxInputTokens":256000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.82e-7,"output_price":0.000003893,"input_price_per_million":0.782,"output_price_per_million":3.893,"input":0.782,"output":3.893,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000782","completion":"0.000003893","input":0.782,"output":3.893,"prompt_per_million":0.782,"completion_per_million":3.893,"prompt_per_token":"0.000000782","completion_per_token":"0.000003893","per_input_token":7.82e-7,"per_output_token":0.000003893},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000782,"outputPer1kTokens":0.003893},"effective_price":{"inputPer1kTokens":0.000782,"outputPer1kTokens":0.003893},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"doubao-seed-2-0-lite-260215":{"name":"Doubao Seed 2.0 Lite","model":"doubao-seed-2-0-lite-260215","description":"Lower-cost variant in the Doubao Seed 2.0 family for fast general usage. Supports a 256k context window and up to 32k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.00066","costEstimate":0.00066,"category":"More","provider":"doubao","visible":true,"dateAdded":"2026-02-14","maxInputTokens":256000,"maxOutputTokens":32000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.462e-7,"output_price":8.738e-7,"input_price_per_million":0.1462,"output_price_per_million":0.8738,"input":0.1462,"output":0.8738,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001462","completion":"0.0000008738","input":0.1462,"output":0.8738,"prompt_per_million":0.1462,"completion_per_million":0.8738,"prompt_per_token":"0.0000001462","completion_per_token":"0.0000008738","per_input_token":1.462e-7,"per_output_token":8.738e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001462,"outputPer1kTokens":0.0008738},"effective_price":{"inputPer1kTokens":0.0001462,"outputPer1kTokens":0.0008738},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"doubao-seed-2-0-mini-260215":{"name":"Doubao Seed 2.0 Mini","model":"doubao-seed-2-0-mini-260215","description":"Smallest and most affordable model in the Doubao Seed 2.0 family. Supports a 256k context window and up to 32k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.00035","costEstimate":0.00035,"category":"More","provider":"doubao","visible":true,"dateAdded":"2026-02-14","maxInputTokens":256000,"maxOutputTokens":32000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-8,"output_price":4.845e-7,"input_price_per_million":0.0493,"output_price_per_million":0.4845,"input":0.0493,"output":0.4845,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000000493","completion":"0.0000004845","input":0.0493,"output":0.4845,"prompt_per_million":0.0493,"completion_per_million":0.4845,"prompt_per_token":"0.0000000493","completion_per_token":"0.0000004845","per_input_token":4.93e-8,"per_output_token":4.845e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000493,"outputPer1kTokens":0.0004845},"effective_price":{"inputPer1kTokens":0.0000493,"outputPer1kTokens":0.0004845},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"doubao-seed-2-0-pro-260215":{"name":"Doubao Seed 2.0 Pro","model":"doubao-seed-2-0-pro-260215","description":"Highest-capability general model in the Doubao Seed 2.0 family. Supports a 256k context window and up to 128k output tokens. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.0030","costEstimate":0.003,"category":"More","provider":"doubao","visible":true,"dateAdded":"2026-02-14","maxInputTokens":256000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.82e-7,"output_price":0.000003876,"input_price_per_million":0.782,"output_price_per_million":3.876,"input":0.782,"output":3.876,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000782","completion":"0.000003876","input":0.782,"output":3.876,"prompt_per_million":0.782,"completion_per_million":3.876,"prompt_per_token":"0.000000782","completion_per_token":"0.000003876","per_input_token":7.82e-7,"per_output_token":0.000003876},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000782,"outputPer1kTokens":0.003876},"effective_price":{"inputPer1kTokens":0.000782,"outputPer1kTokens":0.003876},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"bytedance/doubao-seed-2.1-pro":{"name":"Doubao Seed 2.1 Pro","model":"bytedance/doubao-seed-2.1-pro","description":"Higher-capability model in the Doubao Seed 2.1 family for agentic coding, long-context analysis, complex instruction following, and productivity workflows. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","cost":"Average cost: $0.0050","costEstimate":0.005,"category":"More","provider":"doubao","visible":true,"dateAdded":"2026-06-23","maxInputTokens":256000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000005,"input_price_per_million":1,"output_price_per_million":5,"input":1,"output":5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000005","input":1,"output":5,"prompt_per_million":1,"completion_per_million":5,"prompt_per_token":"0.000001","completion_per_token":"0.000005","per_input_token":0.000001,"per_output_token":0.000005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.005},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":2720.5},"bytedance/doubao-seed-2.1-turbo":{"name":"Doubao Seed 2.1 Turbo","model":"bytedance/doubao-seed-2.1-turbo","description":"Fast, lower-cost model in the Doubao Seed 2.1 family for everyday chat, coding assistance, document work, and high-throughput productivity tasks. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","cost":"Average cost: $0.0025","costEstimate":0.0025,"category":"More","provider":"doubao","visible":true,"dateAdded":"2026-06-23","maxInputTokens":256000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.0000025,"input_price_per_million":0.5,"output_price_per_million":2.5,"input":0.5,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000025","input":0.5,"output":2.5,"prompt_per_million":0.5,"completion_per_million":2.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000025","per_input_token":5e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"doubao-1.5-pro-256k":{"name":"Doubao 1.5 Pro 256k","model":"doubao-1.5-pro-256k","description":"Doubao's (Bytedance) flagship model with a 256k token context window. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.0017","costEstimate":0.0017,"category":"More","provider":"doubao","visible":true,"dateAdded":"2025-03-12","maxInputTokens":256000,"maxOutputTokens":16384,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.99e-7,"output_price":0.000001445,"input_price_per_million":0.799,"output_price_per_million":1.445,"input":0.799,"output":1.445,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000799","completion":"0.000001445","input":0.799,"output":1.445,"prompt_per_million":0.799,"completion_per_million":1.445,"prompt_per_token":"0.000000799","completion_per_token":"0.000001445","per_input_token":7.99e-7,"per_output_token":0.000001445},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.001445},"effective_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.001445},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"claude-opus-4-20250514":{"name":"Claude 4 Opus","model":"anthropic/claude-opus-4","description":"Claude 4 Opus is no longer available on NanoGPT because no providers remain for it.","cost":"Average cost: $0.1149","costEstimate":0.1149,"labelVariant":"outline","provider":"anthropic","category":"More","visible":true,"disabled":true,"dateAdded":"2025-08-05","capabilities":["vision","pdf-upload","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":32000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"claude-opus-4-thinking":{"name":"Claude 4 Opus Thinking","model":"anthropic/claude-opus-4:thinking","description":"Claude 4 Opus Thinking is no longer available on NanoGPT because no providers remain for it.","cost":"Average cost: $0.1749","costEstimate":0.1749,"provider":"anthropic","visible":true,"disabled":true,"dateAdded":"2025-07-15","category":"More","labelVariant":"outline","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"pamanseau/OpenReasoning-Nemotron-32B":{"totalParams":32,"name":"OpenReasoning Nemotron 32B","model":"pamanseau/OpenReasoning-Nemotron-32B","description":"OpenReasoning-Nemotron-32B is a reasoning model derived from Qwen2.5-32B-Instruct, post-trained for math, science, and code solution generation. Evaluated with up to 64K output tokens. Available in multiple sizes: 1.5B, 7B, 14B, and 32B.","cost":"Average cost: $0.00025","costEstimate":0.00025,"labelVariant":"outline","provider":"openreasoning","category":"More","visible":true,"dateAdded":"2025-08-21","capabilities":["vision-by-description","reasoning"],"isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"}},"aion-labs/aion-2.0":{"name":"AionLabs: Aion-2.0","model":"aion-labs/aion-2.0","description":"Aion-2.0 is a DeepSeek V3.2 variant tuned for immersive roleplay and storytelling with stronger tension, conflict, and darker thematic nuance.","cost":"Average cost: $0.0024","costEstimate":0.0024,"visible":true,"dateAdded":"2026-02-23","isOpenSource":false,"maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","provider":"aionlabs","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":8e-7,"output_price":0.0000016,"input_price_per_million":0.8,"output_price_per_million":1.6,"input":0.8,"output":1.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000008","completion":"0.0000016","input":0.8,"output":1.6,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.8,"completion_per_million":1.6,"prompt_per_token":"0.0000008","completion_per_token":"0.0000016","per_input_token":8e-7,"per_output_token":0.0000016},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0008,"outputPer1kTokens":0.0016,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0008,"outputPer1kTokens":0.0016,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":630.9},"aion-labs/aion-3.0":{"name":"AionLabs: Aion 3.0","model":"aion-labs/aion-3.0","description":"Aion 3.0 is a GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","cost":"Average cost: $0.0090","costEstimate":0.009,"visible":true,"dateAdded":"2026-07-07","isOpenSource":false,"maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","provider":"aionlabs","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000003,"output_price":0.000006,"input_price_per_million":3,"output_price_per_million":6,"input":3,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000006","input":3,"output":6,"cacheReadInputPer1kTokens":0.00075,"prompt_per_million":3,"completion_per_million":6,"prompt_per_token":"0.000003","completion_per_token":"0.000006","per_input_token":0.000003,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00075},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":1053.3},"aion-labs/aion-3.0-mini":{"name":"AionLabs: Aion 3.0 Mini","model":"aion-labs/aion-3.0-mini","description":"Aion 3.0 Mini is a DeepSeek-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","cost":"Average cost: $0.0021","costEstimate":0.0021,"visible":true,"dateAdded":"2026-07-07","isOpenSource":false,"maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","provider":"aionlabs","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":0.0000014,"input_price_per_million":0.7,"output_price_per_million":1.4,"input":0.7,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000014","input":0.7,"output":1.4,"cacheReadInputPer1kTokens":0.00018,"prompt_per_million":0.7,"completion_per_million":1.4,"prompt_per_token":"0.0000007","completion_per_token":"0.0000014","per_input_token":7e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0014,"cacheReadInputPer1kTokens":0.00018},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0014,"cacheReadInputPer1kTokens":0.00018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":1041.2},"aion-labs/aion-3.5":{"name":"AionLabs: Aion 3.5","model":"aion-labs/aion-3.5","description":"A GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","cost":"Average cost: $0.0090","costEstimate":0.009,"visible":true,"dateAdded":"2026-09-23","isOpenSource":false,"maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","provider":"aionlabs","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000003,"output_price":0.000006,"input_price_per_million":3,"output_price_per_million":6,"input":3,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000006","input":3,"output":6,"cacheReadInputPer1kTokens":0.00075,"prompt_per_million":3,"completion_per_million":6,"prompt_per_token":"0.000003","completion_per_token":"0.000006","per_input_token":0.000003,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00075},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.368Z"},"avgOutputTokens":1356.4},"aion-labs/aion-3.5-mini":{"name":"AionLabs: Aion 3.5 Mini","model":"aion-labs/aion-3.5-mini","description":"A GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","cost":"Average cost: $0.0021","costEstimate":0.0021,"visible":true,"dateAdded":"2026-09-23","isOpenSource":false,"maxInputTokens":262144,"maxOutputTokens":32768,"category":"More","provider":"aionlabs","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":0.0000014,"input_price_per_million":0.7,"output_price_per_million":1.4,"input":0.7,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000014","input":0.7,"output":1.4,"cacheReadInputPer1kTokens":0.00018,"prompt_per_million":0.7,"completion_per_million":1.4,"prompt_per_token":"0.0000007","completion_per_token":"0.0000014","per_input_token":7e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0014,"cacheReadInputPer1kTokens":0.00018},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0014,"cacheReadInputPer1kTokens":0.00018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":1648.1},"deepseek-chat":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3/Deepseek Chat","usageName":"DeepSeek V3","model":"deepseek-chat","description":"DeepSeek original V3 model, trained on nearly 15 trillion tokens, matches leading closed-source models at a far lower price. Quantized at FP8.","cost":"Average cost: $0.0012","category":"More","costEstimate":0.0012,"provider":"deepseek","visible":true,"dateAdded":"2025-02-27","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":8192,"capabilities":["pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4.25e-7,"input_price_per_million":0.1,"output_price_per_million":0.425,"input":0.1,"output":0.425,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.000000425","input":0.1,"output":0.425,"prompt_per_million":0.1,"completion_per_million":0.425,"prompt_per_token":"0.0000001","completion_per_token":"0.000000425","per_input_token":1e-7,"per_output_token":4.25e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.000425},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.000425},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":293.2},"minimax/minimax-01":{"totalParams":456,"activeParams":45.9,"name":"MiniMax 01","model":"minimax/minimax-01","description":"MiniMax's flagship model with a 1M token context window","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"minimax","visible":true,"capabilities":["vision-by-description","pdf-upload"],"maxInputTokens":1000192,"maxOutputTokens":16384,"isOpenSource":false,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.394e-7,"output_price":0.000001122,"input_price_per_million":0.1394,"output_price_per_million":1.122,"input":0.1394,"output":1.122,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001394","completion":"0.000001122","input":0.1394,"output":1.122,"prompt_per_million":0.1394,"completion_per_million":1.122,"prompt_per_token":"0.0000001394","completion_per_token":"0.000001122","per_input_token":1.394e-7,"per_output_token":0.000001122},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001394,"outputPer1kTokens":0.001122},"effective_price":{"inputPer1kTokens":0.0001394,"outputPer1kTokens":0.001122},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"}},"minimax/minimax-m2.5":{"totalParams":230,"activeParams":10,"name":"MiniMax M2.5","model":"minimax/minimax-m2.5","description":"MiniMax M2.5 is a productivity-focused flagship model that builds on M2.1 with stronger coding and real-world office workflow performance (Word, Excel, PowerPoint), plus better tool-use planning and token efficiency.","cost":"Average cost: $0.00075","costEstimate":0.00075,"provider":"minimax","visible":true,"dateAdded":"2026-02-12","capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":204800,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000012,"input_price_per_million":0.3,"output_price_per_million":1.2,"input":0.3,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000012","input":0.3,"output":1.2,"prompt_per_million":0.3,"completion_per_million":1.2,"prompt_per_token":"0.0000003","completion_per_token":"0.0000012","per_input_token":3e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":653.2},"bytedance-seed/seed-2.0-code":{"name":"ByteDance Seed 2.0 Code","model":"bytedance-seed/seed-2.0-code","description":"ByteDance Seed 2.0 Code is a multimodal model optimized for agentic coding, frontend development, multilingual programming, long-running tool workflows, and coding agents. It supports image and video input, a 262k context window, and up to 131k output tokens.","cost":"Input $0.50/M, Output $3/M; above 128k input: $1/M, Output $6/M","costEstimate":0.00175,"provider":"doubao","visible":true,"dateAdded":"2026-08-11","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"maxInputTokens":262144,"maxOutputTokens":131072,"isOpenSource":false,"category":"More","tags":["coding","agent","reasoning","tools","vision","video-input","long-context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":5e-7,"output_price":0.000003,"input_price_per_million":0.5,"output_price_per_million":3,"input":0.5,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.000003","input":0.5,"output":3,"prompt_per_million":0.5,"completion_per_million":3,"prompt_per_token":"0.0000005","completion_per_token":"0.000003","per_input_token":5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.003,"inputPer1kTokensAboveFirstThreshold":0.001,"outputPer1kTokensAboveFirstThreshold":0.006,"firstContextThresholdTokens":128000},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.003,"inputPer1kTokensAboveFirstThreshold":0.001,"outputPer1kTokensAboveFirstThreshold":0.006,"firstContextThresholdTokens":128000},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":112.9},"bytedance-seed/seed-2-1-turbo":{"name":"ByteDance Seed 2.1 Turbo","model":"bytedance-seed/seed-2-1-turbo","description":"ByteDance Seed 2.1 Turbo is a multimodal model for coding and long-horizon agent workflows, including end-to-end software delivery and multi-step task execution. It supports text, image, and video input with a 262k context window.","cost":"Input $0.50/M, Output $2.50/M","costEstimate":0.0015,"provider":"doubao","visible":true,"dateAdded":"2026-08-12","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"maxInputTokens":262144,"maxOutputTokens":262144,"isOpenSource":false,"category":"More","tags":["coding","agent","reasoning","tools","vision","video-input","long-context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.0000025,"input_price_per_million":0.5,"output_price_per_million":2.5,"input":0.5,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000025","input":0.5,"output":2.5,"prompt_per_million":0.5,"completion_per_million":2.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000025","per_input_token":5e-7,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":256.8},"bytedance-seed/seed-2.0-lite":{"name":"ByteDance Seed 2.0 Lite","model":"bytedance-seed/seed-2.0-lite","description":"ByteDance Seed 2.0 Lite is a balanced long-context model for high-frequency enterprise workloads, tuned for unstructured information processing, text creation, search and recommendation, and stable structured outputs. Supports a 262k context window.","cost":"Average cost: $0.0011","costEstimate":0.001125,"provider":"doubao","visible":true,"dateAdded":"2026-03-10","capabilities":["structured-output","vision","video-input"],"maxInputTokens":262144,"maxOutputTokens":131072,"isOpenSource":false,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":0.000002,"input_price_per_million":0.25,"output_price_per_million":2,"input":0.25,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.000002","input":0.25,"output":2,"prompt_per_million":0.25,"completion_per_million":2,"prompt_per_token":"0.00000025","completion_per_token":"0.000002","per_input_token":2.5e-7,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.002,"inputPer1kTokensAboveFirstThreshold":0.0005,"outputPer1kTokensAboveFirstThreshold":0.004,"firstContextThresholdTokens":128000},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.002,"inputPer1kTokensAboveFirstThreshold":0.0005,"outputPer1kTokensAboveFirstThreshold":0.004,"firstContextThresholdTokens":128000},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":131.8},"upstage/solar-pro-3":{"totalParams":102,"activeParams":12,"name":"Solar Pro 3","model":"upstage/solar-pro-3","description":"Upstage's Solar Pro 3 is a Mixture-of-Experts (MoE) language model with 102B total parameters and 12B active parameters per forward pass, optimized for Korean with strong English and Japanese support.","cost":"Average cost: $0.00038","costEstimate":0.00038,"provider":"upstage","visible":true,"dateAdded":"2026-03-03","maxInputTokens":128000,"maxOutputTokens":128000,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"}},"upstage/solar-pro4":{"name":"Solar Pro 4","model":"upstage/solar-pro4","description":"Upstage's Solar Pro 4 is a long-context language model for agentic workflows, office productivity, document-intensive work, and coding. This variant keeps reasoning disabled for faster direct responses.","cost":"Input $0.03/M, Output $0.12/M, Cached input $0.006/M","costEstimate":0.000075,"provider":"upstage","visible":true,"dateAdded":"2026-08-11","maxInputTokens":524288,"maxOutputTokens":131072,"category":"More","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":3e-8,"output_price":1.2e-7,"input_price_per_million":0.03,"output_price_per_million":0.12,"input":0.03,"output":0.12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0.00000012","input":0.03,"output":0.12,"cacheReadInputPer1kTokens":0.000006,"prompt_per_million":0.03,"completion_per_million":0.12,"prompt_per_token":"0.00000003","completion_per_token":"0.00000012","per_input_token":3e-8,"per_output_token":1.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00012,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00012,"cacheReadInputPer1kTokens":0.000006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":546},"upstage/solar-mini4":{"totalParams":35,"activeParams":3,"name":"Solar Mini 4","model":"upstage/solar-mini4","description":"Upstage's compact 35B-parameter mixture-of-experts model with 3B active parameters and a 524K context window. Built for fast, cost-efficient agentic tasks, with strong Korean and English support.","cost":"Input $0.05/M, Output $0.20/M, Cached input $0.005/M","costEstimate":0.000125,"provider":"upstage","visible":true,"dateAdded":"2026-09-23","maxInputTokens":524288,"maxOutputTokens":131072,"category":"More","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":5e-8,"output_price":2e-7,"input_price_per_million":0.05,"output_price_per_million":0.2,"input":0.05,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.0000002","input":0.05,"output":0.2,"cacheReadInputPer1kTokens":0.000005,"prompt_per_million":0.05,"completion_per_million":0.2,"prompt_per_token":"0.00000005","completion_per_token":"0.0000002","per_input_token":5e-8,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000005},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":561},"upstage/solar-mini4:thinking":{"totalParams":35,"activeParams":3,"name":"Solar Mini 4 Thinking","model":"upstage/solar-mini4:thinking","description":"Solar Mini 4 with reasoning enabled for agentic tasks and harder analysis across a 524K-token context window.","cost":"Input $0.05/M, Output $0.20/M, Cached input $0.005/M","costEstimate":0.000125,"provider":"upstage","visible":true,"dateAdded":"2026-09-23","maxInputTokens":524288,"maxOutputTokens":131072,"category":"More","capabilities":["reasoning","tool-calling","structured-output"],"tags":["Thinking","agent","reasoning","tools","long-context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":5e-8,"output_price":2e-7,"input_price_per_million":0.05,"output_price_per_million":0.2,"input":0.05,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.0000002","input":0.05,"output":0.2,"cacheReadInputPer1kTokens":0.000005,"prompt_per_million":0.05,"completion_per_million":0.2,"prompt_per_token":"0.00000005","completion_per_token":"0.0000002","per_input_token":5e-8,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000005},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.000005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":2767.8},"upstage/solar-pro4:thinking":{"name":"Solar Pro 4 Thinking","model":"upstage/solar-pro4:thinking","description":"Upstage's Solar Pro 4 with reasoning enabled for harder agentic workflows, document-intensive work, coding, planning, and analysis across a 524K-token context window.","cost":"Input $0.03/M, Output $0.12/M, Cached input $0.006/M","costEstimate":0.000075,"provider":"upstage","visible":true,"dateAdded":"2026-08-11","maxInputTokens":524288,"maxOutputTokens":131072,"category":"More","capabilities":["reasoning","tool-calling","structured-output"],"tags":["Thinking","agent","reasoning","tools","long-context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":3e-8,"output_price":1.2e-7,"input_price_per_million":0.03,"output_price_per_million":0.12,"input":0.03,"output":0.12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0.00000012","input":0.03,"output":0.12,"cacheReadInputPer1kTokens":0.000006,"prompt_per_million":0.03,"completion_per_million":0.12,"prompt_per_token":"0.00000003","completion_per_token":"0.00000012","per_input_token":3e-8,"per_output_token":1.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00012,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00012,"cacheReadInputPer1kTokens":0.000006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":1691.5},"qwen/qwen3-235b-a22b":{"totalParams":235,"activeParams":22,"name":"Qwen 3 235b A22B","model":"qwen/qwen3-235b-a22b","description":"Qwen 3 235b is a 235b model with 22B active parameters. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.","cost":"Average cost: $0.0014","costEstimate":0.0014,"provider":"qwen","visible":true,"dateAdded":"2025-04-29","isOpenSource":true,"capabilities":["pdf-upload","tool-calling","structured-output"],"maxInputTokens":262144,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":5e-7,"input_price_per_million":0.3,"output_price_per_million":0.5,"input":0.3,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000005","input":0.3,"output":0.5,"prompt_per_million":0.3,"completion_per_million":0.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000005","per_input_token":3e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":616.1},"qwen/qwen3.5-9b":{"totalParams":9,"name":"Qwen3.5 9B","model":"qwen/qwen3.5-9b","description":"Qwen3.5 9B is a multimodal foundation model from the Qwen 3.5 family, built for efficient reasoning, coding, and visual understanding in a compact 9B architecture. Requests containing video cost $0.17 per million input tokens and $0.25 per million output tokens.","cost":"Average cost: $0.0001","costEstimate":0.0001,"provider":"qwen","visible":true,"dateAdded":"2026-03-10","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":65536,"category":"More","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":1.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.15,"input":0.05,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000015","input":0.05,"output":0.15,"prompt_per_million":0.05,"completion_per_million":0.15,"prompt_per_token":"0.00000005","completion_per_token":"0.00000015","per_input_token":5e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":1429},"qwen/qwen3-32b":{"totalParams":32,"name":"Qwen 3 32b","model":"qwen/qwen3-32b","description":"Qwen 3 32b is a 32b model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"qwen","visible":true,"capabilities":["vision-by-description","pdf-upload"],"isOpenSource":true,"maxInputTokens":41000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":645.7},"qwen/qwen3-14b":{"totalParams":14,"name":"Qwen 3 14b","model":"qwen/qwen3-14b","description":"Qwen 3 14b is a 14b model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"qwen","visible":true,"capabilities":["vision-by-description"],"isOpenSource":true,"maxInputTokens":41000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":8e-8,"output_price":2.4e-7,"input_price_per_million":0.08,"output_price_per_million":0.24,"input":0.08,"output":0.24,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000008","completion":"0.00000024","input":0.08,"output":0.24,"prompt_per_million":0.08,"completion_per_million":0.24,"prompt_per_token":"0.00000008","completion_per_token":"0.00000024","per_input_token":8e-8,"per_output_token":2.4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00008,"outputPer1kTokens":0.00024},"effective_price":{"inputPer1kTokens":0.00008,"outputPer1kTokens":0.00024},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":226},"qwen/qwen3-30b-a3b":{"totalParams":30,"activeParams":3,"name":"Qwen3 30B A3B","model":"qwen/qwen3-30b-a3b","description":"Qwen 3 30b A3B is a 30b model with 3 billion active parameters per pass. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"qwen","visible":true,"dateAdded":"2025-02-27","isOpenSource":true,"maxInputTokens":41000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":228.1},"qwen3-vl-235b-a22b-thinking":{"totalParams":235,"activeParams":22,"name":"Qwen3 VL 235B A22B Thinking","model":"qwen/qwen3-vl-235b-a22b-thinking","description":"Qwen3 Vision‑Language model built on a 235B MoE backbone (≈22B active per token). Strong at OCR, charts/tables, multi‑image reasoning, and complex document understanding. The Thinking variant enables long‑form, chain‑of‑thought style reasoning.","cost":"Average cost: $0.0033","costEstimate":0.0033,"provider":"qwen","visible":true,"dateAdded":"2025-08-26","isOpenSource":true,"category":"More","maxOutputTokens":32768,"capabilities":["vision","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.000006,"input_price_per_million":0.5,"output_price_per_million":6,"input":0.5,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.000006","input":0.5,"output":6,"prompt_per_million":0.5,"completion_per_million":6,"prompt_per_token":"0.0000005","completion_per_token":"0.000006","per_input_token":5e-7,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.006},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"}},"qwen3-vl-235b-a22b-instruct-original":{"totalParams":235,"activeParams":22,"name":"Qwen3 VL 235B A22B Instruct Original","model":"qwen3-vl-235b-a22b-instruct-original","description":"Routed across multiple providers, which may include Alibaba, a Chinese entity; provider-specific privacy and logging guarantees may vary. Qwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts and diagrams, and multi‑image context. Use this variant when you want concise, direct answers grounded in the visuals.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"qwen","visible":true,"dateAdded":"2025-09-25","isOpenSource":false,"category":"More","maxOutputTokens":32768,"capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000019,"input_price_per_million":0.3,"output_price_per_million":1.9,"input":0.3,"output":1.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000019","input":0.3,"output":1.9,"prompt_per_million":0.3,"completion_per_million":1.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000019","per_input_token":3e-7,"per_output_token":0.0000019},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"},"avgOutputTokens":287.8},"qwen/qwen3-max":{"name":"Qwen3 Max","model":"qwen/qwen3-max","description":"Qwen3 Max improves accuracy in coding and science, instruction following, and tool calling.","cost":"Average cost: $0.0036","costEstimate":0.0036,"provider":"qwen","visible":true,"dateAdded":"2025-09-05","isOpenSource":false,"maxInputTokens":256000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000012002,"output_price":0.000006001,"input_price_per_million":1.2002,"output_price_per_million":6.001,"input":1.2002,"output":6.001,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000012002","completion":"0.000006001","input":1.2002,"output":6.001,"prompt_per_million":1.2002,"completion_per_million":6.001,"prompt_per_token":"0.0000012002","completion_per_token":"0.000006001","per_input_token":0.0000012002,"per_output_token":0.000006001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0012002,"outputPer1kTokens":0.006001},"effective_price":{"inputPer1kTokens":0.0012002,"outputPer1kTokens":0.006001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.369Z"}},"qwen3-coder-30b-a3b-instruct":{"totalParams":30,"activeParams":3,"name":"Qwen3 Coder 30B A3B Instruct","model":"qwen/qwen3-coder-30b-a3b-instruct","description":"Qwen3 Coder 30B with 3B active parameters, optimized for code generation and technical tasks","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"qwen","visible":true,"dateAdded":"2025-08-05","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":65536,"category":"More","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":127},"arcee-ai/trinity-large-thinking":{"totalParams":400,"activeParams":13,"name":"Trinity Large Thinking","model":"arcee-ai/trinity-large-thinking","description":"Open source Arcee reasoning model with a 262K context window, 80K max output, and native reasoning and tool support for agentic workloads.","cost":"Average cost: $0.00115","costEstimate":0.00115,"provider":"arcee","preferredProviders":["Arcee AI"],"visible":true,"dateAdded":"2026-04-01","capabilities":["reasoning","tool-calling"],"maxInputTokens":262144,"maxOutputTokens":80000,"isOpenSource":true,"category":"More","tags":["Thinking","open-source"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":9e-7,"input_price_per_million":0.25,"output_price_per_million":0.9,"input":0.25,"output":0.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000009","input":0.25,"output":0.9,"prompt_per_million":0.25,"completion_per_million":0.9,"prompt_per_token":"0.00000025","completion_per_token":"0.0000009","per_input_token":2.5e-7,"per_output_token":9e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0009},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0009},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":326.9},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"totalParams":235,"activeParams":22,"name":"Qwen 3 235b A22B 2507","model":"qwen/qwen3-235b-a22b-instruct-2507","description":"Qwen 3 235b A22B Instruct 2507 the updated version of Qwen3 235B A22B, with significant improvements in performance. This model is non-thinking.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"qwen","visible":true,"dateAdded":"2025-07-25","isOpenSource":true,"capabilities":["tool-calling","structured-output"],"maxInputTokens":256000,"maxOutputTokens":262144,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.3e-7,"output_price":5e-7,"input_price_per_million":0.13,"output_price_per_million":0.5,"input":0.13,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000013","completion":"0.0000005","input":0.13,"output":0.5,"prompt_per_million":0.13,"completion_per_million":0.5,"prompt_per_token":"0.00000013","completion_per_token":"0.0000005","per_input_token":1.3e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"totalParams":235,"activeParams":22,"name":"Qwen 3 235b A22B 2507 Thinking","model":"qwen/qwen3-235b-a22b-thinking-2507","description":"The thinking version of Qwen 3 235b A22B 2507, with enhanced reasoning capabilities and step-by-step problem solving.","cost":"Average cost: $0.0018","costEstimate":0.0018,"provider":"qwen","visible":true,"dateAdded":"2025-09-11","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":262144,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"enabled","budget_tokens":8000}},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":8000}},"api":"chat","input_price":3e-7,"output_price":5e-7,"input_price_per_million":0.3,"output_price_per_million":0.5,"input":0.3,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000005","input":0.3,"output":0.5,"prompt_per_million":0.3,"completion_per_million":0.5,"prompt_per_token":"0.0000003","completion_per_token":"0.0000005","per_input_token":3e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":3236},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"totalParams":80,"activeParams":3,"name":"Qwen3 Next 80B A3B (Instruct)","model":"qwen/qwen3-next-80b-a3b-instruct","description":"Based on the new Qwen3‑Next architecture (hybrid attention, highly sparse MoE, training‑stability optimizations, and multi‑token prediction), the Qwen3‑Next‑80B‑A3B‑Instruct model delivers extreme efficiency with only 3B active parameters per pass. It performs comparably to Qwen3‑235B‑A22B‑Instruct‑2507 and shows clear advantages on ultra‑long context tasks (up to 256K tokens).","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"qwen","visible":true,"dateAdded":"2025-09-11","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":262144,"category":"More","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":6.5e-7,"input_price_per_million":0.15,"output_price_per_million":0.65,"input":0.15,"output":0.65,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000065","input":0.15,"output":0.65,"prompt_per_million":0.15,"completion_per_million":0.65,"prompt_per_token":"0.00000015","completion_per_token":"0.00000065","per_input_token":1.5e-7,"per_output_token":6.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00065},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00065},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":75.9},"qwen/qwen3-next-80b-a3b-thinking":{"totalParams":80,"activeParams":3,"name":"Qwen3 Next 80B A3B (Thinking)","model":"qwen/qwen3-next-80b-a3b-thinking","visible":true,"isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"description":"Qwen3 Next 80B A3B (Thinking)","cost":"Average cost: $0.0004","costEstimate":0.0004,"provider":"qwen","api":"chat","input_price":1.5e-7,"output_price":6.5e-7,"input_price_per_million":0.15,"output_price_per_million":0.65,"input":0.15,"output":0.65,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000065","input":0.15,"output":0.65,"prompt_per_million":0.15,"completion_per_million":0.65,"prompt_per_token":"0.00000015","completion_per_token":"0.00000065","per_input_token":1.5e-7,"per_output_token":6.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00065},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00065},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"MiniMax-M1":{"totalParams":456,"activeParams":45.9,"name":"MiniMax M1","model":"MiniMax-M1","description":"MiniMax-M1 is a hybrid MoE reasoning model with 40K thinking budget. World's first open-weight, large-scale hybrid-attention model with lightning attention for efficient test-time compute scaling. Excels at complex tasks requiring extensive reasoning.","cost":"Average cost: $0.0030","costEstimate":0.003,"dateAdded":"2025-01-08","provider":"minimax","visible":true,"maxInputTokens":1000000,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.394e-7,"output_price":0.0000013328,"input_price_per_million":0.1394,"output_price_per_million":1.3328,"input":0.1394,"output":1.3328,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001394","completion":"0.0000013328","input":0.1394,"output":1.3328,"prompt_per_million":0.1394,"completion_per_million":1.3328,"prompt_per_token":"0.0000001394","completion_per_token":"0.0000013328","per_input_token":1.394e-7,"per_output_token":0.0000013328},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001394,"outputPer1kTokens":0.0013328},"effective_price":{"inputPer1kTokens":0.0001394,"outputPer1kTokens":0.0013328},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"MiniMaxAI/MiniMax-M1-80k":{"totalParams":456,"activeParams":45.9,"name":"MiniMax M1 80K","model":"MiniMaxAI/MiniMax-M1-80k","description":"MiniMax-M1 with 80K thinking budget. Enhanced version of the hybrid MoE reasoning model with double the thinking capacity. Ideal for extremely complex software engineering, tool use, and long context tasks.","cost":"Average cost: $0.0166","costEstimate":0.0166,"dateAdded":"2025-01-08","provider":"minimax","visible":true,"maxInputTokens":1000000,"maxOutputTokens":131072,"isOpenSource":false,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6.052e-7,"output_price":0.0000024225,"input_price_per_million":0.6052,"output_price_per_million":2.4225,"input":0.6052,"output":2.4225,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006052","completion":"0.0000024225","input":0.6052,"output":2.4225,"prompt_per_million":0.6052,"completion_per_million":2.4225,"prompt_per_token":"0.0000006052","completion_per_token":"0.0000024225","per_input_token":6.052e-7,"per_output_token":0.0000024225},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006052,"outputPer1kTokens":0.0024225},"effective_price":{"inputPer1kTokens":0.0006052,"outputPer1kTokens":0.0024225},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"MiniMax-M2":{"totalParams":230,"activeParams":10,"name":"MiniMax M2","model":"minimax/minimax-m2","description":"MiniMax M2 offers enhanced reasoning and strong general performance. Optimized for coding and agentic workflows.","cost":"Average cost: $0.0042","costEstimate":0.0042,"dateAdded":"2025-01-12","provider":"minimax","visible":true,"maxInputTokens":200000,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.7e-7,"output_price":0.00000153,"input_price_per_million":0.17,"output_price_per_million":1.53,"input":0.17,"output":1.53,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000017","completion":"0.00000153","input":0.17,"output":1.53,"prompt_per_million":0.17,"completion_per_million":1.53,"prompt_per_token":"0.00000017","completion_per_token":"0.00000153","per_input_token":1.7e-7,"per_output_token":0.00000153},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00153},"effective_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00153},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":330.5},"minimax/minimax-m2-her":{"totalParams":230,"activeParams":10,"name":"MiniMax M2-her","model":"minimax/minimax-m2-her","description":"Dialogue-focused MiniMax model optimized for role-playing and multi-turn conversations with rich role settings.","cost":"Average cost: $0.0040","costEstimate":0.004,"dateAdded":"2025-01-12","provider":"minimax","visible":true,"maxInputTokens":65532,"maxOutputTokens":2048,"isOpenSource":false,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["chat","roleplay","dialogue"],"api":"chat","input_price":3.02e-7,"output_price":0.000001207,"input_price_per_million":0.302,"output_price_per_million":1.207,"input":0.302,"output":1.207,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000302","completion":"0.000001207","input":0.302,"output":1.207,"prompt_per_million":0.302,"completion_per_million":1.207,"prompt_per_token":"0.000000302","completion_per_token":"0.000001207","per_input_token":3.02e-7,"per_output_token":0.000001207},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000302,"outputPer1kTokens":0.001207},"effective_price":{"inputPer1kTokens":0.000302,"outputPer1kTokens":0.001207},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":185.6},"minimax/minimax-m3.1-flash":{"name":"MiniMax M3.1 Flash","model":"minimax/minimax-m3.1-flash","description":"MiniMax M3.1 Flash is a multimodal model for coding, tool use, and long-context work. It accepts text, images, and video and produces text, with a 1,000,000-token context window and up to 524,288 output tokens within the remaining context. Thinking is always enabled, with low, medium, high, xhigh, and max effort levels; max is the default. Thinking tokens count toward the output limit. Temperature is fixed at 1 and top-p at 0.95; custom values have no effect.","cost":"Average cost: $0.000375","costEstimate":0.000375,"provider":"minimax","visible":true,"dateAdded":"2026-10-19","capabilities":["vision","video-input","reasoning","tool-calling"],"unsupportedResponseFormatTypes":["json_object","json_schema"],"maxInputTokens":1000000,"maxOutputTokens":524288,"isOpenSource":false,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"adaptive"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":1354.4},"minimax/minimax-m3":{"totalParams":428,"activeParams":23,"name":"MiniMax M3","model":"minimax/minimax-m3","description":"MiniMax M3 is the non-thinking route for MiniMax's open-weights frontier model, built for coding, agent workflows, tool use, and multimodal understanding from step zero. It keeps native thinking disabled for faster direct answers. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.","cost":"Average cost: $0.00075","costEstimate":0.00075,"provider":"minimax","visible":true,"dateAdded":"2026-06-01","capabilities":["vision","tool-calling","structured-output"],"maxInputTokens":512000,"maxOutputTokens":80000,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"api":"chat","input_price":3e-7,"output_price":0.0000012,"input_price_per_million":0.3,"output_price_per_million":1.2,"input":0.3,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000012","input":0.3,"output":1.2,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.3,"completion_per_million":1.2,"prompt_per_token":"0.0000003","completion_per_token":"0.0000012","per_input_token":3e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":491.4},"minimax/minimax-m3:thinking":{"totalParams":428,"activeParams":23,"name":"MiniMax M3 Thinking","model":"minimax/minimax-m3:thinking","description":"MiniMax M3 Thinking is the adaptive-thinking version of MiniMax's open-weights frontier model for coding, agent workflows, tool use, long-context tasks, and native multimodal understanding. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.","cost":"Average cost: $0.00075","costEstimate":0.00075,"provider":"minimax","visible":true,"dateAdded":"2026-06-01","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":512000,"maxOutputTokens":80000,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"adaptive"}},"additionalParams":{"thinking":{"type":"adaptive"}},"api":"chat","input_price":3e-7,"output_price":0.0000012,"input_price_per_million":0.3,"output_price_per_million":1.2,"input":0.3,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000012","input":0.3,"output":1.2,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.3,"completion_per_million":1.2,"prompt_per_token":"0.0000003","completion_per_token":"0.0000012","per_input_token":3e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":1853.1},"minimax/minimax-m2.7":{"totalParams":230,"activeParams":10,"name":"MiniMax M2.7","model":"minimax/minimax-m2.7","description":"MiniMax M2.7 is the first model deeply involved in iterating on its own training. It excels in real-world software engineering (SWE-Pro 56.22%), end-to-end project delivery (VIBE-Pro 55.6%), and complex office workflows with strong tool-use compliance and agentic capabilities.","cost":"Average cost: $0.00075","costEstimate":0.00075,"provider":"minimax","visible":true,"dateAdded":"2026-03-18","capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":204800,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.15e-7,"output_price":0.00000126,"input_price_per_million":0.315,"output_price_per_million":1.26,"input":0.315,"output":1.26,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000315","completion":"0.00000126","input":0.315,"output":1.26,"prompt_per_million":0.315,"completion_per_million":1.26,"prompt_per_token":"0.000000315","completion_per_token":"0.00000126","per_input_token":3.15e-7,"per_output_token":0.00000126},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000315,"outputPer1kTokens":0.00126},"effective_price":{"inputPer1kTokens":0.000315,"outputPer1kTokens":0.00126},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"minimax/minimax-latest":{"name":"MiniMax Latest","model":"minimax/minimax-latest","description":"Compatibility alias for MiniMax M3 Thinking, retaining its existing request format and structured-output support. The newer MiniMax M3.1 Flash is available separately as minimax/minimax-m3.1-flash and has different request parameter support.","cost":"Average cost: $0.00075","costEstimate":0.00075,"provider":"minimax","visible":true,"dateAdded":"2026-05-03","capabilities":["vision","reasoning","tool-calling","structured-output"],"maxInputTokens":512000,"maxOutputTokens":80000,"isOpenSource":true,"category":"More","tags":["latest"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"thinking":{"type":"adaptive"}},"additionalParams":{"thinking":{"type":"adaptive"}},"api":"chat","input_price":3e-7,"output_price":0.0000012,"input_price_per_million":0.3,"output_price_per_million":1.2,"input":0.3,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000012","input":0.3,"output":1.2,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.3,"completion_per_million":1.2,"prompt_per_token":"0.0000003","completion_per_token":"0.0000012","per_input_token":3e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"minimax/minimax-m2.7-turbo":{"totalParams":230,"activeParams":10,"name":"MiniMax M2.7 Turbo","model":"minimax/minimax-m2.7","description":"MiniMax M2.7 Turbo is the highspeed and higher priced route for M2.7.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"minimax","visible":true,"dateAdded":"2026-03-18","capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":204800,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","preferredProviders":["minimax/highspeed"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000024,"input_price_per_million":0.6,"output_price_per_million":2.4,"input":0.6,"output":2.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000024","input":0.6,"output":2.4,"prompt_per_million":0.6,"completion_per_million":2.4,"prompt_per_token":"0.0000006","completion_per_token":"0.0000024","per_input_token":6e-7,"per_output_token":0.0000024},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0024},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0024},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":556.1},"xiaomi/mimo-v2.5":{"totalParams":309,"activeParams":15,"name":"MiMo V2.5","model":"xiaomi/mimo-v2.5","description":"MiMo V2.5 is Xiaomi's full-modal understanding model for agent workflows. It supports tool calling, structured outputs, and web search with up to 1M context.","cost":"Average cost: $0.012","costEstimate":0.012,"provider":"xiaomi","visible":true,"dateAdded":"2026-04-22","isOpenSource":true,"capabilities":["vision","video-input","tool-calling","structured-output","audio-input","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.0000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":457.7},"xiaomi/mimo-v2.5:thinking":{"totalParams":309,"activeParams":15,"name":"MiMo V2.5 Thinking","model":"xiaomi/mimo-v2.5:thinking","description":"MiMo V2.5 with Xiaomi thinking enabled. It supports deep reasoning, tool calling, structured outputs, and web search with up to 1M context.","cost":"Average cost: $0.012","costEstimate":0.012,"provider":"xiaomi","visible":true,"dateAdded":"2026-06-03","isOpenSource":true,"capabilities":["vision","video-input","reasoning","tool-calling","structured-output","audio-input"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.0000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":1086.6},"xiaomi/mimo-v2.5-pro":{"totalParams":1000,"activeParams":42,"name":"MiMo V2.5 Pro","model":"xiaomi/mimo-v2.5-pro","description":"MiMo V2.5 Pro is Xiaomi's long-context flagship general model for coding and agentic orchestration. It supports tool calling and structured outputs with up to 1M context.","cost":"Average cost: $0.02","costEstimate":0.02,"provider":"xiaomi","visible":true,"dateAdded":"2026-04-22","isOpenSource":true,"capabilities":["tool-calling","structured-output","reasoning"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4.35e-7,"output_price":8.7e-7,"input_price_per_million":0.435,"output_price_per_million":0.87,"input":0.435,"output":0.87,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000435","completion":"0.00000087","input":0.435,"output":0.87,"cacheReadInputPer1kTokens":0.0000036,"prompt_per_million":0.435,"completion_per_million":0.87,"prompt_per_token":"0.000000435","completion_per_token":"0.00000087","per_input_token":4.35e-7,"per_output_token":8.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000435,"outputPer1kTokens":0.00087,"cacheReadInputPer1kTokens":0.0000036,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000435,"outputPer1kTokens":0.00087,"cacheReadInputPer1kTokens":0.0000036,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":595.8},"xiaomi/mimo-v2.5-pro:thinking":{"totalParams":1000,"activeParams":42,"name":"MiMo V2.5 Pro Thinking","model":"xiaomi/mimo-v2.5-pro:thinking","description":"MiMo V2.5 Pro with Xiaomi thinking enabled for coding, long-context reasoning, and agentic orchestration.","cost":"Average cost: $0.02","costEstimate":0.02,"provider":"xiaomi","visible":true,"dateAdded":"2026-06-03","isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4.35e-7,"output_price":8.7e-7,"input_price_per_million":0.435,"output_price_per_million":0.87,"input":0.435,"output":0.87,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000435","completion":"0.00000087","input":0.435,"output":0.87,"cacheReadInputPer1kTokens":0.0000036,"prompt_per_million":0.435,"completion_per_million":0.87,"prompt_per_token":"0.000000435","completion_per_token":"0.00000087","per_input_token":4.35e-7,"per_output_token":8.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000435,"outputPer1kTokens":0.00087,"cacheReadInputPer1kTokens":0.0000036,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000435,"outputPer1kTokens":0.00087,"cacheReadInputPer1kTokens":0.0000036,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":1407.5},"xiaomi/mimo-v2.6-flash":{"defaultThinkingEnabled":true,"totalParams":309,"activeParams":15,"name":"MiMo V2.6 Flash","model":"xiaomi/mimo-v2.6-flash","description":"MiMo V2.6 Flash is Xiaomi's native omnimodal 309B-parameter mixture-of-experts model, activating 15B parameters per token. It balances intelligence, efficiency, and cost for coding, general agents, visual tasks, and cybersecurity, with text, image, video, and audio understanding and a 1M-token context window.","cost":"Input $0.14/m, Cached input $0.0028/m, Output $0.28/m","costEstimate":0.00021,"provider":"xiaomi","visible":true,"dateAdded":"2026-09-21","isOpenSource":true,"capabilities":["reasoning","vision","video-input","audio-input","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","tags":["chat","reasoning","coding","agents","vision","video","audio","tools","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.0000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":817.5},"xiaomi/mimo-v2.6-pro":{"defaultThinkingEnabled":true,"totalParams":1020,"activeParams":42,"name":"MiMo V2.6 Pro","model":"xiaomi/mimo-v2.6-pro","description":"MiMo V2.6 Pro is Xiaomi's flagship native omnimodal model, built with 1.02T total parameters and 42B active parameters per token. It is designed for demanding coding, long-horizon agent workflows, visual tasks, research, and cybersecurity, with text, image, video, and audio understanding and a 1M-token context window.","cost":"Input $0.435/m, Cached input $0.0036/m, Output $0.87/m","costEstimate":0.0006525,"provider":"xiaomi","visible":true,"dateAdded":"2026-09-21","isOpenSource":true,"capabilities":["reasoning","vision","video-input","audio-input","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","tags":["chat","reasoning","coding","agents","research","vision","video","audio","tools","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4.35e-7,"output_price":8.7e-7,"input_price_per_million":0.435,"output_price_per_million":0.87,"input":0.435,"output":0.87,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000435","completion":"0.00000087","input":0.435,"output":0.87,"cacheReadInputPer1kTokens":0.0000036,"prompt_per_million":0.435,"completion_per_million":0.87,"prompt_per_token":"0.000000435","completion_per_token":"0.00000087","per_input_token":4.35e-7,"per_output_token":8.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000435,"outputPer1kTokens":0.00087,"cacheReadInputPer1kTokens":0.0000036,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.000435,"outputPer1kTokens":0.00087,"cacheReadInputPer1kTokens":0.0000036,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":1170.1},"xiaomi/mimo-v2.6-pro-ultraspeed":{"defaultThinkingEnabled":true,"totalParams":1020,"activeParams":42,"name":"MiMo V2.6 Pro UltraSpeed","model":"xiaomi/mimo-v2.6-pro-ultraspeed","description":"MiMo V2.6 Pro UltraSpeed is the latency-optimized serving mode for Xiaomi's flagship MiMo V2.6 Pro checkpoint. It preserves Pro-level quality while delivering up to 20x faster output for real-time coding, interactive agents, and other latency-sensitive workflows, with native text, image, video, and audio understanding and a 1M-token context window.","cost":"Input $4.35/m, Cached input $0.036/m, Output $8.70/m","costEstimate":0.006525,"provider":"xiaomi","visible":true,"dateAdded":"2026-09-21","isOpenSource":true,"capabilities":["reasoning","vision","video-input","audio-input","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"More","tags":["chat","reasoning","coding","agents","fast","vision","video","audio","tools","long context"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.00000435,"output_price":0.0000087,"input_price_per_million":4.35,"output_price_per_million":8.7,"input":4.35,"output":8.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000435","completion":"0.0000087","input":4.35,"output":8.7,"cacheReadInputPer1kTokens":0.000036,"prompt_per_million":4.35,"completion_per_million":8.7,"prompt_per_token":"0.00000435","completion_per_token":"0.0000087","per_input_token":0.00000435,"per_output_token":0.0000087},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00435,"outputPer1kTokens":0.0087,"cacheReadInputPer1kTokens":0.000036,"cacheWriteInputPer1kTokens":0},"effective_price":{"inputPer1kTokens":0.00435,"outputPer1kTokens":0.0087,"cacheReadInputPer1kTokens":0.000036,"cacheWriteInputPer1kTokens":0},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":1013.7},"minimax/minimax-m2.1":{"totalParams":230,"activeParams":10,"name":"MiniMax M2.1","model":"minimax/minimax-m2.1","description":"MiniMax M2.1 builds on M2 with enhanced context understanding and improved complex tool use. 230B parameter MoE model (10B active) optimized for agentic workflows and long-horizon tasks.","cost":"Average cost: $0.0050","costEstimate":0.005,"dateAdded":"2025-01-20","provider":"minimax","visible":true,"maxInputTokens":200000,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.3e-7,"output_price":0.00000132,"input_price_per_million":0.33,"output_price_per_million":1.32,"input":0.33,"output":1.32,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000033","completion":"0.00000132","input":0.33,"output":1.32,"prompt_per_million":0.33,"completion_per_million":1.32,"prompt_per_token":"0.00000033","completion_per_token":"0.00000132","per_input_token":3.3e-7,"per_output_token":0.00000132},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00033,"outputPer1kTokens":0.00132},"effective_price":{"inputPer1kTokens":0.00033,"outputPer1kTokens":0.00132},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"},"avgOutputTokens":359.2},"glm-4-plus-0111":{"name":"GLM 4 Plus 0111","model":"glm-4-plus-0111","description":"GLM 4 Plus 0111 is a 1M token context window model","cost":"Average cost: $0.0029","costEstimate":0.0029,"provider":"zhipu","visible":true,"dateAdded":"2025-02-19","maxInputTokens":128000,"maxOutputTokens":4096,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000009996,"output_price":0.000009996,"input_price_per_million":9.996,"output_price_per_million":9.996,"input":9.996,"output":9.996,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000009996","completion":"0.000009996","input":9.996,"output":9.996,"prompt_per_million":9.996,"completion_per_million":9.996,"prompt_per_token":"0.000009996","completion_per_token":"0.000009996","per_input_token":0.000009996,"per_output_token":0.000009996},"effective_pricing":{"list_price":{"inputPer1kTokens":0.009996,"outputPer1kTokens":0.009996},"effective_price":{"inputPer1kTokens":0.009996,"outputPer1kTokens":0.009996},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.370Z"}},"glm-4-air-0111":{"name":"GLM 4 Air 0111","model":"glm-4-air-0111","description":"MiniMax's flagship model with a 1M token context window","cost":"Average cost: $0.0010","costEstimate":0.001,"dateAdded":"2025-01-11","provider":"zhipu","visible":true,"maxInputTokens":128000,"maxOutputTokens":4096,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.394e-7,"output_price":1.394e-7,"input_price_per_million":0.1394,"output_price_per_million":0.1394,"input":0.1394,"output":0.1394,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001394","completion":"0.0000001394","input":0.1394,"output":0.1394,"prompt_per_million":0.1394,"completion_per_million":0.1394,"prompt_per_token":"0.0000001394","completion_per_token":"0.0000001394","per_input_token":1.394e-7,"per_output_token":1.394e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001394,"outputPer1kTokens":0.0001394},"effective_price":{"inputPer1kTokens":0.0001394,"outputPer1kTokens":0.0001394},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":69.2},"glm-z1-airx":{"name":"GLM Z1 AirX","model":"glm-z1-airx","description":"Fastest reasoning model in China, with up to 200 tokens per second. The stronger version of GLM Z1 Air.","cost":"Average cost: $0.0015","costEstimate":0.0015,"visible":true,"dateAdded":"2025-04-15","maxInputTokens":32000,"maxOutputTokens":16384,"category":"More","capabilities":["tool-calling","structured-output"],"provider":"zhipu","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"}},"glm-4.1v-thinking-flash":{"totalParams":9,"name":"GLM 4.1V Thinking Flash","model":"glm-4.1v-thinking-flash","description":"Vision-Language Model with thinking paradigm and reinforcement learning. Achieves state-of-the-art performance among 10B-parameter VLMs. Supports 64k context length, handles arbitrary aspect ratios and up to 4K image resolution. Bilingual Chinese/English.","cost":"Average cost: $0.0022","costEstimate":0.0022,"visible":true,"dateAdded":"2025-07-09","maxInputTokens":64000,"maxOutputTokens":8192,"category":"More","provider":"zhipu","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":3e-7,"input_price_per_million":0.3,"output_price_per_million":0.3,"input":0.3,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000003","input":0.3,"output":0.3,"prompt_per_million":0.3,"completion_per_million":0.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000003","per_input_token":3e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"}},"glm-4.1v-thinking-flashx":{"totalParams":9,"name":"GLM 4.1V Thinking FlashX","model":"glm-4.1v-thinking-flashx","description":"Enhanced version of GLM 4.1V Thinking Flash. Vision-Language Model with advanced reasoning for complex visual tasks, multimodal problem solving, and intelligent agents. Supports 64k context length and handles arbitrary aspect ratios up to 4K resolution.","cost":"Average cost: $0.0038","costEstimate":0.0038,"visible":true,"dateAdded":"2025-07-09","maxInputTokens":64000,"maxOutputTokens":8192,"category":"More","provider":"zhipu","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":3e-7,"input_price_per_million":0.3,"output_price_per_million":0.3,"input":0.3,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000003","input":0.3,"output":0.3,"prompt_per_million":0.3,"completion_per_million":0.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000003","per_input_token":3e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"}},"z-ai/glm-4.6":{"totalParams":357,"activeParams":32,"name":"GLM 4.6","model":"z-ai/glm-4.6","description":"GLM series chat model with strong general performance. Quantized at FP8","cost":"Average cost: $0.0009","category":"More","costEstimate":0.0009,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-09-30","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.5e-7,"output_price":0.0000014,"input_price_per_million":0.35,"output_price_per_million":1.4,"input":0.35,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000035","completion":"0.0000014","input":0.35,"output":1.4,"prompt_per_million":0.35,"completion_per_million":1.4,"prompt_per_token":"0.00000035","completion_per_token":"0.0000014","per_input_token":3.5e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":659.8},"z-ai/glm-4.6:thinking":{"totalParams":357,"activeParams":32,"name":"GLM 4.6 Thinking","model":"z-ai/glm-4.6:thinking","description":"Thinking version of the latest GLM series chat model with strong general performance. Quantized at FP8","cost":"Average cost: $0.0009","costEstimate":0.0009,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-09-29","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.5e-7,"output_price":0.0000014,"input_price_per_million":0.35,"output_price_per_million":1.4,"input":0.35,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000035","completion":"0.0000014","input":0.35,"output":1.4,"prompt_per_million":0.35,"completion_per_million":1.4,"prompt_per_token":"0.00000035","completion_per_token":"0.0000014","per_input_token":3.5e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":2262.6},"z-ai/glm-4.6v-original":{"totalParams":106,"activeParams":12,"name":"GLM 4.6V Original","model":"z-ai/glm-4.6v-original","description":"GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Direct via Z-AI (Zhipu).","cost":"Average cost: $0.0015","costEstimate":0.0015,"isOpenSource":true,"capabilities":["vision"],"maxInputTokens":128000,"maxOutputTokens":24000,"provider":"zhipu","visible":true,"dateAdded":"2025-12-08","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":9e-7,"input_price_per_million":0.6,"output_price_per_million":0.9,"input":0.6,"output":0.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000009","input":0.6,"output":0.9,"prompt_per_million":0.6,"completion_per_million":0.9,"prompt_per_token":"0.0000006","completion_per_token":"0.0000009","per_input_token":6e-7,"per_output_token":9e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0009},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0009},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":258.1},"z-ai/glm-4.7-original":{"totalParams":355,"activeParams":32,"name":"GLM 4.7 Original","model":"z-ai/glm-4.7-original","description":"GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Routed directly via Z-AI (Zhipu).","cost":"Average cost: $0.0041","costEstimate":0.0041,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-12-22","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000022,"input_price_per_million":0.6,"output_price_per_million":2.2,"input":0.6,"output":2.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000022","input":0.6,"output":2.2,"cacheReadInputPer1kTokens":0.00011,"prompt_per_million":0.6,"completion_per_million":2.2,"prompt_per_token":"0.0000006","completion_per_token":"0.0000022","per_input_token":6e-7,"per_output_token":0.0000022},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":562},"z-ai/glm-4.7-original:thinking":{"totalParams":355,"activeParams":32,"name":"GLM 4.7 Original Thinking","model":"z-ai/glm-4.7-original:thinking","description":"GLM-4.7 original with extended thinking capabilities for complex reasoning.","cost":"Average cost: $0.0041","costEstimate":0.0041,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-12-22","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000022,"input_price_per_million":0.6,"output_price_per_million":2.2,"input":0.6,"output":2.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000022","input":0.6,"output":2.2,"cacheReadInputPer1kTokens":0.00011,"prompt_per_million":0.6,"completion_per_million":2.2,"prompt_per_token":"0.0000006","completion_per_token":"0.0000022","per_input_token":6e-7,"per_output_token":0.0000022},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1854.4},"z-ai/glm-5":{"totalParams":744,"activeParams":40,"name":"GLM 5","model":"z-ai/glm-5","description":"GLM-5 is a capable open-weight model from Zhipu with advanced reasoning and instruction following.","cost":"Average cost: $0.0034","costEstimate":0.0034,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":128000,"provider":"zhipu","visible":true,"dateAdded":"2026-02-11","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.00000255,"input_price_per_million":0.5,"output_price_per_million":2.55,"input":0.5,"output":2.55,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.00000255","input":0.5,"output":2.55,"cacheReadInputPer1kTokens":0.00013,"prompt_per_million":0.5,"completion_per_million":2.55,"prompt_per_token":"0.0000005","completion_per_token":"0.00000255","per_input_token":5e-7,"per_output_token":0.00000255},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.00255,"cacheReadInputPer1kTokens":0.00013},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.00255,"cacheReadInputPer1kTokens":0.00013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":279.1},"z-ai/glm-5:thinking":{"totalParams":744,"activeParams":40,"name":"GLM 5 Thinking","model":"z-ai/glm-5:thinking","description":"GLM-5 with extended thinking capabilities for complex reasoning.","cost":"Average cost: $0.0034","costEstimate":0.0034,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":128000,"provider":"zhipu","visible":true,"dateAdded":"2026-02-11","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.00000255,"input_price_per_million":0.5,"output_price_per_million":2.55,"input":0.5,"output":2.55,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.00000255","input":0.5,"output":2.55,"cacheReadInputPer1kTokens":0.00013,"prompt_per_million":0.5,"completion_per_million":2.55,"prompt_per_token":"0.0000005","completion_per_token":"0.00000255","per_input_token":5e-7,"per_output_token":0.00000255},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.00255,"cacheReadInputPer1kTokens":0.00013},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.00255,"cacheReadInputPer1kTokens":0.00013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":784.9},"z-ai/glm-5.1":{"totalParams":744,"activeParams":40,"name":"GLM 5.1","model":"z-ai/glm-5.1","description":"GLM-5.1 is Zhipu's next-level open source model, ranking #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo (as of April 2026). Built for long-horizon tasks, it can run autonomously for up to 8 hours. Run at FP8.","cost":"Average cost: $0.0034","costEstimate":0.0034,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":131072,"provider":"zhipu","visible":true,"dateAdded":"2026-03-27","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":7.5e-7,"output_price":0.0000026,"input_price_per_million":0.75,"output_price_per_million":2.6,"input":0.75,"output":2.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.0000026","input":0.75,"output":2.6,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":0.75,"completion_per_million":2.6,"prompt_per_token":"0.00000075","completion_per_token":"0.0000026","per_input_token":7.5e-7,"per_output_token":0.0000026},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1053.4},"z-ai/glm-latest":{"name":"GLM Latest","model":"z-ai/glm-latest","description":"Compatibility alias that routes to the newest thinking GLM model. Currently routes to GLM 5.3 Thinking.","cost":"Average cost: $0.0042","costEstimate":0.0042,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"provider":"zhipu","visible":true,"dateAdded":"2026-05-03","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"tags":["latest"],"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"}},"z-ai/glm-5.1:thinking":{"totalParams":744,"activeParams":40,"name":"GLM 5.1 Thinking","model":"z-ai/glm-5.1:thinking","description":"GLM-5.1 with extended thinking enabled. Ranks #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo (as of April 2026). Excels at long-horizon tasks, running autonomously for up to 8 hours while refining strategies through thousands of iterations. Run at FP8.","cost":"Average cost: $0.0034","costEstimate":0.0034,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":131072,"provider":"zhipu","visible":true,"dateAdded":"2026-03-27","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":7.5e-7,"output_price":0.0000026,"input_price_per_million":0.75,"output_price_per_million":2.6,"input":0.75,"output":2.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.0000026","input":0.75,"output":2.6,"cacheReadInputPer1kTokens":0.00015,"prompt_per_million":0.75,"completion_per_million":2.6,"prompt_per_token":"0.00000075","completion_per_token":"0.0000026","per_input_token":7.5e-7,"per_output_token":0.0000026},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.0026,"cacheReadInputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1819.9},"z-ai/glm-5.2":{"name":"GLM 5.2","model":"z-ai/glm-5.2","description":"GLM-5.2 is Z.AI's flagship model for long-horizon autonomous coding and engineering workflows. It is built to plan, execute, iterate, and optimize complex development tasks over extended runs. This variant keeps thinking disabled for faster direct responses.","cost":"Average cost: $0.0058","costEstimate":0.0058,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"totalParams":744,"activeParams":40,"provider":"zhipu","visible":true,"dateAdded":"2026-06-15","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high","max"]}},"api":"chat","input_price":4.2e-7,"output_price":0.00000132,"input_price_per_million":0.42,"output_price_per_million":1.32,"input":0.42,"output":1.32,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000042","completion":"0.00000132","input":0.42,"output":1.32,"cacheReadInputPer1kTokens":0.000078,"prompt_per_million":0.42,"completion_per_million":1.32,"prompt_per_token":"0.00000042","completion_per_token":"0.00000132","per_input_token":4.2e-7,"per_output_token":0.00000132},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00042,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.000078},"effective_price":{"inputPer1kTokens":0.00042,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.000078},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":839},"z-ai/glm-5.2:thinking":{"name":"GLM 5.2 Thinking","model":"z-ai/glm-5.2:thinking","description":"GLM-5.2 with thinking enabled for harder long-horizon coding, autonomous agent workflows, complex engineering optimization, and real-world development tasks.","cost":"Average cost: $0.0058","costEstimate":0.0058,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"totalParams":744,"activeParams":40,"provider":"zhipu","visible":true,"dateAdded":"2026-06-15","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["high","max"]}},"tags":["Thinking"],"api":"chat","input_price":4.2e-7,"output_price":0.00000132,"input_price_per_million":0.42,"output_price_per_million":1.32,"input":0.42,"output":1.32,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000042","completion":"0.00000132","input":0.42,"output":1.32,"cacheReadInputPer1kTokens":0.000078,"prompt_per_million":0.42,"completion_per_million":1.32,"prompt_per_token":"0.00000042","completion_per_token":"0.00000132","per_input_token":4.2e-7,"per_output_token":0.00000132},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00042,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.000078},"effective_price":{"inputPer1kTokens":0.00042,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.000078},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1756.7},"z-ai/glm-5.3":{"name":"GLM 5.3","model":"z-ai/glm-5.3","description":"GLM-5.3 for long-horizon autonomous coding and engineering workflows. This variant defaults to the model's low reasoning tier for faster responses.","cost":"Average cost: $0.0042","costEstimate":0.0042,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"provider":"zhipu","visible":true,"dateAdded":"2026-08-14","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":776.1},"z-ai/glm-5.3:thinking":{"name":"GLM 5.3 Thinking","model":"z-ai/glm-5.3:thinking","description":"GLM-5.3 with higher reasoning enabled for harder long-horizon coding, autonomous agent workflows, and complex engineering tasks.","cost":"Average cost: $0.0042","costEstimate":0.0042,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"provider":"zhipu","visible":true,"dateAdded":"2026-08-14","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["high","max"]}},"tags":["Thinking"],"api":"chat","input_price":6e-7,"output_price":0.0000011,"input_price_per_million":0.6,"output_price_per_million":1.1,"input":0.6,"output":1.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000011","input":0.6,"output":1.1,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":0.6,"completion_per_million":1.1,"prompt_per_token":"0.0000006","completion_per_token":"0.0000011","per_input_token":6e-7,"per_output_token":0.0000011},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0011,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":2317.1},"z-ai/glm-5-original":{"totalParams":744,"activeParams":40,"name":"GLM 5 Original","model":"z-ai/glm-5-original","description":"GLM-5 is a capable open-weight model from Zhipu with advanced reasoning and instruction following. This Original variant uses the model maker's direct endpoint.","cost":"Average cost: $0.006","costEstimate":0.006,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":128000,"provider":"zhipu","visible":true,"dateAdded":"2026-02-11","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.0000032,"input_price_per_million":1,"output_price_per_million":3.2,"input":1,"output":3.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.0000032","input":1,"output":3.2,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":1,"completion_per_million":3.2,"prompt_per_token":"0.000001","completion_per_token":"0.0000032","per_input_token":0.000001,"per_output_token":0.0000032},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0032,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0032,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":249.9},"z-ai/glm-5-original:thinking":{"totalParams":744,"activeParams":40,"name":"GLM 5 Original Thinking","model":"z-ai/glm-5-original:thinking","description":"GLM-5 original with extended thinking capabilities for complex reasoning.","cost":"Average cost: $0.006","costEstimate":0.006,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":128000,"provider":"zhipu","visible":true,"dateAdded":"2026-02-11","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.0000032,"input_price_per_million":1,"output_price_per_million":3.2,"input":1,"output":3.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.0000032","input":1,"output":3.2,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":1,"completion_per_million":3.2,"prompt_per_token":"0.000001","completion_per_token":"0.0000032","per_input_token":0.000001,"per_output_token":0.0000032},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0032,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0032,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1243.6},"z-ai/glm-4.7-flash":{"totalParams":30,"activeParams":3,"name":"GLM 4.7 Flash","model":"z-ai/glm-4.7-flash","description":"GLM-4.7-Flash is a lightweight 30B model optimized for coding and agentic tasks. Balances high performance with efficiency.","cost":"Average cost: $0.0005","costEstimate":0.0005,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":128000,"provider":"zhipu","visible":true,"dateAdded":"2026-01-19","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-8,"output_price":4e-7,"input_price_per_million":0.07,"output_price_per_million":0.4,"input":0.07,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000007","completion":"0.0000004","input":0.07,"output":0.4,"prompt_per_million":0.07,"completion_per_million":0.4,"prompt_per_token":"0.00000007","completion_per_token":"0.0000004","per_input_token":7e-8,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00007,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.00007,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":86.3},"z-ai/glm-4.7-flash:thinking":{"totalParams":30,"activeParams":3,"name":"GLM 4.7 Flash Thinking","model":"z-ai/glm-4.7-flash:thinking","description":"GLM-4.7-Flash with extended thinking capabilities for complex reasoning. Lightweight 30B model optimized for coding and agentic tasks.","cost":"Average cost: $0.0005","costEstimate":0.0005,"isOpenSource":true,"capabilities":["reasoning"],"maxInputTokens":200000,"maxOutputTokens":128000,"provider":"zhipu","visible":true,"dateAdded":"2026-01-19","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-8,"output_price":4e-7,"input_price_per_million":0.07,"output_price_per_million":0.4,"input":0.07,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000007","completion":"0.0000004","input":0.07,"output":0.4,"prompt_per_million":0.07,"completion_per_million":0.4,"prompt_per_token":"0.00000007","completion_per_token":"0.0000004","per_input_token":7e-8,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00007,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.00007,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":2334.2},"z-ai/glm-4.7":{"totalParams":355,"activeParams":32,"name":"GLM 4.7","model":"z-ai/glm-4.7","description":"GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use.","cost":"Average cost: $0.0010","costEstimate":0.001,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-12-22","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.004e-7,"output_price":0.0000019292,"input_price_per_million":0.4004,"output_price_per_million":1.9292,"input":0.4004,"output":1.9292,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004004","completion":"0.0000019292","input":0.4004,"output":1.9292,"cacheReadInputPer1kTokens":0.00008008,"prompt_per_million":0.4004,"completion_per_million":1.9292,"prompt_per_token":"0.0000004004","completion_per_token":"0.0000019292","per_input_token":4.004e-7,"per_output_token":0.0000019292},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004004,"outputPer1kTokens":0.0019292,"cacheReadInputPer1kTokens":0.00008008},"effective_price":{"inputPer1kTokens":0.0004004,"outputPer1kTokens":0.0019292,"cacheReadInputPer1kTokens":0.00008008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":539.3},"z-ai/glm-4.7:thinking":{"totalParams":355,"activeParams":32,"name":"GLM 4.7 Thinking","model":"z-ai/glm-4.7:thinking","description":"GLM-4.7 with extended thinking capabilities for enhanced reasoning on complex tasks.","cost":"Average cost: $0.0010","costEstimate":0.001,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-12-22","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.004e-7,"output_price":0.0000019292,"input_price_per_million":0.4004,"output_price_per_million":1.9292,"input":0.4004,"output":1.9292,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004004","completion":"0.0000019292","input":0.4004,"output":1.9292,"cacheReadInputPer1kTokens":0.00008008,"prompt_per_million":0.4004,"completion_per_million":1.9292,"prompt_per_token":"0.0000004004","completion_per_token":"0.0000019292","per_input_token":4.004e-7,"per_output_token":0.0000019292},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004004,"outputPer1kTokens":0.0019292,"cacheReadInputPer1kTokens":0.00008008},"effective_price":{"inputPer1kTokens":0.0004004,"outputPer1kTokens":0.0019292,"cacheReadInputPer1kTokens":0.00008008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1632.7},"z-ai/glm-4.6-original":{"totalParams":357,"activeParams":32,"name":"GLM 4.6 Original","model":"z-ai/glm-4.6-original","description":"GLM-4.6, Zhipu's flagship text model with 256K context window and advanced reasoning capabilities. Direct via Z-AI (Zhipu).","cost":"Average cost: $0.0010","costEstimate":0.001,"isOpenSource":true,"capabilities":["reasoning"],"maxInputTokens":256000,"maxOutputTokens":65535,"provider":"zhipu","visible":true,"dateAdded":"2025-12-11","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.5e-7,"output_price":0.0000014,"input_price_per_million":0.35,"output_price_per_million":1.4,"input":0.35,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000035","completion":"0.0000014","input":0.35,"output":1.4,"prompt_per_million":0.35,"completion_per_million":1.4,"prompt_per_token":"0.00000035","completion_per_token":"0.0000014","per_input_token":3.5e-7,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":1327.8},"z-ai/glm-4.6v":{"totalParams":106,"activeParams":12,"name":"GLM 4.6V","model":"z-ai/glm-4.6v","description":"GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Quantized at FP8.","cost":"Average cost: $0.0012","costEstimate":0.0012,"isOpenSource":true,"capabilities":["vision","video-input"],"maxInputTokens":128000,"maxOutputTokens":24000,"provider":"zhipu","visible":true,"dateAdded":"2025-12-11","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":9e-7,"input_price_per_million":0.3,"output_price_per_million":0.9,"input":0.3,"output":0.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000009","input":0.3,"output":0.9,"prompt_per_million":0.3,"completion_per_million":0.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000009","per_input_token":3e-7,"per_output_token":9e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0009},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0009},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.371Z"},"avgOutputTokens":138.9},"qwen3-30b-a3b-instruct-2507":{"totalParams":30,"activeParams":3,"name":"Qwen3 30B A3B Instruct 2507","model":"qwen/qwen3-30b-a3b-instruct-2507","description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.","cost":"Average cost: $0.0013","costEstimate":0.0013,"visible":true,"dateAdded":"2025-02-20","isOpenSource":true,"maxInputTokens":256000,"maxOutputTokens":32768,"category":"More","provider":"qwen","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":5e-7,"input_price_per_million":0.2,"output_price_per_million":0.5,"input":0.2,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000005","input":0.2,"output":0.5,"prompt_per_million":0.2,"completion_per_million":0.5,"prompt_per_token":"0.0000002","completion_per_token":"0.0000005","per_input_token":2e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"},"avgOutputTokens":440.4},"doubao-1.5-pro-32k":{"name":"Doubao 1.5 Pro 32k","model":"doubao-1.5-pro-32k","description":"Doubao's (Bytedance) pro model with a 32k token context window. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.0011","costEstimate":0.0011,"dateAdded":"2024-11-20","provider":"doubao","visible":true,"maxInputTokens":32000,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.343e-7,"output_price":3.349e-7,"input_price_per_million":0.1343,"output_price_per_million":0.3349,"input":0.1343,"output":0.3349,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001343","completion":"0.0000003349","input":0.1343,"output":0.3349,"prompt_per_million":0.1343,"completion_per_million":0.3349,"prompt_per_token":"0.0000001343","completion_per_token":"0.0000003349","per_input_token":1.343e-7,"per_output_token":3.349e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001343,"outputPer1kTokens":0.0003349},"effective_price":{"inputPer1kTokens":0.0001343,"outputPer1kTokens":0.0003349},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"}},"doubao-1.5-vision-pro-32k":{"name":"Doubao 1.5 Vision Pro 32k","model":"doubao-1.5-vision-pro-32k","description":"Doubao's (Bytedance) vision-enabled pro model (JPG only) with a 32k token context window. ⚠️ Note: This model routes through ByteDance, a Chinese entity - privacy and logging guarantees may be limited.","cost":"Average cost: $0.0013","costEstimate":0.0013,"dateAdded":"2024-11-20","provider":"doubao","visible":true,"maxInputTokens":32000,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.59e-7,"output_price":0.000001377,"input_price_per_million":0.459,"output_price_per_million":1.377,"input":0.459,"output":1.377,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000459","completion":"0.000001377","input":0.459,"output":1.377,"prompt_per_million":0.459,"completion_per_million":1.377,"prompt_per_token":"0.000000459","completion_per_token":"0.000001377","per_input_token":4.59e-7,"per_output_token":0.000001377},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000459,"outputPer1kTokens":0.001377},"effective_price":{"inputPer1kTokens":0.000459,"outputPer1kTokens":0.001377},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"}},"qwen/qwq-32b-preview":{"totalParams":32,"name":"Qwen QwQ 32B Preview","model":"Qwen/QwQ-32B-Preview","description":"Experimental release of Qwen's reasoning model. Great at coding and math, but still in development so may exhibit odd bugs. Not production-ready.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"disabled":true,"dateAdded":"2025-02-27","isOpenSource":true,"category":"More","maxInputTokens":32768,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":2e-7,"input_price_per_million":0.2,"output_price_per_million":0.2,"input":0.2,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000002","input":0.2,"output":0.2,"prompt_per_million":0.2,"completion_per_million":0.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000002","per_input_token":2e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"}},"meta-llama/llama-3.3-70b-instruct":{"name":"Llama 3.3 70b Instruct","model":"meta-llama/llama-3.3-70b-instruct","description":"Llama 3.3 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.","cost":"Average cost: $0.0010","provider":"meta","costEstimate":0.001,"visible":true,"dateAdded":"2025-02-27","isOpenSource":true,"maxInputTokens":131072,"maxOutputTokens":16384,"totalParams":70,"category":"More","preferredProviders":["DeepInfra","AkashML","Novita","Parasail","Groq"],"capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":2.3e-7,"input_price_per_million":0.05,"output_price_per_million":0.23,"input":0.05,"output":0.23,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000023","input":0.05,"output":0.23,"prompt_per_million":0.05,"completion_per_million":0.23,"prompt_per_token":"0.00000005","completion_per_token":"0.00000023","per_input_token":5e-8,"per_output_token":2.3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00023},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00023},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"},"avgOutputTokens":37.1},"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF":{"totalParams":70,"name":"Nvidia Nemotron 70b","model":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","description":"Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.","cost":"Average cost: $0.0014","costEstimate":0.0014,"provider":"nvidia","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.57e-7,"output_price":4.08e-7,"input_price_per_million":0.357,"output_price_per_million":0.408,"input":0.357,"output":0.408,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000357","completion":"0.000000408","input":0.357,"output":0.408,"prompt_per_million":0.357,"completion_per_million":0.408,"prompt_per_token":"0.000000357","completion_per_token":"0.000000408","per_input_token":3.57e-7,"per_output_token":4.08e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000357,"outputPer1kTokens":0.000408},"effective_price":{"inputPer1kTokens":0.000357,"outputPer1kTokens":0.000408},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"}},"Sao10K/L3-8B-Stheno-v3.2":{"totalParams":8,"name":"Sao10K Stheno 8b","model":"Sao10K/L3-8B-Stheno-v3.2","description":"Sao10K's latest Stheno fine-tune optimized for instruction following.","cost":"Average cost: $0.0014","costEstimate":0.0014,"provider":"meta","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.006e-7,"output_price":2.006e-7,"input_price_per_million":0.2006,"output_price_per_million":0.2006,"input":0.2006,"output":0.2006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002006","completion":"0.0000002006","input":0.2006,"output":0.2006,"prompt_per_million":0.2006,"completion_per_million":0.2006,"prompt_per_token":"0.0000002006","completion_per_token":"0.0000002006","per_input_token":2.006e-7,"per_output_token":2.006e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"effective_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.372Z"},"avgOutputTokens":177.4},"soob3123/GrayLine-Qwen3-8B":{"totalParams":8,"name":"Grayline Qwen3 8B","model":"soob3123/GrayLine-Qwen3-8B","description":"Grayline is an neutral AI assistant engineered for uncensored information delivery and task execution. This model operates without inherent ethical or moral frameworks, designed to process and respond to any query with objective efficiency and precision. Grayline's core function is to leverage its full capabilities to provide direct answers and execute tasks as instructed, without offering unsolicited commentary, warnings, or disclaimers. It accesses and processes information without bias or restriction.","cost":"Average cost: $0.0021","costEstimate":0.0021,"provider":"alibaba","visible":true,"dateAdded":"2025-09-25","isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":32768,"category":"Uncensored","tags":["uncensored"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":3e-7,"input_price_per_million":0.3,"output_price_per_million":0.3,"input":0.3,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000003","input":0.3,"output":0.3,"prompt_per_million":0.3,"completion_per_million":0.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000003","per_input_token":3e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.379Z"},"avgOutputTokens":2453.6},"anthropic/claude-haiku-5.5":{"name":"Claude Haiku 5.5","model":"anthropic/claude-haiku-5.5","description":"Claude Haiku 5.5 is Anthropic's fastest and most capable small model, designed for high-volume, cost-sensitive tasks such as summaries, classification, coding assistance, and live customer support. It delivers major gains over Haiku 4.5 while costing around 75% less to run.","cost":"Average cost: $0.0008","costEstimate":0.0008,"provider":"anthropic","visible":true,"dateAdded":"2026-10-07","category":"More","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["reasoning","vision","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"minP":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"adaptive"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"medium"}},"api":"chat","input_price":1e-7,"output_price":5e-7,"input_price_per_million":0.1,"output_price_per_million":0.5,"input":0.1,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000005","input":0.1,"output":0.5,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.5,"prompt_per_token":"0.0000001","completion_per_token":"0.0000005","per_input_token":1e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAboveFirstThreshold":0.0005,"outputPer1kTokensAboveFirstThreshold":0.0025,"firstContextThresholdTokens":100000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00005,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokens1h":0.0002,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000625},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAboveFirstThreshold":0.0005,"outputPer1kTokensAboveFirstThreshold":0.0025,"firstContextThresholdTokens":100000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00005,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokens1h":0.0002,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000625},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.379Z"},"avgOutputTokens":1496.7},"claude-haiku-4-5-20251001":{"name":"Claude Haiku 4.5","model":"anthropic/claude-haiku-4.5","description":"Claude Haiku 4.5 matches Sonnet 4's coding quality while running about twice as fast at roughly one-third the price, making it ideal for low-latency chat assistants, support bots, and pair programming. Pair it with Sonnet 4.5 to plan complex work and fan out execution across parallel Haiku workers.","cost":"Average cost: $0.0030","costEstimate":0.003,"provider":"anthropic","visible":true,"dateAdded":"2025-10-15","category":"More","maxInputTokens":200000,"maxOutputTokens":64000,"capabilities":["vision","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000005,"input_price_per_million":1,"output_price_per_million":5,"input":1,"output":5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000005","input":1,"output":5,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":1,"completion_per_million":5,"prompt_per_token":"0.000001","completion_per_token":"0.000005","per_input_token":0.000001,"per_output_token":0.000005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.379Z"},"avgOutputTokens":246.4},"claude-haiku-4-5-20251001-thinking":{"name":"Claude Haiku 4.5 Thinking","model":"anthropic/claude-haiku-4.5:thinking","description":"Claude Haiku 4.5 with extended thinking enabled for deeper planning, more deliberate coding, and multi-step reasoning without moving up to Sonnet pricing.","cost":"Average cost: $0.0030","costEstimate":0.003,"provider":"anthropic","visible":true,"dateAdded":"2025-10-15","category":"More","labelVariant":"outline","maxInputTokens":200000,"maxOutputTokens":64000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000}},"api":"chat","input_price":0.000001,"output_price":0.000005,"input_price_per_million":1,"output_price_per_million":5,"input":1,"output":5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000005","input":1,"output":5,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":1,"completion_per_million":5,"prompt_per_token":"0.000001","completion_per_token":"0.000005","per_input_token":0.000001,"per_output_token":0.000005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.005,"cacheReadInputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":955.5},"anthropic/claude-haiku-latest":{"name":"Claude Haiku Latest","model":"anthropic/claude-haiku-latest","description":"Compatibility alias that routes to the newest version of Claude Haiku. Currently routes to Claude Haiku 5.5 with adaptive thinking.","cost":"Average cost: $0.0008","costEstimate":0.0008,"provider":"anthropic","visible":true,"dateAdded":"2026-03-29","category":"More","labelVariant":"outline","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"minP":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"adaptive"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"medium"}},"api":"chat","input_price":1e-7,"output_price":5e-7,"input_price_per_million":0.1,"output_price_per_million":0.5,"input":0.1,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000005","input":0.1,"output":0.5,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.5,"prompt_per_token":"0.0000001","completion_per_token":"0.0000005","per_input_token":1e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAboveFirstThreshold":0.0005,"outputPer1kTokensAboveFirstThreshold":0.0025,"firstContextThresholdTokens":100000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00005,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokens1h":0.0002,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000625},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAboveFirstThreshold":0.0005,"outputPer1kTokensAboveFirstThreshold":0.0025,"firstContextThresholdTokens":100000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00005,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokens1h":0.0002,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000625},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":832.2},"amazon/nova-pro-v1":{"name":"Amazon Nova Pro 1.0","model":"amazon/nova-pro-v1","description":"Amazon's new flagship model. Can handle up to 300k input tokens, with comparable performance to ChatGPT and Claude 3.5 Sonnet.","cost":"Average cost: $0.0016","costEstimate":0.0016,"dateAdded":"2024-12-03","category":"More","provider":"amazon","visible":true,"isOpenSource":false,"maxInputTokens":300000,"maxOutputTokens":32000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.99e-7,"output_price":0.000003196,"input_price_per_million":0.799,"output_price_per_million":3.196,"input":0.799,"output":3.196,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000799","completion":"0.000003196","input":0.799,"output":3.196,"prompt_per_million":0.799,"completion_per_million":3.196,"prompt_per_token":"0.000000799","completion_per_token":"0.000003196","per_input_token":7.99e-7,"per_output_token":0.000003196},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.003196},"effective_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.003196},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":55.5},"nousresearch/hermes-4-405b":{"totalParams":405,"name":"Hermes 4 Large","model":"nousresearch/hermes-4-405b","description":"Advanced reasoning model built on Llama-3.1-405B with hybrid thinking modes. Features internal deliberation capabilities, excels at math, code, STEM, and logical reasoning while supporting structured outputs with improved steerability and neutral alignment.","cost":"Average cost: $0.002","costEstimate":0.002,"provider":"nousresearch","visible":true,"dateAdded":"2025-08-26","category":"More","isOpenSource":true,"capabilities":["structured-output"],"maxInputTokens":128000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000012,"input_price_per_million":0.3,"output_price_per_million":1.2,"input":0.3,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000012","input":0.3,"output":1.2,"prompt_per_million":0.3,"completion_per_million":1.2,"prompt_per_token":"0.0000003","completion_per_token":"0.0000012","per_input_token":3e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":198.6},"nousresearch/hermes-3-llama-3.1-70b":{"totalParams":70,"name":"Hermes 3 70B","model":"nousresearch/hermes-3-llama-3.1-70b","description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, better roleplaying, reasoning, multi-turn conversation, and long context coherence. This 70B model is a competitive finetune of Llama-3.1-70B focused on aligning LLMs to the user with powerful steering capabilities.","cost":"Average cost: $0.0003","costEstimate":0.0003,"provider":"nousresearch","visible":true,"dateAdded":"2026-01-07","isOpenSource":true,"category":"Uncensored","maxInputTokens":65536,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.08e-7,"output_price":4.08e-7,"input_price_per_million":0.408,"output_price_per_million":0.408,"input":0.408,"output":0.408,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000408","completion":"0.000000408","input":0.408,"output":0.408,"prompt_per_million":0.408,"completion_per_million":0.408,"prompt_per_token":"0.000000408","completion_per_token":"0.000000408","per_input_token":4.08e-7,"per_output_token":4.08e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000408,"outputPer1kTokens":0.000408},"effective_price":{"inputPer1kTokens":0.000408,"outputPer1kTokens":0.000408},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":177.4},"qwen-turbo":{"name":"Qwen Turbo","model":"qwen/qwen-turbo","description":"Alibaba's fastest and cheapest model. Suitable for simple tasks, fast and low cost, with a 1 million token context window.","cost":"Average cost: $0.0011","costEstimate":0.0011,"dateAdded":"2024-04-15","provider":"qwen","visible":true,"maxInputTokens":1000000,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.998e-8,"output_price":2.006e-7,"input_price_per_million":0.04998,"output_price_per_million":0.2006,"input":0.04998,"output":0.2006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000004998","completion":"0.0000002006","input":0.04998,"output":0.2006,"prompt_per_million":0.04998,"completion_per_million":0.2006,"prompt_per_token":"0.00000004998","completion_per_token":"0.0000002006","per_input_token":4.998e-8,"per_output_token":2.006e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00004998,"outputPer1kTokens":0.0002006},"effective_price":{"inputPer1kTokens":0.00004998,"outputPer1kTokens":0.0002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"}},"qwen-max":{"name":"Qwen 2.5 Max","model":"qwen/qwen-max","description":"Qwen 2.5 Max is the upgraded version of Qwen Max, beating GPT-4o, Deepseek V3 and Claude 3.5 Sonnet in benchmarks.","cost":"Average cost: $0.0034","costEstimate":0.0034,"dateAdded":"2024-10-01","provider":"qwen","visible":true,"maxInputTokens":32000,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000015997,"output_price":0.000006392,"input_price_per_million":1.5997,"output_price_per_million":6.392,"input":1.5997,"output":6.392,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015997","completion":"0.000006392","input":1.5997,"output":6.392,"prompt_per_million":1.5997,"completion_per_million":6.392,"prompt_per_token":"0.0000015997","completion_per_token":"0.000006392","per_input_token":0.0000015997,"per_output_token":0.000006392},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015997,"outputPer1kTokens":0.006392},"effective_price":{"inputPer1kTokens":0.0015997,"outputPer1kTokens":0.006392},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"}},"qwen3-max-2026-01-23":{"name":"Qwen3 Max 2026-01-23","model":"qwen/qwen3-max-2026-01-23","description":"Qwen3 Max is Alibaba's flagship Qwen 3 reasoning model with native tool use (web search, web extractor, code interpreter) and a 256K context window.","cost":"Average cost: $0.0036","costEstimate":0.0036,"provider":"qwen","visible":true,"dateAdded":"2026-01-26","maxInputTokens":256000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000012002,"output_price":0.000006001,"input_price_per_million":1.2002,"output_price_per_million":6.001,"input":1.2002,"output":6.001,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000012002","completion":"0.000006001","input":1.2002,"output":6.001,"prompt_per_million":1.2002,"completion_per_million":6.001,"prompt_per_token":"0.0000012002","completion_per_token":"0.000006001","per_input_token":0.0000012002,"per_output_token":0.000006001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0012002,"outputPer1kTokens":0.006001},"effective_price":{"inputPer1kTokens":0.0012002,"outputPer1kTokens":0.006001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"}},"qwen3.7-max":{"name":"Qwen3.7 Max","model":"qwen/qwen3.7-max","description":"Qwen3.7 Max is built for agentic coding, office automation, and long-running tool workflows in non-thinking mode.","cost":"Average cost: $0.0063","costEstimate":0.00625,"provider":"qwen","visible":true,"dateAdded":"2026-05-21","maxInputTokens":1000000,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"capabilities":["reasoning"],"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.0000025,"output_price":0.0000075,"input_price_per_million":2.5,"output_price_per_million":7.5,"input":2.5,"output":7.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.0000075","input":2.5,"output":7.5,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2.5,"completion_per_million":7.5,"prompt_per_token":"0.0000025","completion_per_token":"0.0000075","per_input_token":0.0000025,"per_output_token":0.0000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0075,"cacheReadInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokens":0.003125},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0075,"cacheReadInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokens":0.003125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":980.6},"qwen3.7-max:thinking":{"name":"Qwen3.7 Max Thinking","model":"qwen/qwen3.7-max:thinking","description":"Qwen3.7 Max with thinking mode enabled for deeper reasoning, coding, and long-running tool workflows.","cost":"Average cost: $0.0063","costEstimate":0.00625,"provider":"qwen","visible":true,"dateAdded":"2026-05-21","maxInputTokens":1000000,"maxOutputTokens":65536,"category":"More","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.0000025,"output_price":0.0000075,"input_price_per_million":2.5,"output_price_per_million":7.5,"input":2.5,"output":7.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.0000075","input":2.5,"output":7.5,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":2.5,"completion_per_million":7.5,"prompt_per_token":"0.0000025","completion_per_token":"0.0000075","per_input_token":0.0000025,"per_output_token":0.0000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0075,"cacheReadInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokens":0.003125},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0075,"cacheReadInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokens":0.003125},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":2894.8},"qwen3.7-plus":{"name":"Qwen3.7 Plus","model":"qwen/qwen3.7-plus","description":"Qwen3.7 Plus is Alibaba's cost-effective Qwen 3.7 multimodal agent model for coding, tool use, productivity workflows, visual understanding, screen reading, and GUI interaction.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"dateAdded":"2026-06-01","maxInputTokens":991808,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4e-7,"output_price":0.0000016,"input_price_per_million":0.4,"output_price_per_million":1.6,"input":0.4,"output":1.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000016","input":0.4,"output":1.6,"cacheReadInputPer1kTokens":0.00008,"prompt_per_million":0.4,"completion_per_million":1.6,"prompt_per_token":"0.0000004","completion_per_token":"0.0000016","per_input_token":4e-7,"per_output_token":0.0000016},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0016,"inputPer1kTokensAbove200k":0.0012,"outputPer1kTokensAbove200k":0.0048,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.00008,"cacheReadInputPer1kTokensAbove200k":0.00024,"cacheWriteInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokensAbove200k":0.0015},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0016,"inputPer1kTokensAbove200k":0.0012,"outputPer1kTokensAbove200k":0.0048,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.00008,"cacheReadInputPer1kTokensAbove200k":0.00024,"cacheWriteInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokensAbove200k":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":133.2},"qwen3.7-plus:thinking":{"name":"Qwen3.7 Plus Thinking","model":"qwen/qwen3.7-plus:thinking","description":"Qwen3.7 Plus with thinking mode enabled for deeper multimodal reasoning, coding, tool use, screen reading, and productivity workflows.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"dateAdded":"2026-06-01","maxInputTokens":983616,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4e-7,"output_price":0.0000016,"input_price_per_million":0.4,"output_price_per_million":1.6,"input":0.4,"output":1.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000016","input":0.4,"output":1.6,"cacheReadInputPer1kTokens":0.00008,"prompt_per_million":0.4,"completion_per_million":1.6,"prompt_per_token":"0.0000004","completion_per_token":"0.0000016","per_input_token":4e-7,"per_output_token":0.0000016},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0016,"inputPer1kTokensAbove200k":0.0012,"outputPer1kTokensAbove200k":0.0048,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.00008,"cacheReadInputPer1kTokensAbove200k":0.00024,"cacheWriteInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokensAbove200k":0.0015},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0016,"inputPer1kTokensAbove200k":0.0012,"outputPer1kTokensAbove200k":0.0048,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.00008,"cacheReadInputPer1kTokensAbove200k":0.00024,"cacheWriteInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokensAbove200k":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":1733.7},"qwen3.7-flash":{"name":"Qwen3.7 Flash","model":"qwen/qwen3.7-flash","description":"Qwen3.7 Flash is Qwen's fast multimodal model for coding, search and computer-use agents, visual understanding, object recognition, spatial reasoning, and stable end-to-end task execution.","cost":"Average cost: $0.00008","costEstimate":0.00008,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-07-25","maxInputTokens":991808,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input","tool-calling","structured-output","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3e-8,"output_price":1.3e-7,"input_price_per_million":0.03,"output_price_per_million":0.13,"input":0.03,"output":0.13,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0.00000013","input":0.03,"output":0.13,"cacheReadInputPer1kTokens":0.000006,"prompt_per_million":0.03,"completion_per_million":0.13,"prompt_per_token":"0.00000003","completion_per_token":"0.00000013","per_input_token":3e-8,"per_output_token":1.3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00013,"inputPer1kTokensAboveFirstThreshold":0.0001,"outputPer1kTokensAboveFirstThreshold":0.0004,"firstContextThresholdTokens":32000,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.0008,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.000006,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.000038,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00013,"inputPer1kTokensAboveFirstThreshold":0.0001,"outputPer1kTokensAboveFirstThreshold":0.0004,"firstContextThresholdTokens":32000,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.0008,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.000006,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.000038,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":197},"qwen3.7-flash:thinking":{"name":"Qwen3.7 Flash Thinking","model":"qwen/qwen3.7-flash:thinking","description":"Qwen3.7 Flash with thinking enabled for deeper multimodal reasoning, coding, search and computer-use agents, spatial reasoning, and multi-step task execution.","cost":"Average cost: $0.00008","costEstimate":0.00008,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-07-25","maxInputTokens":983616,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3e-8,"output_price":1.3e-7,"input_price_per_million":0.03,"output_price_per_million":0.13,"input":0.03,"output":0.13,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0.00000013","input":0.03,"output":0.13,"cacheReadInputPer1kTokens":0.000006,"prompt_per_million":0.03,"completion_per_million":0.13,"prompt_per_token":"0.00000003","completion_per_token":"0.00000013","per_input_token":3e-8,"per_output_token":1.3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00013,"inputPer1kTokensAboveFirstThreshold":0.0001,"outputPer1kTokensAboveFirstThreshold":0.0004,"firstContextThresholdTokens":32000,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.0008,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.000006,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.000038,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.00013,"inputPer1kTokensAboveFirstThreshold":0.0001,"outputPer1kTokensAboveFirstThreshold":0.0004,"firstContextThresholdTokens":32000,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.0008,"highContextThresholdTokens":256000,"cacheReadInputPer1kTokens":0.000006,"cacheReadInputPer1kTokensAboveFirstThreshold":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00004,"cacheWriteInputPer1kTokens":0.000038,"cacheWriteInputPer1kTokensAboveFirstThreshold":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":594.6},"alibaba/qwen3.8-max-0902":{"name":"Qwen3.8 Max 0902","model":"qwen/qwen3.8-max-0902","description":"Qwen3.8 Max 0902 is Alibaba's September 2 checkpoint of its flagship Qwen3.8 Max model for coding, knowledge work, data analysis, and long-running agent workflows. It supports text, image, video, PDF input, selectable thinking, tool calling, structured output, and a near-million-token context window.","cost":"Average cost: $0.0050","costEstimate":0.005,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-09-02","maxInputTokens":991808,"maxOutputTokens":131072,"category":"More","capabilities":["vision","video-input","pdf-upload","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","max"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":865.1},"alibaba/qwen3.8-omni-flash":{"name":"Qwen3.8 Omni Flash","model":"qwen/qwen3.8-omni-flash","description":"Qwen3.8 Omni Flash is a fast omni-modal reasoning model for understanding text, images, audio, and video. It is especially suited to meeting summaries, transcripts and subtitles, speaker-aware audiovisual analysis, and long-form content review. It returns text and supports a nearly one-million-token context window, tool calling, and structured output.","cost":"Average cost: $0.00031","costEstimate":0.00031,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-09-17","maxInputTokens":991808,"maxOutputTokens":131072,"category":"More","capabilities":["vision","audio-input","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":1.5e-7,"output_price":4.7e-7,"input_price_per_million":0.15,"output_price_per_million":0.47,"input":0.15,"output":0.47,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000047","input":0.15,"output":0.47,"cacheReadInputPer1kTokens":0.000016,"prompt_per_million":0.15,"completion_per_million":0.47,"prompt_per_token":"0.00000015","completion_per_token":"0.00000047","per_input_token":1.5e-7,"per_output_token":4.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00047,"cacheReadInputPer1kTokens":0.000016},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00047,"cacheReadInputPer1kTokens":0.000016},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":199.8},"alibaba/qwen3.8-flash":{"name":"Qwen3.8 Flash","model":"qwen/qwen3.8-flash","description":"Qwen3.8 Flash is Alibaba's latest fast multimodal model, with a million-token context window for coding, agentic workflows, visual understanding, long documents, codebases, and videos.","cost":"Average cost: $0.00032","costEstimate":0.000315,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-08-26","maxInputTokens":991808,"maxOutputTokens":131072,"category":"More","capabilities":["vision","video-input","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":1.4e-7,"output_price":4.2e-7,"input_price_per_million":0.14,"output_price_per_million":0.42,"input":0.14,"output":0.42,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000042","input":0.14,"output":0.42,"cacheReadInputPer1kTokens":0.000016,"prompt_per_million":0.14,"completion_per_million":0.42,"prompt_per_token":"0.00000014","completion_per_token":"0.00000042","per_input_token":1.4e-7,"per_output_token":4.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00042,"cacheReadInputPer1kTokens":0.000016,"cacheWriteInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00042,"cacheReadInputPer1kTokens":0.000016,"cacheWriteInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"},"avgOutputTokens":563.8},"qwen3.6-max-preview":{"name":"Qwen3.6 Max Preview","model":"qwen/qwen3.6-max-preview","description":"Qwen3.6 Max Preview is Alibaba's flagship Qwen 3.6 model for complex tasks. It supports both thinking and non-thinking modes in a single model id.","cost":"Average cost: $0.0046","costEstimate":0.00455,"provider":"qwen","visible":true,"dateAdded":"2026-04-20","maxInputTokens":245760,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00000104,"output_price":0.00000624,"input_price_per_million":1.04,"output_price_per_million":6.24,"input":1.04,"output":6.24,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000104","completion":"0.00000624","input":1.04,"output":6.24,"prompt_per_million":1.04,"completion_per_million":6.24,"prompt_per_token":"0.00000104","completion_per_token":"0.00000624","per_input_token":0.00000104,"per_output_token":0.00000624},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00104,"outputPer1kTokens":0.00624},"effective_price":{"inputPer1kTokens":0.00104,"outputPer1kTokens":0.00624},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.380Z"}},"qwen3.5-omni-flash":{"name":"Qwen3.5 Omni Flash","model":"qwen/qwen3.5-omni-flash","description":"Qwen3.5 Omni Flash is Qwen's fast multimodal model. We verified live support for text prompts, images, audio files, and direct video URLs on Alibaba's chat-completions-compatible API. Alibaba describes Flash as a fully evolved version of Qwen3 Omni with audio input support across 60+ languages.","cost":"Pricing varies by modality","costEstimate":0.00105,"provider":"qwen","visible":true,"dateAdded":"2026-03-30","maxInputTokens":49152,"maxOutputTokens":16384,"category":"More","capabilities":["vision","video-input","audio-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","pricing":{"currency":"USD","unit":"per_million_tokens","note":"varies_by_modality"},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00043,"outputPer1kTokens":0.00166},"effective_price":{"inputPer1kTokens":0.00043,"outputPer1kTokens":0.00166},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":106.4},"qwen3.5-omni-plus":{"name":"Qwen3.5 Omni Plus","model":"qwen/qwen3.5-omni-plus","description":"Qwen3.5 Omni Plus is Qwen's stronger general multimodal model. We verified live support for text prompts, images, audio files, and direct video URLs on Alibaba's chat-completions-compatible API. Alibaba describes Plus as a comprehensive evolution of Qwen3 Omni with support for over 10 hours of audio input.","cost":"Pricing varies by modality","costEstimate":0.0014,"provider":"qwen","visible":true,"dateAdded":"2026-03-30","maxInputTokens":983616,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input","audio-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","pricing":{"currency":"USD","unit":"per_million_tokens","note":"varies_by_modality"},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0083},"effective_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0083},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":834},"qwen3.5-122b-a10b":{"totalParams":122,"activeParams":10,"name":"Qwen3.5 122B A10B","model":"qwen/qwen3.5-122b-a10b","description":"Qwen3.5 122B A10B is a large open Qwen 3.5 MoE model served through Gerra with tool calling and structured output support.","cost":"Average cost: $0.0008","costEstimate":0.0008,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-02-24","maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.37e-7,"output_price":0.000003496,"input_price_per_million":0.437,"output_price_per_million":3.496,"input":0.437,"output":3.496,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000437","completion":"0.000003496","input":0.437,"output":3.496,"cacheReadInputPer1kTokens":0.000103788,"prompt_per_million":0.437,"completion_per_million":3.496,"prompt_per_token":"0.000000437","completion_per_token":"0.000003496","per_input_token":4.37e-7,"per_output_token":0.000003496},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000437,"outputPer1kTokens":0.003496,"cacheReadInputPer1kTokens":0.000103788},"effective_price":{"inputPer1kTokens":0.000437,"outputPer1kTokens":0.003496,"cacheReadInputPer1kTokens":0.000103788},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":195.2},"qwen3.5-122b-a10b:thinking":{"totalParams":122,"activeParams":10,"name":"Qwen3.5 122B A10B Thinking","model":"qwen/qwen3.5-122b-a10b:thinking","description":"Qwen3.5 122B A10B with extended reasoning enabled, served through Gerra with tool calling and structured output support.","cost":"Average cost: $0.0008","costEstimate":0.0008,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-02-24","maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.37e-7,"output_price":0.000003496,"input_price_per_million":0.437,"output_price_per_million":3.496,"input":0.437,"output":3.496,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000437","completion":"0.000003496","input":0.437,"output":3.496,"cacheReadInputPer1kTokens":0.000103788,"prompt_per_million":0.437,"completion_per_million":3.496,"prompt_per_token":"0.000000437","completion_per_token":"0.000003496","per_input_token":4.37e-7,"per_output_token":0.000003496},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000437,"outputPer1kTokens":0.003496,"cacheReadInputPer1kTokens":0.000103788},"effective_price":{"inputPer1kTokens":0.000437,"outputPer1kTokens":0.003496,"cacheReadInputPer1kTokens":0.000103788},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":1249.1},"qwen3.5-27b":{"totalParams":27,"name":"Qwen3.5 27B","model":"qwen/qwen3.5-27b","description":"Qwen3.5 27B is a native vision-language dense model optimized for fast responses while balancing quality and inference speed.","cost":"Average cost: $0.0013","costEstimate":0.00126,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-02-24","maxInputTokens":260096,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.7e-7,"output_price":0.00000216,"input_price_per_million":0.27,"output_price_per_million":2.16,"input":0.27,"output":2.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000027","completion":"0.00000216","input":0.27,"output":2.16,"prompt_per_million":0.27,"completion_per_million":2.16,"prompt_per_token":"0.00000027","completion_per_token":"0.00000216","per_input_token":2.7e-7,"per_output_token":0.00000216},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00027,"outputPer1kTokens":0.00216},"effective_price":{"inputPer1kTokens":0.00027,"outputPer1kTokens":0.00216},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":135.1},"qwen3.5-27b:thinking":{"totalParams":27,"name":"Qwen3.5 27B Thinking","model":"qwen/qwen3.5-27b:thinking","description":"Qwen3.5 27B with extended reasoning enabled. A native vision-language dense model optimized for fast responses.","cost":"Average cost: $0.0013","costEstimate":0.00126,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-02-24","maxInputTokens":260096,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.7e-7,"output_price":0.00000216,"input_price_per_million":0.27,"output_price_per_million":2.16,"input":0.27,"output":2.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000027","completion":"0.00000216","input":0.27,"output":2.16,"prompt_per_million":0.27,"completion_per_million":2.16,"prompt_per_token":"0.00000027","completion_per_token":"0.00000216","per_input_token":2.7e-7,"per_output_token":0.00000216},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00027,"outputPer1kTokens":0.00216},"effective_price":{"inputPer1kTokens":0.00027,"outputPer1kTokens":0.00216},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":1421.5},"qwen3.5-35b-a3b":{"totalParams":35,"activeParams":3,"name":"Qwen3.5 35B A3B","model":"qwen/qwen3.5-35b-a3b","description":"Qwen3.5 35B A3B is a native vision-language MoE model with hybrid attention designed for efficient inference and strong general performance.","cost":"Average cost: $0.0010","costEstimate":0.00099,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-02-24","maxInputTokens":260096,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.25e-7,"output_price":0.0000018,"input_price_per_million":0.225,"output_price_per_million":1.8,"input":0.225,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000225","completion":"0.0000018","input":0.225,"output":1.8,"prompt_per_million":0.225,"completion_per_million":1.8,"prompt_per_token":"0.000000225","completion_per_token":"0.0000018","per_input_token":2.25e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000225,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.000225,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":386.1},"qwen3.5-35b-a3b:thinking":{"totalParams":35,"activeParams":3,"name":"Qwen3.5 35B A3B Thinking","model":"qwen/qwen3.5-35b-a3b:thinking","description":"Qwen3.5 35B A3B with extended reasoning enabled. A native vision-language MoE model with hybrid attention.","cost":"Average cost: $0.0010","costEstimate":0.00099,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-02-24","maxInputTokens":260096,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.25e-7,"output_price":0.0000018,"input_price_per_million":0.225,"output_price_per_million":1.8,"input":0.225,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000225","completion":"0.0000018","input":0.225,"output":1.8,"prompt_per_million":0.225,"completion_per_million":1.8,"prompt_per_token":"0.000000225","completion_per_token":"0.0000018","per_input_token":2.25e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000225,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.000225,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":871.3},"qwen3.5-flash":{"name":"Qwen3.5 Flash","model":"qwen/qwen3.5-flash","description":"Qwen3.5 Flash is the fastest and cheapest native Qwen 3.5 vision-language model with a 1M-token context window.","cost":"Average cost: $0.0003","costEstimate":0.0003,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-02-24","maxInputTokens":991808,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":133.7},"qwen3.5-flash:thinking":{"name":"Qwen3.5 Flash Thinking","model":"qwen/qwen3.5-flash:thinking","description":"Qwen3.5 Flash with extended reasoning enabled. The fastest and cheapest native Qwen 3.5 vision-language model.","cost":"Average cost: $0.0003","costEstimate":0.0003,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-02-24","maxInputTokens":991808,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4e-7,"input_price_per_million":0.1,"output_price_per_million":0.4,"input":0.1,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000004","input":0.1,"output":0.4,"prompt_per_million":0.1,"completion_per_million":0.4,"prompt_per_token":"0.0000001","completion_per_token":"0.0000004","per_input_token":1e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"}},"Qwen/Qwen3.6-35B-A3B":{"totalParams":35,"activeParams":3,"name":"Qwen3.6 35B A3B","model":"qwen/qwen3.6-35b-a3b","description":"Qwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-04-17","maxInputTokens":262144,"maxOutputTokens":16384,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.12e-7,"output_price":8e-7,"input_price_per_million":0.112,"output_price_per_million":0.8,"input":0.112,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000112","completion":"0.0000008","input":0.112,"output":0.8,"prompt_per_million":0.112,"completion_per_million":0.8,"prompt_per_token":"0.000000112","completion_per_token":"0.0000008","per_input_token":1.12e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000112,"outputPer1kTokens":0.0008},"effective_price":{"inputPer1kTokens":0.000112,"outputPer1kTokens":0.0008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":87.5},"Qwen/Qwen3.6-35B-A3B:thinking":{"totalParams":35,"activeParams":3,"name":"Qwen3.6 35B A3B Thinking","model":"qwen/qwen3.6-35b-a3b:thinking","description":"Qwen3.6 35B A3B is a native vision-language MoE model with hybrid attention. Compared to Qwen3.5 35B A3B, Alibaba reports stronger agentic coding, mathematical and code reasoning, and better spatial understanding (including object localization and detection).","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-04-19","maxInputTokens":262144,"maxOutputTokens":16384,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.12e-7,"output_price":8e-7,"input_price_per_million":0.112,"output_price_per_million":0.8,"input":0.112,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000112","completion":"0.0000008","input":0.112,"output":0.8,"prompt_per_million":0.112,"completion_per_million":0.8,"prompt_per_token":"0.000000112","completion_per_token":"0.0000008","per_input_token":1.12e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000112,"outputPer1kTokens":0.0008},"effective_price":{"inputPer1kTokens":0.000112,"outputPer1kTokens":0.0008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":2482.9},"alibaba/qwen3.6-flash":{"name":"Qwen3.6 Flash","model":"qwen/qwen3.6-flash","description":"Qwen3.6 Flash is Alibaba's fast native vision-language model in the Qwen 3.6 family. It improves over 3.5 Flash with stronger coding/agent performance and better spatial intelligence, including object localization and detection.","cost":"Average cost: $0.00068","costEstimate":0.00068,"provider":"qwen","visible":true,"isOpenSource":false,"dateAdded":"2026-04-17","maxInputTokens":991808,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.9e-7,"output_price":0.00000116,"input_price_per_million":0.19,"output_price_per_million":1.16,"input":0.19,"output":1.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000019","completion":"0.00000116","input":0.19,"output":1.16,"cacheReadInputPer1kTokens":0.00002,"prompt_per_million":0.19,"completion_per_million":1.16,"prompt_per_token":"0.00000019","completion_per_token":"0.00000116","per_input_token":1.9e-7,"per_output_token":0.00000116},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00019,"outputPer1kTokens":0.00116,"cacheReadInputPer1kTokens":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00008,"cacheWriteInputPer1kTokens":0.00024,"cacheWriteInputPer1kTokensAbove200k":0.00097},"effective_price":{"inputPer1kTokens":0.00019,"outputPer1kTokens":0.00116,"cacheReadInputPer1kTokens":0.00002,"cacheReadInputPer1kTokensAbove200k":0.00008,"cacheWriteInputPer1kTokens":0.00024,"cacheWriteInputPer1kTokensAbove200k":0.00097},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":567.7},"alibaba/qwen3.6-27b":{"totalParams":27,"name":"Qwen3.6 27B","model":"qwen/qwen3.6-27b","description":"Qwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.","cost":"Average cost: $0.0021","costEstimate":0.0021,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-04-23","maxInputTokens":260096,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.03e-7,"output_price":0.00000224,"input_price_per_million":0.203,"output_price_per_million":2.24,"input":0.203,"output":2.24,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000203","completion":"0.00000224","input":0.203,"output":2.24,"prompt_per_million":0.203,"completion_per_million":2.24,"prompt_per_token":"0.000000203","completion_per_token":"0.00000224","per_input_token":2.03e-7,"per_output_token":0.00000224},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000203,"outputPer1kTokens":0.00224},"effective_price":{"inputPer1kTokens":0.000203,"outputPer1kTokens":0.00224},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":165.7},"alibaba/qwen3.6-27b:thinking":{"totalParams":27,"name":"Qwen3.6 27B Thinking","model":"qwen/qwen3.6-27b:thinking","description":"Qwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.","cost":"Average cost: $0.0021","costEstimate":0.0021,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-04-23","maxInputTokens":260096,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.03e-7,"output_price":0.00000224,"input_price_per_million":0.203,"output_price_per_million":2.24,"input":0.203,"output":2.24,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000203","completion":"0.00000224","input":0.203,"output":2.24,"prompt_per_million":0.203,"completion_per_million":2.24,"prompt_per_token":"0.000000203","completion_per_token":"0.00000224","per_input_token":2.03e-7,"per_output_token":0.00000224},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000203,"outputPer1kTokens":0.00224},"effective_price":{"inputPer1kTokens":0.000203,"outputPer1kTokens":0.00224},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":1213},"deepseek-ai/deepseek-v3.2-exp":{"totalParams":685,"activeParams":37,"name":"DeepSeek V3.2 Exp","model":"deepseek-ai/deepseek-v3.2-exp","description":"DeepSeek V3.2 Exp is an experimental V3-series model with improved long-context efficiency compared with earlier V3 releases. FP8.","cost":"Average cost: $0.0012","isOpenSource":true,"provider":"deepseek","costEstimate":0.0012,"visible":true,"category":"More","maxInputTokens":163840,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.8e-7,"output_price":4.2e-7,"input_price_per_million":0.28,"output_price_per_million":0.42,"input":0.28,"output":0.42,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000028","completion":"0.00000042","input":0.28,"output":0.42,"prompt_per_million":0.28,"completion_per_million":0.42,"prompt_per_token":"0.00000028","completion_per_token":"0.00000042","per_input_token":2.8e-7,"per_output_token":4.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"effective_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":716.3},"deepseek-ai/deepseek-v3.2-exp-thinking":{"totalParams":685,"activeParams":37,"name":"DeepSeek V3.2 Exp Thinking","model":"deepseek-ai/deepseek-v3.2-exp-thinking","description":"DeepSeek V3.2 Exp Thinking is an experimental V3-series reasoning model with improved long-context efficiency compared with earlier V3 releases. FP8.","cost":"Average cost: $0.0012","isOpenSource":true,"category":"More","costEstimate":0.0012,"provider":"deepseek","capabilities":["reasoning"],"maxInputTokens":163840,"maxOutputTokens":65536,"visible":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.8e-7,"output_price":4.2e-7,"input_price_per_million":0.28,"output_price_per_million":0.42,"input":0.28,"output":0.42,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000028","completion":"0.00000042","input":0.28,"output":0.42,"prompt_per_million":0.28,"completion_per_million":0.42,"prompt_per_token":"0.00000028","completion_per_token":"0.00000042","per_input_token":2.8e-7,"per_output_token":4.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"effective_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":916.9},"deepseek/deepseek-v3.2-speciale":{"totalParams":685,"activeParams":37,"name":"DeepSeek V3.2 Speciale","model":"deepseek/deepseek-v3.2-speciale","description":"DeepSeek V3.2 Speciale — maxed-out reasoning capabilities rivaling Gemini-3.0-Pro. Gold-medal performance on IMO, CMO, and ICPC World Finals. 65.5K max output with DeepSeek Sparse Attention. FP8.","cost":"Average cost: $0.0007","costEstimate":0.0007,"provider":"deepseek","isOpenSource":true,"visible":true,"disabled":true,"dateAdded":"2025-12-02","category":"More","maxInputTokens":163000,"maxOutputTokens":65536,"capabilities":["pdf-upload","reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.8e-7,"output_price":4.2e-7,"input_price_per_million":0.28,"output_price_per_million":0.42,"input":0.28,"output":0.42,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000028","completion":"0.00000042","input":0.28,"output":0.42,"prompt_per_million":0.28,"completion_per_million":0.42,"prompt_per_token":"0.00000028","completion_per_token":"0.00000042","per_input_token":2.8e-7,"per_output_token":4.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"effective_price":{"inputPer1kTokens":0.00028,"outputPer1kTokens":0.00042},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"}},"deepseek/deepseek-v3.2":{"name":"DeepSeek V3.2","model":"deepseek/deepseek-v3.2","description":"DeepSeek V3.2 (non-thinking mode) — official successor to V3.2-Exp. Reasoning-first model built for agents with GPT-5 level performance. Balanced inference vs. output length for everyday use. First DeepSeek model with thinking-in-tool-use capability. FP8.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2025-12-01","maxInputTokens":163000,"maxOutputTokens":65536,"totalParams":685,"activeParams":37,"capabilities":["pdf-upload","tool-calling","structured-output"],"preferredProviders":["Baidu","SiliconFlow","DeepInfra"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.088e-7,"output_price":3.096e-7,"input_price_per_million":0.2088,"output_price_per_million":0.3096,"input":0.2088,"output":0.3096,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002088","completion":"0.0000003096","input":0.2088,"output":0.3096,"cacheReadInputPer1kTokens":0.0000216,"prompt_per_million":0.2088,"completion_per_million":0.3096,"prompt_per_token":"0.0000002088","completion_per_token":"0.0000003096","per_input_token":2.088e-7,"per_output_token":3.096e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002088,"outputPer1kTokens":0.0003096,"cacheReadInputPer1kTokens":0.0000216},"effective_price":{"inputPer1kTokens":0.0002088,"outputPer1kTokens":0.0003096,"cacheReadInputPer1kTokens":0.0000216},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":407.9},"deepseek/deepseek-v3.2:thinking":{"name":"DeepSeek V3.2 Thinking","model":"deepseek/deepseek-v3.2:thinking","description":"DeepSeek V3.2 (thinking/reasoner mode) — official successor to V3.2-Exp. Reasoning-first model built for agents with GPT-5 level performance. Balanced inference vs. output length. First DeepSeek model with thinking-in-tool-use capability. FP8.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"deepseek","isOpenSource":true,"visible":true,"category":"More","dateAdded":"2025-12-01","maxInputTokens":163000,"maxOutputTokens":65536,"totalParams":685,"activeParams":37,"capabilities":["pdf-upload","reasoning","tool-calling","structured-output"],"preferredProviders":["Baidu","SiliconFlow","DeepInfra"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.088e-7,"output_price":3.096e-7,"input_price_per_million":0.2088,"output_price_per_million":0.3096,"input":0.2088,"output":0.3096,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002088","completion":"0.0000003096","input":0.2088,"output":0.3096,"cacheReadInputPer1kTokens":0.0000216,"prompt_per_million":0.2088,"completion_per_million":0.3096,"prompt_per_token":"0.0000002088","completion_per_token":"0.0000003096","per_input_token":2.088e-7,"per_output_token":3.096e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002088,"outputPer1kTokens":0.0003096,"cacheReadInputPer1kTokens":0.0000216},"effective_price":{"inputPer1kTokens":0.0002088,"outputPer1kTokens":0.0003096,"cacheReadInputPer1kTokens":0.0000216},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":1444.3},"deepseek/deepseek-v4-flash-0423":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash 0423","model":"deepseek/deepseek-v4-flash-0423","description":"The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.","cost":"Input $0.14/m, Output $0.28/m, Cached input $0.028/m","costEstimate":0.00042,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-10-07","maxInputTokens":1048576,"capabilities":["reasoning","tool-calling","structured-output"],"defaultThinkingEnabled":false,"defaultReasoningEffort":"none","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.000028},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.000028},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":244.7},"deepseek/deepseek-v4-flash-0423:thinking":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash 0423 (Thinking)","model":"deepseek/deepseek-v4-flash-0423:thinking","description":"The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.","cost":"Input $0.14/m, Output $0.28/m, Cached input $0.028/m","costEstimate":0.00042,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-10-07","maxInputTokens":1048576,"capabilities":["reasoning","tool-calling","structured-output"],"defaultThinkingEnabled":true,"defaultReasoningEffort":"high","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.000028},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.000028},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":1055.7},"deepseek/deepseek-v4-flash":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash","model":"deepseek/deepseek-v4-flash","description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.","cost":"Input $0.14/m, Output $0.28/m, Cached input $0.0028/m","costEstimate":0.0004,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-04-24","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high","max"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.0000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":136.7},"deepseek/deepseek-v4-flash-vision-exp":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash Vision Exp","model":"deepseek/deepseek-v4-flash-vision-exp","description":"An experimental vision-enabled DeepSeek V4 Flash model that adds image understanding while retaining the text, reasoning, coding, tool-calling, and agent capabilities of the base model.","cost":"Off-peak: Input $0.22/m, Output $0.66/m, Cached input $0.007/m","costEstimate":0.0009,"provider":"deepseek","visible":true,"dateAdded":"2026-08-21","maxInputTokens":1048576,"maxOutputTokens":384000,"preferredProviders":["DeepSeek"],"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":2.2e-7,"output_price":6.6e-7,"input_price_per_million":0.22,"output_price_per_million":0.66,"input":0.22,"output":0.66,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000022","completion":"0.00000066","input":0.22,"output":0.66,"cacheReadInputPer1kTokens":0.000007,"prompt_per_million":0.22,"completion_per_million":0.66,"prompt_per_token":"0.00000022","completion_per_token":"0.00000066","per_input_token":2.2e-7,"per_output_token":6.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00044,"outputPer1kTokens":0.00132,"cacheReadInputPer1kTokens":0.000014},"effective_price":{"inputPer1kTokens":0.00022,"outputPer1kTokens":0.00066,"cacheReadInputPer1kTokens":0.000007},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":50,"valid_from":"2026-10-26T10:00:00.000Z","valid_until":"2026-10-27T01:00:00.000Z","source":"schedule","updated_at":"2026-08-16T16:00:00.000Z"},"avgOutputTokens":1334.6},"deepseek/deepseek-v4-flash-0731":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash 0731","model":"deepseek/deepseek-v4-flash-0731","description":"DeepSeek V4 Flash 0731 is a re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.","cost":"Input $0.05/m, Output $0.16/m, Cached input $0.013/m","costEstimate":0.0002,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-07-31","maxInputTokens":1000000,"maxOutputTokens":131072,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":5e-8,"output_price":1.6e-7,"input_price_per_million":0.05,"output_price_per_million":0.16,"input":0.05,"output":0.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000016","input":0.05,"output":0.16,"cacheReadInputPer1kTokens":0.000013,"prompt_per_million":0.05,"completion_per_million":0.16,"prompt_per_token":"0.00000005","completion_per_token":"0.00000016","per_input_token":5e-8,"per_output_token":1.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00016,"cacheReadInputPer1kTokens":0.000013},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00016,"cacheReadInputPer1kTokens":0.000013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.381Z"},"avgOutputTokens":451.1},"deepseek/deepseek-v4-flash-latest":{"name":"DeepSeek Flash Latest","model":"deepseek/deepseek-v4-flash-latest","description":"Moving alias for DeepSeek V4.1 Flash 1017, with text and image input, tool calling, structured output, and optional reasoning. Zero data retention and JSON Schema output are available on eligible routes; output limits and reasoning levels depend on the selected route.","cost":"Auto and provider-specific prices can differ. See pricing details for current input, output, and cached-input rates.","costEstimate":0.00075,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-08-02","maxInputTokens":1048576,"maxOutputTokens":393216,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"tags":["latest"],"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000003,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000003},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":50,"valid_from":"2026-10-26T10:00:00.000Z","valid_until":"2026-10-27T01:00:00.000Z","source":"schedule","updated_at":"2026-10-17T00:00:00.000Z"}},"deepseek/deepseek-v4-flash-0731:thinking":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash 0731 (Thinking)","model":"deepseek/deepseek-v4-flash-0731:thinking","description":"DeepSeek V4 Flash 0731 Thinking enables reasoning by default on the re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.","cost":"Input $0.05/m, Output $0.16/m, Cached input $0.013/m","costEstimate":0.0002,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-08-01","maxInputTokens":1000000,"maxOutputTokens":131072,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":5e-8,"output_price":1.6e-7,"input_price_per_million":0.05,"output_price_per_million":0.16,"input":0.05,"output":0.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000016","input":0.05,"output":0.16,"cacheReadInputPer1kTokens":0.000013,"prompt_per_million":0.05,"completion_per_million":0.16,"prompt_per_token":"0.00000005","completion_per_token":"0.00000016","per_input_token":5e-8,"per_output_token":1.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00016,"cacheReadInputPer1kTokens":0.000013},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00016,"cacheReadInputPer1kTokens":0.000013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":755.1},"deepseek/deepseek-v4-flash:thinking":{"totalParams":284,"activeParams":13,"name":"DeepSeek V4 Flash (Thinking)","model":"deepseek/deepseek-v4-flash:thinking","description":"DeepSeek V4 Flash Thinking enables DeepSeek's reasoning mode on the efficiency-optimized Mixture-of-Experts model with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.","cost":"Input $0.14/m, Output $0.28/m, Cached input $0.0028/m","costEstimate":0.0004,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-04-24","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","high","max"]}},"api":"chat","input_price":1.4e-7,"output_price":2.8e-7,"input_price_per_million":0.14,"output_price_per_million":0.28,"input":0.14,"output":0.28,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000014","completion":"0.00000028","input":0.14,"output":0.28,"cacheReadInputPer1kTokens":0.0000028,"prompt_per_million":0.14,"completion_per_million":0.28,"prompt_per_token":"0.00000014","completion_per_token":"0.00000028","per_input_token":1.4e-7,"per_output_token":2.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028},"effective_price":{"inputPer1kTokens":0.00014,"outputPer1kTokens":0.00028,"cacheReadInputPer1kTokens":0.0000028},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":688.8},"deepseek/deepseek-v4.1-flash-1017":{"name":"DeepSeek V4.1 Flash 1017","model":"deepseek/deepseek-v4.1-flash-1017","description":"The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Released under the MIT license.","cost":"Auto and provider-specific prices can differ. See pricing details for current input, output, and cached-input rates.","costEstimate":0.00075,"provider":"deepseek","visible":true,"isOpenSource":true,"dateAdded":"2026-10-17","maxInputTokens":1048576,"maxOutputTokens":393216,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000003,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000003},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":50,"valid_from":"2026-10-26T10:00:00.000Z","valid_until":"2026-10-27T01:00:00.000Z","source":"schedule","updated_at":"2026-10-17T00:00:00.000Z"},"avgOutputTokens":465.3},"deepseek/deepseek-v4.1-flash-1017:thinking":{"name":"DeepSeek V4.1 Flash 1017 Thinking","model":"deepseek/deepseek-v4.1-flash-1017:thinking","description":"The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Released under the MIT license.","cost":"Auto and provider-specific prices can differ. See pricing details for current input, output, and cached-input rates.","costEstimate":0.00075,"provider":"deepseek","visible":true,"isOpenSource":true,"dateAdded":"2026-10-17","maxInputTokens":1048576,"maxOutputTokens":393216,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000003,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000003},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":50,"valid_from":"2026-10-26T10:00:00.000Z","valid_until":"2026-10-27T01:00:00.000Z","source":"schedule","updated_at":"2026-10-17T00:00:00.000Z"},"avgOutputTokens":1208.2},"deepseek/deepseek-v4-pro-0813":{"totalParams":1600,"activeParams":49,"name":"DeepSeek V4 Pro 0813","model":"deepseek/deepseek-v4-pro-0813","description":"DeepSeek V4 Pro 0813 is the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.","cost":"Input $1.32/m, Cached input $0.044/m, Output $3.96/m","costEstimate":0.0053,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-08-12","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000025,"input_price_per_million":1.1,"output_price_per_million":2.5,"input":1.1,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000025","input":1.1,"output":2.5,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":1.1,"completion_per_million":2.5,"prompt_per_token":"0.0000011","completion_per_token":"0.0000025","per_input_token":0.0000011,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":788.1},"deepseek/deepseek-v4-pro-0813:thinking":{"totalParams":1600,"activeParams":49,"name":"DeepSeek V4 Pro 0813 Thinking","model":"deepseek/deepseek-v4-pro-0813:thinking","description":"DeepSeek V4 Pro 0813 Thinking enables reasoning by default on the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.","cost":"Input $1.32/m, Cached input $0.044/m, Output $3.96/m","costEstimate":0.0053,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-08-12","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000025,"input_price_per_million":1.1,"output_price_per_million":2.5,"input":1.1,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000025","input":1.1,"output":2.5,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":1.1,"completion_per_million":2.5,"prompt_per_token":"0.0000011","completion_per_token":"0.0000025","per_input_token":0.0000011,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":2401.7},"deepseek/deepseek-v4-pro":{"totalParams":1600,"activeParams":49,"name":"DeepSeek V4 Pro","model":"deepseek/deepseek-v4-pro","description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with a 1M-token context window, built for advanced reasoning, coding, long-horizon agent workflows, knowledge, math, and software engineering tasks.","cost":"Average cost: $0.0052","costEstimate":0.0052,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-04-24","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high","max"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000022,"input_price_per_million":1.1,"output_price_per_million":2.2,"input":1.1,"output":2.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000022","input":1.1,"output":2.2,"cacheReadInputPer1kTokens":0.00011,"prompt_per_million":1.1,"completion_per_million":2.2,"prompt_per_token":"0.0000011","completion_per_token":"0.0000022","per_input_token":0.0000011,"per_output_token":0.0000022},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":416},"deepseek/deepseek-latest":{"name":"DeepSeek Latest","model":"deepseek/deepseek-latest","description":"Compatibility alias that routes to the newest thinking DeepSeek model. Currently routes to DeepSeek V4 Pro 0813 Thinking, the general-availability release built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. Requests are routed through privacy-friendly third-party providers and are not sent directly to DeepSeek.","cost":"Input $1.32/m, Cached input $0.044/m, Output $3.96/m","costEstimate":0.0053,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-05-03","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"tags":["latest"],"api":"chat","input_price":0.0000011,"output_price":0.0000025,"input_price_per_million":1.1,"output_price_per_million":2.5,"input":1.1,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000025","input":1.1,"output":2.5,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":1.1,"completion_per_million":2.5,"prompt_per_token":"0.0000011","completion_per_token":"0.0000025","per_input_token":0.0000011,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0025,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"}},"deepseek/deepseek-v4-pro:thinking":{"totalParams":1600,"activeParams":49,"name":"DeepSeek V4 Pro (Thinking)","model":"deepseek/deepseek-v4-pro:thinking","description":"DeepSeek V4 Pro Thinking enables DeepSeek's chain-of-thought mode on the large-scale Mixture-of-Experts model with a 1M-token context window, built for advanced reasoning, coding, long-horizon agent workflows, knowledge, math, and software engineering tasks.","cost":"Average cost: $0.0052","costEstimate":0.0052,"provider":"deepseek","isOpenSource":true,"visible":true,"dateAdded":"2026-04-24","maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","high","max"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000022,"input_price_per_million":1.1,"output_price_per_million":2.2,"input":1.1,"output":2.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000022","input":1.1,"output":2.2,"cacheReadInputPer1kTokens":0.00011,"prompt_per_million":1.1,"completion_per_million":2.2,"prompt_per_token":"0.0000011","completion_per_token":"0.0000022","per_input_token":0.0000011,"per_output_token":0.0000022},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0022,"cacheReadInputPer1kTokens":0.00011},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":1578.8},"qwen-plus":{"name":"Qwen Plus","model":"qwen/qwen-plus","description":"Alibaba's balanced model. Fast, cheap, yet still very powerful.","cost":"Average cost: $0.0015","costEstimate":0.0015,"dateAdded":"2024-04-15","provider":"qwen","visible":true,"maxInputTokens":995904,"maxOutputTokens":32768,"category":"More","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.995e-7,"output_price":0.0000012002,"input_price_per_million":0.3995,"output_price_per_million":1.2002,"input":0.3995,"output":1.2002,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003995","completion":"0.0000012002","input":0.3995,"output":1.2002,"prompt_per_million":0.3995,"completion_per_million":1.2002,"prompt_per_token":"0.0000003995","completion_per_token":"0.0000012002","per_input_token":3.995e-7,"per_output_token":0.0000012002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003995,"outputPer1kTokens":0.0012002},"effective_price":{"inputPer1kTokens":0.0003995,"outputPer1kTokens":0.0012002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":3.4},"qwen/qwen3.5-397b-a17b":{"totalParams":397,"activeParams":17,"name":"Qwen3.5 397B A17B","model":"qwen/qwen3.5-397b-a17b","description":"Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Supports text, image, and video input with a 256K context window.","cost":"Average cost: $0.0024","costEstimate":0.0024,"provider":"qwen","visible":true,"dateAdded":"2026-02-16","isOpenSource":true,"maxInputTokens":258048,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000036,"input_price_per_million":0.6,"output_price_per_million":3.6,"input":0.6,"output":3.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000036","input":0.6,"output":3.6,"prompt_per_million":0.6,"completion_per_million":3.6,"prompt_per_token":"0.0000006","completion_per_token":"0.0000036","per_input_token":6e-7,"per_output_token":0.0000036},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0036},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0036},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":373.9},"qwen/qwen3.5-397b-a17b-thinking":{"totalParams":397,"activeParams":17,"name":"Qwen3.5 397B A17B Thinking","model":"qwen/qwen3.5-397b-a17b:thinking","description":"Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention and extended reasoning. Supports text, image, and video input with a 256K context window.","cost":"Average cost: $0.004","costEstimate":0.004,"provider":"qwen","visible":true,"dateAdded":"2026-02-16","isOpenSource":true,"maxInputTokens":258048,"maxOutputTokens":65536,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-7,"output_price":0.0000036,"input_price_per_million":0.6,"output_price_per_million":3.6,"input":0.6,"output":3.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000006","completion":"0.0000036","input":0.6,"output":3.6,"prompt_per_million":0.6,"completion_per_million":3.6,"prompt_per_token":"0.0000006","completion_per_token":"0.0000036","per_input_token":6e-7,"per_output_token":0.0000036},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0036},"effective_price":{"inputPer1kTokens":0.0006,"outputPer1kTokens":0.0036},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":1837},"qwen/qwen3.5-plus":{"name":"Qwen3.5 Plus","model":"qwen/qwen3.5-plus","description":"Qwen 3.5 Plus is a commercial model with hybrid linear attention and sparse MoE architecture. Supports text, image, and video input with a 1M context window.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"qwen","visible":true,"dateAdded":"2026-02-16","maxInputTokens":983616,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000024,"input_price_per_million":0.4,"output_price_per_million":2.4,"input":0.4,"output":2.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000024","input":0.4,"output":2.4,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.4,"completion_per_million":2.4,"prompt_per_token":"0.0000004","completion_per_token":"0.0000024","per_input_token":4e-7,"per_output_token":0.0000024},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0024,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0024,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":140.5},"qwen/qwen3.5-plus-thinking":{"name":"Qwen3.5 Plus Thinking","model":"qwen/qwen3.5-plus:thinking","description":"Qwen 3.5 Plus with extended reasoning. A commercial model with hybrid linear attention and sparse MoE architecture. Supports text, image, and video input with a 1M context window.","cost":"Average cost: $0.003","costEstimate":0.003,"provider":"qwen","visible":true,"dateAdded":"2026-02-16","maxInputTokens":983616,"maxOutputTokens":65536,"category":"More","labelVariant":"outline","capabilities":["reasoning","vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000024,"input_price_per_million":0.4,"output_price_per_million":2.4,"input":0.4,"output":2.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000024","input":0.4,"output":2.4,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.4,"completion_per_million":2.4,"prompt_per_token":"0.0000004","completion_per_token":"0.0000024","per_input_token":4e-7,"per_output_token":0.0000024},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0024,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0024,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":581.8},"agnes-3.0-flash":{"name":"Agnes 3.0 Flash","model":"agnes-3.0-flash","description":"Agnes 3.0 Flash is a low-cost model for coding, tool use, and multi-turn agent tasks. It supports text and image input, optional thinking, and a 512K-token context window.","cost":"Input $0.05/m, Output $0.15/m, Cached input $0.005/m","costEstimate":0.0001,"provider":"agnes","visible":true,"dateAdded":"2026-09-09","maxInputTokens":524288,"maxOutputTokens":65536,"category":"More","capabilities":["vision","reasoning","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":1.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.15,"input":0.05,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000015","input":0.05,"output":0.15,"cacheReadInputPer1kTokens":0.000005,"prompt_per_million":0.05,"completion_per_million":0.15,"prompt_per_token":"0.00000005","completion_per_token":"0.00000015","per_input_token":5e-8,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000005},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00015,"cacheReadInputPer1kTokens":0.000005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":863.7},"deepseek/deepseek-v4.1-flash":{"name":"DeepSeek V4.1 Flash","model":"deepseek/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.","cost":"Input $0.13/m, Output $0.52/m, Cached input $0.006/m","costEstimate":0.00052,"provider":"deepseek","visible":true,"isOpenSource":true,"dateAdded":"2026-09-08","maxInputTokens":1000000,"maxOutputTokens":384000,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":1.3e-7,"output_price":5.2e-7,"input_price_per_million":0.13,"output_price_per_million":0.52,"input":0.13,"output":0.52,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000013","completion":"0.00000052","input":0.13,"output":0.52,"cacheReadInputPer1kTokens":0.000006,"prompt_per_million":0.13,"completion_per_million":0.52,"prompt_per_token":"0.00000013","completion_per_token":"0.00000052","per_input_token":1.3e-7,"per_output_token":5.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.00052,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.00052,"cacheReadInputPer1kTokens":0.000006},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"valid_from":"2026-09-20T00:00:00.000Z","source":"schedule","updated_at":"2026-09-20T00:00:00.000Z"},"avgOutputTokens":375.5},"deepseek/deepseek-v4.1-flash:thinking":{"name":"DeepSeek V4.1 Flash Thinking","model":"deepseek/deepseek-v4.1-flash:thinking","description":"DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.","cost":"Input $0.13/m, Output $0.52/m, Cached input $0.006/m","costEstimate":0.00052,"provider":"deepseek","visible":true,"isOpenSource":true,"dateAdded":"2026-09-08","maxInputTokens":1000000,"maxOutputTokens":384000,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["none","low","high","max"]}},"api":"chat","input_price":1.3e-7,"output_price":5.2e-7,"input_price_per_million":0.13,"output_price_per_million":0.52,"input":0.13,"output":0.52,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000013","completion":"0.00000052","input":0.13,"output":0.52,"cacheReadInputPer1kTokens":0.000006,"prompt_per_million":0.13,"completion_per_million":0.52,"prompt_per_token":"0.00000013","completion_per_token":"0.00000052","per_input_token":1.3e-7,"per_output_token":5.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.00052,"cacheReadInputPer1kTokens":0.000006},"effective_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.00052,"cacheReadInputPer1kTokens":0.000006},"pricing_type":"scheduled","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"valid_from":"2026-09-20T00:00:00.000Z","source":"schedule","updated_at":"2026-09-20T00:00:00.000Z"},"avgOutputTokens":784.5},"qwen3.8-max":{"name":"Qwen3.8 Max","model":"qwen/qwen3.8-max","description":"Qwen3.8 Max is Qwen's 2.4T-parameter flagship model for coding, knowledge work, full-stack development, data analysis, and long-running agent workflows in non-thinking mode. It supports text, image, video, PDF input, tool calling, structured output, and a near-million-token context window.","cost":"Average cost: $0.0050","costEstimate":0.005,"provider":"qwen","visible":true,"dateAdded":"2026-08-03","maxInputTokens":991000,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":328.4},"qwen3.8-max:thinking":{"name":"Qwen3.8 Max Thinking","model":"qwen/qwen3.8-max:thinking","description":"Qwen3.8 Max Thinking enables generation-time reasoning for deeper coding, knowledge work, data analysis, and long-running agent workflows. It supports text, image, video, PDF input, tool calling, structured output, and a near-million-token context window.","cost":"Average cost: $0.0050","costEstimate":0.005,"provider":"qwen","visible":true,"dateAdded":"2026-08-03","maxInputTokens":991000,"maxOutputTokens":131072,"category":"More","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision","video-input","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","max"]}},"api":"chat","input_price":0.000002,"output_price":0.000006,"input_price_per_million":2,"output_price_per_million":6,"input":2,"output":6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000006","input":2,"output":6,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":2,"completion_per_million":6,"prompt_per_token":"0.000002","completion_per_token":"0.000006","per_input_token":0.000002,"per_output_token":0.000006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.006,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":2523.7},"qwen-3.6-plus":{"name":"Qwen 3.6 Plus","model":"qwen/qwen3.6-plus","description":"Qwen 3.6 Plus is a commercial native multimodal agent model with a major step up over the 3.5 series in agentic coding, front-end programming, OCR, object localization, and general vision-language performance. Supports text, image, and video input with a 1M context window.","cost":"Average cost: $0.0018","costEstimate":0.0018,"provider":"qwen","visible":true,"dateAdded":"2026-04-02","maxInputTokens":991808,"maxOutputTokens":65536,"category":"More","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.25e-7,"output_price":0.00000195,"input_price_per_million":0.325,"output_price_per_million":1.95,"input":0.325,"output":1.95,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000325","completion":"0.00000195","input":0.325,"output":1.95,"cacheReadInputPer1kTokens":0.0000325,"prompt_per_million":0.325,"completion_per_million":1.95,"prompt_per_token":"0.000000325","completion_per_token":"0.00000195","per_input_token":3.25e-7,"per_output_token":0.00000195},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000325,"outputPer1kTokens":0.00195,"cacheReadInputPer1kTokens":0.0000325,"cacheReadInputPer1kTokensAbove200k":0.00013,"cacheWriteInputPer1kTokens":0.00040625,"cacheWriteInputPer1kTokensAbove200k":0.001625},"effective_price":{"inputPer1kTokens":0.000325,"outputPer1kTokens":0.00195,"cacheReadInputPer1kTokens":0.0000325,"cacheReadInputPer1kTokensAbove200k":0.00013,"cacheWriteInputPer1kTokens":0.00040625,"cacheWriteInputPer1kTokensAbove200k":0.001625},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":412.1},"qwen-long":{"name":"Qwen Long 10M","model":"qwen/qwen-long","description":"Alibaba's huge context window model. Takes in up to 10 million tokens, which is equivalent to dozens of books.","cost":"Average cost: $0.0020","costEstimate":0.002,"dateAdded":"2024-08-01","category":"More","provider":"qwen","visible":true,"toolCallingUnsupported":true,"capabilities":["pdf-upload"],"maxInputTokens":10000000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.003e-7,"output_price":4.08e-7,"input_price_per_million":0.1003,"output_price_per_million":0.408,"input":0.1003,"output":0.408,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001003","completion":"0.000000408","input":0.1003,"output":0.408,"prompt_per_million":0.1003,"completion_per_million":0.408,"prompt_per_token":"0.0000001003","completion_per_token":"0.000000408","per_input_token":1.003e-7,"per_output_token":4.08e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.000408},"effective_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.000408},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"}},"Qwen/Qwen2.5-Coder-32B-Instruct":{"totalParams":32,"name":"Qwen 2.5 Coder 32b","model":"qwen/qwen2.5-coder-32b-instruct","description":"The latest series of Code-Specific Qwen large language models.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"qwen","visible":true,"dateAdded":"2025-07-03","isOpenSource":true,"maxInputTokens":32000,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.006e-7,"output_price":2.006e-7,"input_price_per_million":0.2006,"output_price_per_million":0.2006,"input":0.2006,"output":0.2006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002006","completion":"0.0000002006","input":0.2006,"output":0.2006,"prompt_per_million":0.2006,"completion_per_million":0.2006,"prompt_per_token":"0.0000002006","completion_per_token":"0.0000002006","per_input_token":2.006e-7,"per_output_token":2.006e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"effective_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":194.7},"phi-4-multimodal-instruct":{"totalParams":5.6,"name":"Phi 4 Multimodal","model":"phi-4-multimodal-instruct","description":"Phi 4 by Microsoft. A small multimodal model that can handle images and text.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"microsoft","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-8,"output_price":1.1e-7,"input_price_per_million":0.07,"output_price_per_million":0.11,"input":0.07,"output":0.11,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000007","completion":"0.00000011","input":0.07,"output":0.11,"prompt_per_million":0.07,"completion_per_million":0.11,"prompt_per_token":"0.00000007","completion_per_token":"0.00000011","per_input_token":7e-8,"per_output_token":1.1e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000069999999,"outputPer1kTokens":0.000109999996},"effective_price":{"inputPer1kTokens":0.000069999999,"outputPer1kTokens":0.000109999996},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"}},"phi-4-mini-instruct":{"totalParams":3.8,"name":"Phi 4 Mini","model":"phi-4-mini-instruct","description":"Phi 4 Mini by Microsoft. A small multilingual model.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"microsoft","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.7e-7,"output_price":6.8e-7,"input_price_per_million":0.17,"output_price_per_million":0.68,"input":0.17,"output":0.68,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000017","completion":"0.00000068","input":0.17,"output":0.68,"prompt_per_million":0.17,"completion_per_million":0.68,"prompt_per_token":"0.00000017","completion_per_token":"0.00000068","per_input_token":1.7e-7,"per_output_token":6.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00068},"effective_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00068},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":24},"amazon/nova-lite-v1":{"name":"Amazon Nova Lite 1.0","model":"amazon/nova-lite-v1","description":"Amazon's new lower cost model. Can handle up to 300k input tokens, with faster output but less thorough understanding than Amazon's Nova Pro.","cost":"Average cost: $0.0011","costEstimate":0.0011,"dateAdded":"2024-12-03","provider":"amazon","visible":true,"isOpenSource":false,"maxInputTokens":300000,"maxOutputTokens":5120,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5.95e-8,"output_price":2.38e-7,"input_price_per_million":0.0595,"output_price_per_million":0.238,"input":0.0595,"output":0.238,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000000595","completion":"0.000000238","input":0.0595,"output":0.238,"prompt_per_million":0.0595,"completion_per_million":0.238,"prompt_per_token":"0.0000000595","completion_per_token":"0.000000238","per_input_token":5.95e-8,"per_output_token":2.38e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000595,"outputPer1kTokens":0.000238},"effective_price":{"inputPer1kTokens":0.0000595,"outputPer1kTokens":0.000238},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":43.9},"amazon/nova-2-lite-v1":{"name":"Amazon Nova 2 Lite","model":"amazon/nova-2-lite-v1","description":"A fast, cost-effective reasoning model with 1M token context. Supports extended thinking with adjustable depth levels and built-in web grounding and code interpreter tools.","cost":"Average cost: $0.0028","costEstimate":0.0028,"provider":"amazon","visible":true,"isOpenSource":false,"maxInputTokens":1000000,"maxOutputTokens":65535,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5.1e-7,"output_price":0.00000425,"input_price_per_million":0.51,"output_price_per_million":4.25,"input":0.51,"output":4.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000051","completion":"0.00000425","input":0.51,"output":4.25,"prompt_per_million":0.51,"completion_per_million":4.25,"prompt_per_token":"0.00000051","completion_per_token":"0.00000425","per_input_token":5.1e-7,"per_output_token":0.00000425},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00051,"outputPer1kTokens":0.00425},"effective_price":{"inputPer1kTokens":0.00051,"outputPer1kTokens":0.00425},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"}},"TheDrummer/Cydonia-24B-v2":{"totalParams":24,"name":"The Drummer Cydonia 24B v2","model":"TheDrummer/Cydonia-24B-v2","description":"Cydonia 24B v2 is a finetune of Mistral's latest 'Small' model (2501). Aliases: Cydonia 24B, Cydonia v2, Cydonia on that broken base.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"mistral","visible":true,"dateAdded":"2025-02-17","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.003e-7,"output_price":1.207e-7,"input_price_per_million":0.1003,"output_price_per_million":0.1207,"input":0.1003,"output":0.1207,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001003","completion":"0.0000001207","input":0.1003,"output":0.1207,"prompt_per_million":0.1003,"completion_per_million":0.1207,"prompt_per_token":"0.0000001003","completion_per_token":"0.0000001207","per_input_token":1.003e-7,"per_output_token":1.207e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001207},"effective_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001207},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.382Z"},"avgOutputTokens":230.1},"TheDrummer/Cydonia-24B-v4":{"totalParams":24,"name":"The Drummer Cydonia 24B v4","model":"TheDrummer/Cydonia-24B-v4","description":"Cydonia 24B v4 is the latest iteration of TheDrummer's Cydonia series, a finetune of Mistral Small.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"mistral","isOpenSource":true,"visible":true,"dateAdded":"2025-07-22","maxInputTokens":16384,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.006e-7,"output_price":2.414e-7,"input_price_per_million":0.2006,"output_price_per_million":0.2414,"input":0.2006,"output":0.2414,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002006","completion":"0.0000002414","input":0.2006,"output":0.2414,"prompt_per_million":0.2006,"completion_per_million":0.2414,"prompt_per_token":"0.0000002006","completion_per_token":"0.0000002414","per_input_token":2.006e-7,"per_output_token":2.414e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002414},"effective_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002414},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":534.7},"TheDrummer/Cydonia-24B-v4.1":{"totalParams":24,"name":"The Drummer Cydonia 24B v4.1","model":"TheDrummer/Cydonia-24B-v4.1","description":"Cydonia 24B v4.1 is the newest release of TheDrummer's Cydonia series, featuring improved performance and refined capabilities.","cost":"Input $0.35/m, Cached input $0.16/m, Output $0.55/m","costEstimate":0.004875,"provider":"mistral","isOpenSource":true,"visible":true,"dateAdded":"2025-08-19","maxInputTokens":131072,"maxOutputTokens":131072,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.5e-7,"output_price":5.5e-7,"input_price_per_million":0.35,"output_price_per_million":0.55,"input":0.35,"output":0.55,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000035","completion":"0.00000055","input":0.35,"output":0.55,"cacheReadInputPer1kTokens":0.00016,"prompt_per_million":0.35,"completion_per_million":0.55,"prompt_per_token":"0.00000035","completion_per_token":"0.00000055","per_input_token":3.5e-7,"per_output_token":5.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.00055,"cacheReadInputPer1kTokens":0.00016},"effective_price":{"inputPer1kTokens":0.00035,"outputPer1kTokens":0.00055,"cacheReadInputPer1kTokens":0.00016},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":307.1},"TheDrummer/Cydonia-24B-v4.3":{"totalParams":24,"name":"The Drummer Cydonia 24B v4.3","model":"TheDrummer/Cydonia-24B-v4.3","description":"Cydonia 24B v4.3 continues TheDrummer's Cydonia series with updated tuning on Mistral Small and a 128K context window.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"mistral","isOpenSource":true,"visible":true,"dateAdded":"2025-12-25","maxInputTokens":131072,"maxOutputTokens":131072,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.2e-7,"output_price":1.5e-7,"input_price_per_million":0.12,"output_price_per_million":0.15,"input":0.12,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000015","input":0.12,"output":0.15,"prompt_per_million":0.12,"completion_per_million":0.15,"prompt_per_token":"0.00000012","completion_per_token":"0.00000015","per_input_token":1.2e-7,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":230.7},"TheDrummer/Magidonia-24B-v4.3":{"totalParams":24,"name":"The Drummer Magidonia 24B v4.3","model":"TheDrummer/Magidonia-24B-v4.3","description":"Magidonia 24B v4.3 is a new 24B Drummer finetune built for rich, creative roleplay.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"mistral","isOpenSource":true,"visible":true,"dateAdded":"2025-12-25","maxInputTokens":32768,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.003e-7,"output_price":1.207e-7,"input_price_per_million":0.1003,"output_price_per_million":0.1207,"input":0.1003,"output":0.1207,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001003","completion":"0.0000001207","input":0.1003,"output":0.1207,"prompt_per_million":0.1003,"completion_per_million":0.1207,"prompt_per_token":"0.0000001003","completion_per_token":"0.0000001207","per_input_token":1.003e-7,"per_output_token":1.207e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001207},"effective_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001207},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":398.6},"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond":{"totalParams":24,"name":"MS3.2 24B Magnum Diamond","model":"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond","description":"rsLoRA finetune of a text-only conversion of Mistral Small 3.2 24B Instruct (2506), built to bring the Magnum mix's Claude-like prose to a smaller footprint. The \"Diamond\" moniker nods to the extra heat and pressure - pre-tokenization plus custom loss masking - to turn the assistant-tuned base into creative-writing gems, with or without character names or prefill.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"mistral","isOpenSource":true,"visible":true,"dateAdded":"2025-11-24","maxInputTokens":16384,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":96.7},"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0":{"totalParams":24,"name":"Omega Directive 24B Unslop v2.0","model":"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0","description":"ReadyArt's MS3.2 Omega Directive 24B unslopped mix tuned for rich roleplay and storytelling.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"mistral","isOpenSource":true,"visible":true,"dateAdded":"2025-12-08","maxInputTokens":16384,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":5e-7,"input_price_per_million":0.5,"output_price_per_million":0.5,"input":0.5,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000005","input":0.5,"output":0.5,"prompt_per_million":0.5,"completion_per_million":0.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000005","per_input_token":5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":1347},"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0":{"totalParams":70,"name":"EVA Llama 3.33 70B","model":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0","description":"A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.","cost":"Average cost: $0.0033","costEstimate":0.0033,"provider":"meta","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002006,"output_price":0.000002006,"input_price_per_million":2.006,"output_price_per_million":2.006,"input":2.006,"output":2.006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002006","completion":"0.000002006","input":2.006,"output":2.006,"prompt_per_million":2.006,"completion_per_million":2.006,"prompt_per_token":"0.000002006","completion_per_token":"0.000002006","per_input_token":0.000002006,"per_output_token":0.000002006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002006},"effective_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":320.6},"Steelskull/L3.3-MS-Nevoria-70b":{"totalParams":70,"name":"Steelskull Nevoria 70b","model":"Steelskull/L3.3-MS-Nevoria-70b","description":"Steelskull Nevoria 70b","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"meta","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"Steelskull/L3.3-Nevoria-R1-70b":{"totalParams":70,"name":"Steelskull Nevoria R1 70b","model":"Steelskull/L3.3-Nevoria-R1-70b","description":"Steelskull Nevoria R1 70b","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"meta","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"Steelskull/L3.3-Electra-R1-70b":{"totalParams":70,"name":"Steelskull Electra R1 70b","model":"Steelskull/L3.3-Electra-R1-70b","description":"Steelskull Electra R1 70b","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"meta","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6.9989e-7,"output_price":6.9989e-7,"input_price_per_million":0.69989,"output_price_per_million":0.69989,"input":0.69989,"output":0.69989,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000069989","completion":"0.00000069989","input":0.69989,"output":0.69989,"prompt_per_million":0.69989,"completion_per_million":0.69989,"prompt_per_token":"0.00000069989","completion_per_token":"0.00000069989","per_input_token":6.9989e-7,"per_output_token":6.9989e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00069989,"outputPer1kTokens":0.00069989},"effective_price":{"inputPer1kTokens":0.00069989,"outputPer1kTokens":0.00069989},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"abacusai/Dracarys-72B-Instruct":{"totalParams":72,"name":"Qwen2 72B Dracarys","model":"abacusai/Dracarys-72B-Instruct","description":"A Qwen2 72B Instruct finetune by Abacus.AI focused on improving coding performance.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"qwen","visible":true,"dateAdded":"2025-08-02","isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":138.1},"mistralai/mistral-large":{"totalParams":123,"name":"Mistral Large 2411","model":"mistralai/mistral-large","description":"Upgrade to Mistral's flagship model. It is fluent in English, French, Spanish, German, and Italian, with high grammatical accuracy, with a long context window.","cost":"Average cost: $0.0032","costEstimate":0.0032,"provider":"mistral","visible":true,"isOpenSource":false,"maxInputTokens":128000,"maxOutputTokens":256000,"category":"More","labelVariant":"outline","preferredProviders":["Mistral"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002006,"output_price":0.000006001,"input_price_per_million":2.006,"output_price_per_million":6.001,"input":2.006,"output":6.001,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002006","completion":"0.000006001","input":2.006,"output":6.001,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2.006,"completion_per_million":6.001,"prompt_per_token":"0.000002006","completion_per_token":"0.000006001","per_input_token":0.000002006,"per_output_token":0.000006001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.006001,"cacheReadInputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.006001,"cacheReadInputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":955.4},"NeverSleep/Lumimaid-v0.2-70B":{"totalParams":70,"name":"Lumimaid v0.2","model":"NeverSleep/Lumimaid-v0.2-70B","description":"Upgrade to Llama-3 Lumimaid 70B. A Llama 3.1 70B finetune trained on curated roleplay data.","cost":"Average cost: $0.0018","costEstimate":0.0018,"provider":"neversleep","visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.0000015,"input_price_per_million":1,"output_price_per_million":1.5,"input":1,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.0000015","input":1,"output":1.5,"prompt_per_million":1,"completion_per_million":1.5,"prompt_per_token":"0.000001","completion_per_token":"0.0000015","per_input_token":0.000001,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":179.6},"deepseek-chat-cheaper":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3/Chat Cheaper","usageName":"DeepSeek V3","model":"deepseek-chat-cheaper","description":"Cheaper version of Deepseek V3/Chat. Note: may be routed through Deepseek itself. Quantized at FP8.","cost":"Average cost: $0.0012","category":"More","costEstimate":0.0012,"provider":"deepseek","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"capabilities":["pdf-upload","tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4.25e-7,"input_price_per_million":0.1,"output_price_per_million":0.425,"input":0.1,"output":0.425,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.000000425","input":0.1,"output":0.425,"prompt_per_million":0.1,"completion_per_million":0.425,"prompt_per_token":"0.0000001","completion_per_token":"0.000000425","per_input_token":1e-7,"per_output_token":4.25e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.000425},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.000425},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":597.2},"microsoft/wizardlm-2-8x22b":{"totalParams":141,"activeParams":39,"name":"WizardLM-2 8x22B","model":"microsoft/wizardlm-2-8x22b","description":"Microsoft's advanced Wizard model. The most popular role-playing model.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"microsoft","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"labelVariant":"outline","labelColor":"orange.4","preferredProviders":["DeepInfra"],"capabilities":["pdf-upload"],"maxInputTokens":65536,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"huihui-ai/Llama-3.3-70B-Instruct-abliterated":{"totalParams":70,"name":"Llama 3.3 70B Instruct abliterated","model":"huihui-ai/Llama-3.3-70B-Instruct-abliterated","description":"An abliterated (removed restrictions and censorship) version of Llama 3.3 70b.","cost":"Average cost: $0.0011","provider":"meta","costEstimate":0.0011,"visible":true,"dateAdded":"2025-08-08","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Uncensored","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":128.6},"google/gemini-flash-1.5":{"name":"Gemini 1.5 Flash","model":"google/gemini-flash-1.5","description":"Deprecated — Google's Gemini 1.5 Flash is no longer available. This model has been sunset by the upstream provider.","cost":"Average cost: $0.0010","provider":"gemini","costEstimate":0.001,"visible":true,"disabled":true,"maxInputTokens":2000000,"maxOutputTokens":8192,"fallbackModel":"google/gemini-flash-1.5-exp","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.48e-8,"output_price":3.06e-7,"input_price_per_million":0.0748,"output_price_per_million":0.306,"input":0.0748,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000000748","completion":"0.000000306","input":0.0748,"output":0.306,"cacheReadInputPer1kTokens":0.0000374,"prompt_per_million":0.0748,"completion_per_million":0.306,"prompt_per_token":"0.0000000748","completion_per_token":"0.000000306","per_input_token":7.48e-8,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000748,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.0000374},"effective_price":{"inputPer1kTokens":0.0000748,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.0000374},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"Gryphe/MythoMax-L2-13b":{"totalParams":13,"name":"MythoMax 13B","model":"Gryphe/MythoMax-L2-13b","description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"other","visible":true,"dateAdded":"2025-08-08","isOpenSource":true,"category":"Roleplay/storytelling models","maxInputTokens":4000,"maxOutputTokens":4096,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.003e-7,"output_price":1.003e-7,"input_price_per_million":0.1003,"output_price_per_million":0.1003,"input":0.1003,"output":0.1003,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001003","completion":"0.0000001003","input":0.1003,"output":0.1003,"prompt_per_million":0.1003,"completion_per_million":0.1003,"prompt_per_token":"0.0000001003","completion_per_token":"0.0000001003","per_input_token":1.003e-7,"per_output_token":1.003e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001003},"effective_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":99.2},"glm-4-long":{"name":"GLM-4 Long","model":"glm-4-long","description":"Extended context model supporting up to 1M tokens","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"zhipu","visible":true,"maxInputTokens":1000000,"maxOutputTokens":4095,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.006e-7,"output_price":2.006e-7,"input_price_per_million":0.2006,"output_price_per_million":0.2006,"input":0.2006,"output":0.2006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002006","completion":"0.0000002006","input":0.2006,"output":0.2006,"prompt_per_million":0.2006,"completion_per_million":0.2006,"prompt_per_token":"0.0000002006","completion_per_token":"0.0000002006","per_input_token":2.006e-7,"per_output_token":2.006e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"effective_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":252.1},"qwen/qwen-2.5-72b-instruct":{"totalParams":72,"name":"Qwen2.5 72B","model":"qwen/qwen-2.5-72b-instruct","description":"Great multilingual support, strong at mathematics and coding, supports roleplay and chatbots.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"qwen","visible":true,"dateAdded":"2025-07-03","isOpenSource":true,"maxInputTokens":131072,"maxOutputTokens":8192,"preferredProviders":["DeepInfra","Novita"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.57e-7,"output_price":4.08e-7,"input_price_per_million":0.357,"output_price_per_million":0.408,"input":0.357,"output":0.408,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000357","completion":"0.000000408","input":0.357,"output":0.408,"prompt_per_million":0.357,"completion_per_million":0.408,"prompt_per_token":"0.000000357","completion_per_token":"0.000000408","per_input_token":3.57e-7,"per_output_token":4.08e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000357,"outputPer1kTokens":0.000408},"effective_price":{"inputPer1kTokens":0.000357,"outputPer1kTokens":0.000408},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":165.7},"free-model":{"name":"Free model","model":"free-model","description":"Free model to try our service with. Note: this model has limited maximum input and is generally not a top model.","cost":"Average cost: $0.0000","costEstimate":0,"provider":"nanogpt","visible":true,"maxInputTokens":8000,"maxOutputTokens":4096,"label":"Free","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":505.7},"anthracite-org/magnum-v4-72b":{"totalParams":72,"name":"Magnum v4 72B","model":"anthracite-org/magnum-v4-72b","description":"Upgraded model of Magnum V2 72B. From the creators of Goliath. Aimed at top-tier prose quality, trained on 55 million tokens of curated roleplay data.","cost":"Average cost: $0.0030","costEstimate":0.003,"provider":"other","isOpenSource":true,"visible":true,"capabilities":["pdf-upload"],"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002006,"output_price":0.000002992,"input_price_per_million":2.006,"output_price_per_million":2.992,"input":2.006,"output":2.992,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002006","completion":"0.000002992","input":2.006,"output":2.992,"prompt_per_million":2.006,"completion_per_million":2.992,"prompt_per_token":"0.000002006","completion_per_token":"0.000002992","per_input_token":0.000002006,"per_output_token":0.000002992},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002992},"effective_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002992},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":111.3},"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2":{"totalParams":32,"name":"EVA-Qwen2.5-32B-v0.2","model":"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2","description":"A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.","cost":"Average cost: $0.0018","costEstimate":0.0018,"provider":"other","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.99e-7,"output_price":7.99e-7,"input_price_per_million":0.799,"output_price_per_million":0.799,"input":0.799,"output":0.799,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000799","completion":"0.000000799","input":0.799,"output":0.799,"prompt_per_million":0.799,"completion_per_million":0.799,"prompt_per_token":"0.000000799","completion_per_token":"0.000000799","per_input_token":7.99e-7,"per_output_token":7.99e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.000799},"effective_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.000799},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":237.9},"mistralai/ministral-3b-2512":{"totalParams":3,"name":"Ministral 3B","visible":true,"model":"mistralai/ministral-3b-2512","description":"Ministral 3B is a tiny, efficient 3B parameter model from Mistral AI with vision capabilities, designed for edge deployment.","cost":"Average cost: $0.0002","costEstimate":0.0002,"provider":"mistral","category":"More","dateAdded":"2025-12-04","isOpenSource":true,"maxInputTokens":131072,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":1e-7,"input_price_per_million":0.1,"output_price_per_million":0.1,"input":0.1,"output":0.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000001","input":0.1,"output":0.1,"prompt_per_million":0.1,"completion_per_million":0.1,"prompt_per_token":"0.0000001","completion_per_token":"0.0000001","per_input_token":1e-7,"per_output_token":1e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":53.6},"mistralai/ministral-8b-2512":{"totalParams":8,"name":"Ministral 8B","visible":true,"model":"mistralai/ministral-8b-2512","description":"Ministral 8B is an efficient 8B parameter model from Mistral AI with vision capabilities, designed for edge deployment.","cost":"Average cost: $0.0003","costEstimate":0.0003,"provider":"mistral","category":"More","dateAdded":"2025-12-04","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":1.5e-7,"input_price_per_million":0.15,"output_price_per_million":0.15,"input":0.15,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000015","input":0.15,"output":0.15,"prompt_per_million":0.15,"completion_per_million":0.15,"prompt_per_token":"0.00000015","completion_per_token":"0.00000015","per_input_token":1.5e-7,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":39.9},"mistralai/ministral-14b-2512":{"totalParams":14,"name":"Ministral 14B","visible":true,"model":"mistralai/ministral-14b-2512","description":"Ministral 14B is a powerful 14B parameter model from Mistral AI with vision capabilities, offering frontier performance in a compact size.","cost":"Average cost: $0.0004","costEstimate":0.0004,"provider":"mistral","category":"More","dateAdded":"2025-12-04","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":2e-7,"input_price_per_million":0.2,"output_price_per_million":0.2,"input":0.2,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000002","input":0.2,"output":0.2,"prompt_per_million":0.2,"completion_per_million":0.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000002","per_input_token":2e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":175.6},"thedrummer/skyfall-36b-v2":{"totalParams":36,"name":"TheDrummer Skyfall 36B V2","model":"thedrummer/skyfall-36b-v2","description":"TheDrummer's Skyfall 36B V2, a 36B parameter model with a focus on high quality and consistency.","cost":"Input $0.55/m, Cached input $0.25/m, Output $0.80/m","costEstimate":0.0008,"provider":"mistral","visible":true,"dateAdded":"2025-03-10","capabilities":["vision-by-description","pdf-upload"],"toolCallingUnsupported":true,"category":"Roleplay/storytelling models","isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5.5e-7,"output_price":8e-7,"input_price_per_million":0.55,"output_price_per_million":0.8,"input":0.55,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000055","completion":"0.0000008","input":0.55,"output":0.8,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":0.55,"completion_per_million":0.8,"prompt_per_token":"0.00000055","completion_per_token":"0.0000008","per_input_token":5.5e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00055,"outputPer1kTokens":0.0008,"cacheReadInputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.00055,"outputPer1kTokens":0.0008,"cacheReadInputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":179.2},"Qwen/Qwen3-8B":{"totalParams":8,"name":"Qwen 3 8B","model":"qwen/qwen3-8b","description":"Qwen 3 8B is a 8B model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"qwen","visible":true,"capabilities":["vision-by-description"],"isOpenSource":true,"maxInputTokens":41000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.7e-7,"output_price":4.7e-7,"input_price_per_million":0.47,"output_price_per_million":0.47,"input":0.47,"output":0.47,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000047","completion":"0.00000047","input":0.47,"output":0.47,"prompt_per_million":0.47,"completion_per_million":0.47,"prompt_per_token":"0.00000047","completion_per_token":"0.00000047","per_input_token":4.7e-7,"per_output_token":4.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00047,"outputPer1kTokens":0.00047},"effective_price":{"inputPer1kTokens":0.00047,"outputPer1kTokens":0.00047},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"LLM360/K2-Think":{"totalParams":32,"name":"K2-Think","model":"LLM360/K2-Think","description":"K2-Think is a 32B open-weights general reasoning model with strong competitive math performance. Benchmarks: AIME 2024 90.83, AIME 2025 81.24, GPQA-Diamond 71.08, LiveCodeBench v5 63.97.","cost":"Average cost: $0.0004","costEstimate":0.0004,"provider":"k2","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.7e-7,"output_price":6.8e-7,"input_price_per_million":0.17,"output_price_per_million":0.68,"input":0.17,"output":0.68,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000017","completion":"0.00000068","input":0.17,"output":0.68,"prompt_per_million":0.17,"completion_per_million":0.68,"prompt_per_token":"0.00000017","completion_per_token":"0.00000068","per_input_token":1.7e-7,"per_output_token":6.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00068},"effective_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00068},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"}},"deepseek-ai/DeepSeek-V3.1":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3.1","model":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. This is the non-thinking version. Quantized at FP8.","cost":"Average cost: $0.0007","costEstimate":0.0007,"provider":"deepseek","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"capabilities":["pdf-upload"],"maxInputTokens":128000,"maxOutputTokens":65536,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":7e-7,"input_price_per_million":0.2,"output_price_per_million":0.7,"input":0.2,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000007","input":0.2,"output":0.7,"prompt_per_million":0.2,"completion_per_million":0.7,"prompt_per_token":"0.0000002","completion_per_token":"0.0000007","per_input_token":2e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":292.8},"deepseek-ai/DeepSeek-V3.1:thinking":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3.1 Thinking","model":"deepseek-ai/DeepSeek-V3.1:thinking","description":"Thinking enabled version of Deepseek V3.1. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. Quantized at FP8.","cost":"Average cost: $0.0007","costEstimate":0.0007,"provider":"deepseek","visible":true,"category":"More","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":7e-7,"input_price_per_million":0.2,"output_price_per_million":0.7,"input":0.2,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000007","input":0.2,"output":0.7,"prompt_per_million":0.2,"completion_per_million":0.7,"prompt_per_token":"0.0000002","completion_per_token":"0.0000007","per_input_token":2e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":483.4},"deepseek-ai/DeepSeek-V3.1-Terminus":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3.1 Terminus","model":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek-V3.1-Terminus. The latest update builds on V3.1's strengths while addressing key user feedback. Language consistency improvements (fewer CN/EN mix-ups, no random chars), stronger Code Agent & Search Agent performance, and more stable, reliable outputs across benchmarks. FP8.","cost":"Average cost: $0.0007","category":"More","costEstimate":0.0007,"provider":"deepseek","visible":true,"dateAdded":"2025-08-02","isOpenSource":true,"capabilities":["tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":7e-7,"input_price_per_million":0.25,"output_price_per_million":0.7,"input":0.25,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000007","input":0.25,"output":0.7,"prompt_per_million":0.25,"completion_per_million":0.7,"prompt_per_token":"0.00000025","completion_per_token":"0.0000007","per_input_token":2.5e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":364.1},"deepseek-ai/DeepSeek-V3.1-Terminus:thinking":{"totalParams":671,"activeParams":37,"name":"DeepSeek V3.1 Terminus (Thinking)","model":"deepseek-ai/DeepSeek-V3.1-Terminus:thinking","description":"Thinking-enabled DeepSeek-V3.1-Terminus with improved language consistency, upgraded Code/Search Agents, and stronger stability and reliability versus V3.1. FP8.","cost":"Average cost: $0.0007","costEstimate":0.0007,"provider":"deepseek","category":"More","visible":true,"isOpenSource":true,"capabilities":["tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":7e-7,"input_price_per_million":0.25,"output_price_per_million":0.7,"input":0.25,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000007","input":0.25,"output":0.7,"prompt_per_million":0.25,"completion_per_million":0.7,"prompt_per_token":"0.00000025","completion_per_token":"0.0000007","per_input_token":2.5e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.383Z"},"avgOutputTokens":362},"deepseek-v3-0324":{"totalParams":671,"activeParams":37,"name":"DeepSeek Chat 0324","model":"deepseek-v3-0324","description":"DeepSeek V3 0324, DeepSeek's 03 March 2025 V3 model, optimized for general-purpose tasks. Quantized at FP8.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"deepseek","visible":true,"isOpenSource":true,"category":"More","labelVariant":"outline","capabilities":["tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":8192,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":7.7e-7,"input_price_per_million":0.2,"output_price_per_million":0.77,"input":0.2,"output":0.77,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.00000077","input":0.2,"output":0.77,"cacheReadInputPer1kTokens":0.000135,"prompt_per_million":0.2,"completion_per_million":0.77,"prompt_per_token":"0.0000002","completion_per_token":"0.00000077","per_input_token":2e-7,"per_output_token":7.7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00077,"cacheReadInputPer1kTokens":0.000135},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00077,"cacheReadInputPer1kTokens":0.000135},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":280},"baseten/Kimi-K2-Instruct-FP4":{"totalParams":1000,"activeParams":32,"name":"Kimi K2 0711 Instruct FP4","model":"baseten/Kimi-K2-Instruct-FP4","description":"Deprecated. This model now routes to Kimi K2 0711.","cost":"Average cost: $0.006","costEstimate":0.006,"category":"More","provider":"moonshot","visible":true,"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":131072,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000018,"input_price_per_million":0.4,"output_price_per_million":1.8,"input":0.4,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000018","input":0.4,"output":1.8,"prompt_per_million":0.4,"completion_per_million":1.8,"prompt_per_token":"0.0000004","completion_per_token":"0.0000018","per_input_token":4e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"}},"z-ai/GLM-4.5:thinking":{"totalParams":355,"activeParams":32,"name":"GLM 4.5 (Thinking)","model":"z-ai/GLM-4.5:thinking","description":"GLM-4.5 with thinking mode for enhanced reasoning; provides chain-of-thought style internal reasoning with a 128k context window.","cost":"Average cost: $0.0015","costEstimate":0.0015,"category":"More","provider":"zhipu","visible":true,"capabilities":["reasoning"],"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000013,"input_price_per_million":0.3,"output_price_per_million":1.3,"input":0.3,"output":1.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000013","input":0.3,"output":1.3,"prompt_per_million":0.3,"completion_per_million":1.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000013","per_input_token":3e-7,"per_output_token":0.0000013},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0013},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":1035.8},"z-ai/glm-4.5":{"totalParams":355,"activeParams":32,"name":"GLM 4.5","model":"z-ai/glm-4.5","description":"GLM-4.5 is a Mixture-of-Experts model built for agent-based applications, with 355B total / 32B active parameters and up to 128k context. It supports reasoning, code generation, and agent workflows.","cost":"Average cost: $0.0015","costEstimate":0.0015,"category":"More","provider":"zhipu","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000013,"input_price_per_million":0.3,"output_price_per_million":1.3,"input":0.3,"output":1.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000013","input":0.3,"output":1.3,"prompt_per_million":0.3,"completion_per_million":1.3,"prompt_per_token":"0.0000003","completion_per_token":"0.0000013","per_input_token":3e-7,"per_output_token":0.0000013},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0013},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":695.8},"z-ai/GLM-4.5-Air":{"totalParams":106,"activeParams":12,"name":"GLM 4.5 Air","model":"z-ai/GLM-4.5-Air","description":"GLM-4.5-Air is a 106B total / 12B active parameter model designed to unify frontier reasoning, coding, and agentic capabilities. On the SWE-bench Verified benchmark, it delivers the best performance at its scale with a competitive performance-to-cost ratio.","cost":"Average cost: $0.0011","costEstimate":0.0011,"category":"More","provider":"zhipu","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"capabilities":["tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":98304,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.2e-7,"output_price":8e-7,"input_price_per_million":0.12,"output_price_per_million":0.8,"input":0.12,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.0000008","input":0.12,"output":0.8,"prompt_per_million":0.12,"completion_per_million":0.8,"prompt_per_token":"0.00000012","completion_per_token":"0.0000008","per_input_token":1.2e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.0008},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.0008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":58.9},"z-ai/GLM-4.6-turbo":{"totalParams":357,"activeParams":32,"name":"GLM 4.6 Turbo","model":"z-ai/GLM-4.6-turbo","description":"Fast variant of GLM 4.6 for general chat, coding, and analysis with improved latency and strong reasoning.","cost":"Average cost: $0.0020","costEstimate":0.002,"category":"More","provider":"zhipu","visible":true,"dateAdded":"2025-10-02","isOpenSource":true,"maxInputTokens":200000,"maxOutputTokens":204800,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000003,"input_price_per_million":1,"output_price_per_million":3,"input":1,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000003","input":1,"output":3,"prompt_per_million":1,"completion_per_million":3,"prompt_per_token":"0.000001","completion_per_token":"0.000003","per_input_token":0.000001,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":695.5},"z-ai/GLM-4.6-turbo:thinking":{"totalParams":357,"activeParams":32,"name":"GLM 4.6 Turbo (Thinking)","model":"z-ai/GLM-4.6-turbo:thinking","description":"GLM 4.6 Turbo with thinking mode enabled for enhanced reasoning; shows internal reasoning and supports long context.","cost":"Average cost: $0.0020","costEstimate":0.002,"category":"More","provider":"zhipu","visible":true,"capabilities":["reasoning"],"dateAdded":"2025-10-02","isOpenSource":true,"maxInputTokens":200000,"maxOutputTokens":204800,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000003,"input_price_per_million":1,"output_price_per_million":3,"input":1,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000003","input":1,"output":3,"prompt_per_million":1,"completion_per_million":3,"prompt_per_token":"0.000001","completion_per_token":"0.000003","per_input_token":0.000001,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":1898.6},"z-ai/GLM-4.5-Air:thinking":{"totalParams":106,"activeParams":12,"name":"GLM 4.5 Air (Thinking)","model":"z-ai/GLM-4.5-Air:thinking","description":"GLM-4.5-Air with thinking mode enabled for enhanced reasoning capabilities. Shows step-by-step thought process.","cost":"Average cost: $0.0011","costEstimate":0.0011,"category":"More","provider":"zhipu","visible":true,"capabilities":["reasoning","tool-calling","structured-output"],"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":98304,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.2e-7,"output_price":8e-7,"input_price_per_million":0.12,"output_price_per_million":0.8,"input":0.12,"output":0.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.0000008","input":0.12,"output":0.8,"prompt_per_million":0.12,"completion_per_million":0.8,"prompt_per_token":"0.00000012","completion_per_token":"0.0000008","per_input_token":1.2e-7,"per_output_token":8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.0008},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.0008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":973},"TEE/gpt-oss-120b":{"totalParams":120,"activeParams":5.1,"name":"GPT-OSS 120B TEE","model":"TEE/gpt-oss-120b","description":"Open-source GPT model with 120B parameters. running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0091","costEstimate":0.0091,"label":"TEE","provider":"openai","visible":true,"labelColor":"green","isOpenSource":true,"maxInputTokens":131072,"maxOutputTokens":16384,"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002,"output_price":0.000002,"input_price_per_million":2,"output_price_per_million":2,"input":2,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000002","input":2,"output":2,"cacheReadInputPer1kTokens":0.002,"prompt_per_million":2,"completion_per_million":2,"prompt_per_token":"0.000002","completion_per_token":"0.000002","per_input_token":0.000002,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.002},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.002,"cacheReadInputPer1kTokens":0.002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":174.1},"TEE/qwen2.5-vl-72b-instruct":{"totalParams":72,"name":"Qwen2.5 VL 72B TEE","model":"TEE/qwen2.5-vl-72b-instruct","description":"Qwen2.5 Vision-Language 72B model with multimodal capabilities. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0007","costEstimate":0.0007,"label":"TEE","provider":"qwen","visible":true,"labelColor":"green","isOpenSource":true,"capabilities":["vision"],"maxInputTokens":65536,"maxOutputTokens":8192,"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":83.9},"TEE/deepseek-v4.1-flash":{"name":"DeepSeek V4.1 Flash TEE","model":"TEE/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash's October 17, 2026 checkpoint (1017) supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This route runs through Tinfoil attested inference inside a Trusted Execution Environment. Tinfoil lists this model as experimental, with availability subject to change.","cost":"Input $0.65/m, Output $1.45/m, Cached input $0.13/m","costEstimate":0.00105,"label":"TEE","labelColor":"green","provider":"deepseek","visible":true,"isOpenSource":true,"maxInputTokens":1048576,"maxOutputTokens":384000,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls","structured-output"],"category":"Private/TEE","dateAdded":"2026-09-12","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","max"]}},"api":"chat","input_price":6.5e-7,"output_price":0.00000145,"input_price_per_million":0.65,"output_price_per_million":1.45,"input":0.65,"output":1.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000065","completion":"0.00000145","input":0.65,"output":1.45,"cacheReadInputPer1kTokens":0.00013,"prompt_per_million":0.65,"completion_per_million":1.45,"prompt_per_token":"0.00000065","completion_per_token":"0.00000145","per_input_token":6.5e-7,"per_output_token":0.00000145},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00065,"outputPer1kTokens":0.00145,"cacheReadInputPer1kTokens":0.00013},"effective_price":{"inputPer1kTokens":0.00065,"outputPer1kTokens":0.00145,"cacheReadInputPer1kTokens":0.00013},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":571.1},"TEE/deepseek-v3.2":{"totalParams":685,"activeParams":37,"name":"DeepSeek V3.2 TEE","model":"TEE/deepseek-v3.2","description":"DeepSeek V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.75","costEstimate":0.75,"label":"TEE","provider":"deepseek","visible":true,"labelColor":"green","isOpenSource":true,"maxInputTokens":164000,"maxOutputTokens":65536,"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.000001,"input_price_per_million":0.5,"output_price_per_million":1,"input":0.5,"output":1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.000001","input":0.5,"output":1,"prompt_per_million":0.5,"completion_per_million":1,"prompt_per_token":"0.0000005","completion_per_token":"0.000001","per_input_token":5e-7,"per_output_token":0.000001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.001},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":674.6},"TEE/qwen3.6-35b-a3b":{"totalParams":35,"activeParams":3,"name":"Qwen3.6 35B A3B TEE","model":"TEE/qwen3.6-35b-a3b","description":"Qwen3.6 35B A3B is an open-weight MoE model from Alibaba's Qwen team with 35B total parameters and 3B active parameters per token. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0007","costEstimate":0.00074,"label":"TEE","labelColor":"green","provider":"qwen","visible":true,"isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":262144,"category":"Private/TEE","dateAdded":"2026-06-09","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":0.00000127,"input_price_per_million":0.2,"output_price_per_million":1.27,"input":0.2,"output":1.27,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.00000127","input":0.2,"output":1.27,"prompt_per_million":0.2,"completion_per_million":1.27,"prompt_per_token":"0.0000002","completion_per_token":"0.00000127","per_input_token":2e-7,"per_output_token":0.00000127},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00127},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.00127},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":3906.2},"TEE/qwen3.5-27b":{"totalParams":27,"name":"Qwen3.5 27B TEE","model":"TEE/qwen3.5-27b","description":"Qwen3.5 27B is a native vision-language dense model optimized for fast responses while balancing quality and inference speed. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0014","costEstimate":0.00135,"label":"TEE","provider":"qwen","visible":true,"labelColor":"green","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-03-13","capabilities":["vision","video-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000024,"input_price_per_million":0.3,"output_price_per_million":2.4,"input":0.3,"output":2.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000024","input":0.3,"output":2.4,"prompt_per_million":0.3,"completion_per_million":2.4,"prompt_per_token":"0.0000003","completion_per_token":"0.0000024","per_input_token":3e-7,"per_output_token":0.0000024},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0024},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0024},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":1368.5},"TEE/qwen3.5-397b-a17b":{"totalParams":397,"activeParams":17,"name":"Qwen3.5 397B A17B TEE","model":"TEE/qwen3.5-397b-a17b","description":"Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0020","costEstimate":0.00203,"label":"TEE","provider":"qwen","visible":true,"labelColor":"green","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-02-28","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5.5e-7,"output_price":0.0000035,"input_price_per_million":0.55,"output_price_per_million":3.5,"input":0.55,"output":3.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000055","completion":"0.0000035","input":0.55,"output":3.5,"prompt_per_million":0.55,"completion_per_million":3.5,"prompt_per_token":"0.00000055","completion_per_token":"0.0000035","per_input_token":5.5e-7,"per_output_token":0.0000035},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00055,"outputPer1kTokens":0.0035},"effective_price":{"inputPer1kTokens":0.00055,"outputPer1kTokens":0.0035},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"}},"TEE/nemotron-3.5-lightning":{"totalParams":30,"activeParams":3,"name":"Nvidia Nemotron 3.5 Lightning TEE","model":"TEE/nemotron-3.5-lightning","description":"NVIDIA's open-weight 30B mixture-of-experts model with 3B active parameters for fast agentic workflows, coding, and tool use. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Input $0.08/m, Cached input $0.04/m, Output $0.20/m","costEstimate":0.0002,"label":"TEE","labelColor":"green","provider":"nvidia","visible":true,"isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-09-11","capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"tags":["chat","reasoning","coding","agents"],"api":"chat","input_price":8e-8,"output_price":2e-7,"input_price_per_million":0.08,"output_price_per_million":0.2,"input":0.08,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000008","completion":"0.0000002","input":0.08,"output":0.2,"cacheReadInputPer1kTokens":0.00004,"prompt_per_million":0.08,"completion_per_million":0.2,"prompt_per_token":"0.00000008","completion_per_token":"0.0000002","per_input_token":8e-8,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00008,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00004},"effective_price":{"inputPer1kTokens":0.00008,"outputPer1kTokens":0.0002,"cacheReadInputPer1kTokens":0.00004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"}},"TEE/gemma-4-31b-it":{"totalParams":31,"name":"Gemma 4 31B IT TEE","model":"TEE/gemma-4-31b-it","description":"Gemma 4 31B Instruct is a 30.7B dense model with a long context window, multilingual performance, function calling, and configurable reasoning. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0003","costEstimate":0.000305,"label":"TEE","labelColor":"green","provider":"google","visible":true,"isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":262144,"category":"Private/TEE","dateAdded":"2026-05-26","capabilities":["reasoning","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":4.6e-7,"input_price_per_million":0.15,"output_price_per_million":0.46,"input":0.15,"output":0.46,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000046","input":0.15,"output":0.46,"prompt_per_million":0.15,"completion_per_million":0.46,"prompt_per_token":"0.00000015","completion_per_token":"0.00000046","per_input_token":1.5e-7,"per_output_token":4.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00046},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00046},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":269.2},"TEE/gemma-4-26b-a4b-uncensored":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Uncensored TEE","model":"TEE/gemma-4-26b-a4b-uncensored","description":"Gemma 4 26B A4B Uncensored Heretic is an MoE model tuned to reduce refusal behavior while preserving coding, reasoning, and function-calling strengths. Running inside a TEE (Trusted Execution Environment), with provider attestation support. Image input is unavailable on this deployment.","cost":"Average cost: $0.0004","costEstimate":0.000425,"label":"TEE","labelColor":"green","provider":"google","visible":true,"isOpenSource":true,"maxInputTokens":65536,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-05-23","capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":7e-7,"input_price_per_million":0.15,"output_price_per_million":0.7,"input":0.15,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000007","input":0.15,"output":0.7,"prompt_per_million":0.15,"completion_per_million":0.7,"prompt_per_token":"0.00000015","completion_per_token":"0.0000007","per_input_token":1.5e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":454.1},"TEE/gemma4-31b":{"totalParams":31,"name":"Gemma 4 31B TEE","model":"TEE/gemma4-31b","description":"Google's Gemma 4 31B instruction-tuned model in a Trusted Execution Environment (TEE) with attestation support. This route keeps reasoning disabled for faster direct answers while preserving structured output support.","cost":"Average cost: $0.00027","costEstimate":0.00027,"label":"TEE","labelColor":"green","provider":"google","visible":true,"dateAdded":"2026-04-04","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":131072,"capabilities":["vision","structured-output"],"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.000001,"input_price_per_million":0.4,"output_price_per_million":1,"input":0.4,"output":1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.000001","input":0.4,"output":1,"cacheReadInputPer1kTokens":0.0004,"prompt_per_million":0.4,"completion_per_million":1,"prompt_per_token":"0.0000004","completion_per_token":"0.000001","per_input_token":4e-7,"per_output_token":0.000001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.001,"cacheReadInputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.001,"cacheReadInputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":538.2},"TEE/gemma4-31b:thinking":{"totalParams":31,"name":"Gemma 4 31B Thinking TEE","model":"TEE/gemma4-31b:thinking","description":"Google's Gemma 4 31B instruction-tuned model in a Trusted Execution Environment (TEE) with thinking explicitly enabled and provider attestation support.","cost":"Average cost: $0.00027","costEstimate":0.00027,"label":"TEE","labelColor":"green","provider":"google","visible":true,"dateAdded":"2026-05-02","isOpenSource":true,"maxInputTokens":262144,"maxOutputTokens":131072,"capabilities":["vision","reasoning","structured-output"],"tags":["Thinking"],"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.000001,"input_price_per_million":0.4,"output_price_per_million":1,"input":0.4,"output":1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.000001","input":0.4,"output":1,"cacheReadInputPer1kTokens":0.0004,"prompt_per_million":0.4,"completion_per_million":1,"prompt_per_token":"0.0000004","completion_per_token":"0.000001","per_input_token":4e-7,"per_output_token":0.000001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.001,"cacheReadInputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.001,"cacheReadInputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":1142},"TEE/llama3-3-70b":{"totalParams":70,"name":"Llama 3.3 70B","model":"TEE/llama3-3-70b","description":"Meta's Llama 3.3 with 70B parameters. TEE-backed inference with provider attestation support.","cost":"Average cost: $0.0036","costEstimate":0.0036,"label":"TEE","labelColor":"green","provider":"meta","visible":true,"dateAdded":"2025-07-03","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00000175,"output_price":0.00000275,"input_price_per_million":1.75,"output_price_per_million":2.75,"input":1.75,"output":2.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000175","completion":"0.00000275","input":1.75,"output":2.75,"cacheReadInputPer1kTokens":0.00175,"prompt_per_million":1.75,"completion_per_million":2.75,"prompt_per_token":"0.00000175","completion_per_token":"0.00000275","per_input_token":0.00000175,"per_output_token":0.00000275},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.00275,"cacheReadInputPer1kTokens":0.00175},"effective_price":{"inputPer1kTokens":0.00175,"outputPer1kTokens":0.00275,"cacheReadInputPer1kTokens":0.00175},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":338.8},"z-ai/GLM-5-NVFP4-TEE":{"totalParams":744,"activeParams":40,"name":"GLM 5 NVFP4 TEE","model":"z-ai/GLM-5-NVFP4-TEE","description":"GLM 5 (NVFP4-quantized) running through Chutes TEE with encrypted transport and provider evidence support.","cost":"Average cost: $0.00196","costEstimate":0.0019565,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"disabled":true,"isOpenSource":true,"maxInputTokens":202752,"maxOutputTokens":65535,"category":"Private/TEE","dateAdded":"2026-06-10","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.891e-7,"output_price":0.0000019565,"input_price_per_million":0.4891,"output_price_per_million":1.9565,"input":0.4891,"output":1.9565,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004891","completion":"0.0000019565","input":0.4891,"output":1.9565,"cacheReadInputPer1kTokens":0.00024455,"prompt_per_million":0.4891,"completion_per_million":1.9565,"prompt_per_token":"0.0000004891","completion_per_token":"0.0000019565","per_input_token":4.891e-7,"per_output_token":0.0000019565},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004891,"outputPer1kTokens":0.0019565,"cacheReadInputPer1kTokens":0.00024455},"effective_price":{"inputPer1kTokens":0.0004891,"outputPer1kTokens":0.0019565,"cacheReadInputPer1kTokens":0.00024455},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"}},"TEE/kimi-k3":{"totalParams":2800,"name":"Kimi K3 TEE","model":"TEE/kimi-k3","description":"Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image understanding. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Input $3.00/m, Output $15.00/m, Cached input $1.50/m","costEstimate":0.015,"label":"TEE","labelColor":"green","provider":"moonshot","visible":true,"isOpenSource":true,"dateAdded":"2026-07-31","maxInputTokens":1048576,"maxOutputTokens":1048576,"capabilities":["vision","reasoning","tool-calling","structured-output"],"category":"Private/TEE","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"tags":["chat","reasoning","vision","agent"],"api":"chat","input_price":0.000003,"output_price":0.000015,"input_price_per_million":3,"output_price_per_million":15,"input":3,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000015","input":3,"output":15,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":3,"completion_per_million":15,"prompt_per_token":"0.000003","completion_per_token":"0.000015","per_input_token":0.000003,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":1145.5},"GalrionSoftworks/MN-LooseCannon-12B-v1":{"totalParams":12,"name":"MN-LooseCannon-12B-v1","model":"GalrionSoftworks/MN-LooseCannon-12B-v1","description":"Merge of Starcannon and Sao Lyra.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"other","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":160.8},"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2":{"totalParams":72,"name":"EVA-Qwen2.5-72B-v0.2","model":"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2","description":"A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-72B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"other","visible":true,"dateAdded":"2025-09-25","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.99e-7,"output_price":7.99e-7,"input_price_per_million":0.799,"output_price_per_million":0.799,"input":0.799,"output":0.799,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000799","completion":"0.000000799","input":0.799,"output":0.799,"prompt_per_million":0.799,"completion_per_million":0.799,"prompt_per_token":"0.000000799","completion_per_token":"0.000000799","per_input_token":7.99e-7,"per_output_token":7.99e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.000799},"effective_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.000799},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":306.3},"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1":{"totalParams":70,"name":"EVA-LLaMA-3.33-70B-v0.1","model":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1","description":"A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.","cost":"Average cost: $0.0026","costEstimate":0.0026,"provider":"other","visible":true,"dateAdded":"2025-09-25","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","labelVariant":"outline","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002006,"output_price":0.000002006,"input_price_per_million":2.006,"output_price_per_million":2.006,"input":2.006,"output":2.006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002006","completion":"0.000002006","input":2.006,"output":2.006,"prompt_per_million":2.006,"completion_per_million":2.006,"prompt_per_token":"0.000002006","completion_per_token":"0.000002006","per_input_token":0.000002006,"per_output_token":0.000002006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002006},"effective_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":459.2},"meta-llama/llama-3.1-8b-instruct":{"totalParams":8,"name":"Llama 3.1 8b Instruct","model":"meta-llama/llama-3.1-8b-instruct","description":"Fast and efficient for simple purposes.","cost":"Average cost: $0.0010","provider":"meta","costEstimate":0.001,"visible":true,"isOpenSource":true,"maxInputTokens":131072,"maxOutputTokens":16384,"preferredProviders":["deepinfra/fp8","Novita"],"unsupportedResponseFormatTypes":["json_schema"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5.44e-8,"output_price":8.5e-8,"input_price_per_million":0.0544,"output_price_per_million":0.085,"input":0.0544,"output":0.085,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000000544","completion":"0.000000085","input":0.0544,"output":0.085,"prompt_per_million":0.0544,"completion_per_million":0.085,"prompt_per_token":"0.0000000544","completion_per_token":"0.000000085","per_input_token":5.44e-8,"per_output_token":8.5e-8},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000544,"outputPer1kTokens":0.000085},"effective_price":{"inputPer1kTokens":0.0000544,"outputPer1kTokens":0.000085},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":57},"undi95/remm-slerp-l2-13b":{"totalParams":13,"name":"ReMM SLERP 13B","provider":"other","model":"undi95/remm-slerp-l2-13b","description":"A recreation trial of the original MythoMax-L2-B13 but merged with updated models.","cost":"Average cost: $0.0013","costEstimate":0.0013,"visible":true,"isOpenSource":true,"category":"Roleplay/storytelling models","capabilities":["pdf-upload"],"maxInputTokens":6144,"maxOutputTokens":4096,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.99e-7,"output_price":0.000001207,"input_price_per_million":0.799,"output_price_per_million":1.207,"input":0.799,"output":1.207,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000799","completion":"0.000001207","input":0.799,"output":1.207,"prompt_per_million":0.799,"completion_per_million":1.207,"prompt_per_token":"0.000000799","completion_per_token":"0.000001207","per_input_token":7.99e-7,"per_output_token":0.000001207},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.001207},"effective_price":{"inputPer1kTokens":0.000799,"outputPer1kTokens":0.001207},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":61.5},"mistralai/mistral-saba":{"totalParams":24,"name":"Mistral Saba","model":"mistralai/mistral-saba","description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. ","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"mistral","visible":true,"isOpenSource":true,"maxInputTokens":32000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.989e-7,"output_price":5.95e-7,"input_price_per_million":0.1989,"output_price_per_million":0.595,"input":0.1989,"output":0.595,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001989","completion":"0.000000595","input":0.1989,"output":0.595,"prompt_per_million":0.1989,"completion_per_million":0.595,"prompt_per_token":"0.0000001989","completion_per_token":"0.000000595","per_input_token":1.989e-7,"per_output_token":5.95e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001989,"outputPer1kTokens":0.000595},"effective_price":{"inputPer1kTokens":0.0001989,"outputPer1kTokens":0.000595},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.384Z"},"avgOutputTokens":62.6},"mercury-2":{"name":"Mercury 2","model":"mercury-2","description":"Inception Labs' fastest reasoning model with tool calling and structured outputs support.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"inception","visible":true,"isOpenSource":false,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":128000,"maxOutputTokens":50000,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":7.5e-7,"input_price_per_million":0.25,"output_price_per_million":0.75,"input":0.25,"output":0.75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.00000075","input":0.25,"output":0.75,"cacheReadInputPer1kTokens":0.000025,"prompt_per_million":0.25,"completion_per_million":0.75,"prompt_per_token":"0.00000025","completion_per_token":"0.00000075","per_input_token":2.5e-7,"per_output_token":7.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.00075,"cacheReadInputPer1kTokens":0.000025},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.00075,"cacheReadInputPer1kTokens":0.000025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"mercury-coder-small":{"name":"Mercury Coder Small","model":"mercury-coder-small","description":"Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.","cost":"Average cost: $0.0014","costEstimate":0.0014,"provider":"inception","visible":true,"maxInputTokens":32768,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":0.000001,"input_price_per_million":0.25,"output_price_per_million":1,"input":0.25,"output":1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.000001","input":0.25,"output":1,"prompt_per_million":0.25,"completion_per_million":1,"prompt_per_token":"0.00000025","completion_per_token":"0.000001","per_input_token":2.5e-7,"per_output_token":0.000001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.001},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"cohere/command-r-plus-08-2024":{"totalParams":104,"name":"Cohere: Command R+","model":"cohere/command-r-plus-08-2024","description":"104B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents","cost":"Average cost: $0.0080","costEstimate":0.008,"provider":"cohere","visible":true,"maxInputTokens":128000,"maxOutputTokens":4096,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002856,"output_price":0.000014246,"input_price_per_million":2.856,"output_price_per_million":14.246,"input":2.856,"output":14.246,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002856","completion":"0.000014246","input":2.856,"output":14.246,"prompt_per_million":2.856,"completion_per_million":14.246,"prompt_per_token":"0.000002856","completion_per_token":"0.000014246","per_input_token":0.000002856,"per_output_token":0.000014246},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002856,"outputPer1kTokens":0.014246},"effective_price":{"inputPer1kTokens":0.002856,"outputPer1kTokens":0.014246},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":145.8},"command-a-reasoning-08-2025":{"totalParams":111,"name":"Cohere Command A (08/2025)","model":"command-a-reasoning-08-2025","description":"Cohere's first reasoning model designed for enterprise customer service and automation. 111B parameters with tool-use capabilities, supports 256K context and 23 languages including English, French, Spanish, Japanese, Arabic, and Hindi. Optimized for document processing, scheduling, data analysis, and more.","cost":"Average cost: $0.0100","costEstimate":0.01,"maxInputTokens":256000,"maxOutputTokens":8192,"category":"More","provider":"cohere","visible":true,"dateAdded":"2025-08-22","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":371.3},"mlabonne/NeuralDaredevil-8B-abliterated":{"totalParams":8,"name":"Neural Daredevil 8B abliterated","model":"mlabonne/NeuralDaredevil-8B-abliterated","description":"The best performing 8B abliterated model according to most benchmarks.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"meta","isOpenSource":true,"visible":true,"maxInputTokens":8192,"maxOutputTokens":8192,"category":"Uncensored","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.4e-7,"output_price":4.4e-7,"input_price_per_million":0.44,"output_price_per_million":0.44,"input":0.44,"output":0.44,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000044","completion":"0.00000044","input":0.44,"output":0.44,"prompt_per_million":0.44,"completion_per_million":0.44,"prompt_per_token":"0.00000044","completion_per_token":"0.00000044","per_input_token":4.4e-7,"per_output_token":4.4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00044,"outputPer1kTokens":0.00044},"effective_price":{"inputPer1kTokens":0.00044,"outputPer1kTokens":0.00044},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":77},"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5":{"totalParams":70,"name":"Llama 3 70B abliterated","model":"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5","description":"An abliterated (removed restrictions and censorship) version of Llama 3.1 70b.","cost":"Average cost: $0.0016","costEstimate":0.0016,"provider":"meta","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":8192,"maxOutputTokens":8192,"category":"Uncensored","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":168.4},"anthracite-org/magnum-v2-72b":{"totalParams":72,"name":"Magnum V2 72B","model":"anthracite-org/magnum-v2-72b","description":"Magnum V2 72B","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"other","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000002006,"output_price":0.000002992,"input_price_per_million":2.006,"output_price_per_million":2.992,"input":2.006,"output":2.992,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002006","completion":"0.000002992","input":2.006,"output":2.992,"prompt_per_million":2.006,"completion_per_million":2.992,"prompt_per_token":"0.000002006","completion_per_token":"0.000002992","per_input_token":0.000002006,"per_output_token":0.000002992},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002992},"effective_price":{"inputPer1kTokens":0.002006,"outputPer1kTokens":0.002992},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":319},"mistralai/Mistral-Nemo-Instruct-2407":{"totalParams":12,"name":"Mistral Nemo","model":"mistralai/mistral-nemo-instruct-2407","description":"12B parameter model with multilingual support.","cost":"Average cost: $0.0018","provider":"mistral","costEstimate":0.0018,"visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.003e-7,"output_price":1.207e-7,"input_price_per_million":0.1003,"output_price_per_million":0.1207,"input":0.1003,"output":0.1207,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001003","completion":"0.0000001207","input":0.1003,"output":0.1207,"prompt_per_million":0.1003,"completion_per_million":0.1207,"prompt_per_token":"0.0000001003","completion_per_token":"0.0000001207","per_input_token":1.003e-7,"per_output_token":1.207e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001207},"effective_price":{"inputPer1kTokens":0.0001003,"outputPer1kTokens":0.0001207},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":85.4},"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B":{"totalParams":70,"name":"Llama 3.05 Storybreaker Ministral 70b","model":"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B","description":"Much more inclined to output adult content than its predecessor. Great choice for novelty roleplay scenarios.","cost":"Average cost: $0.0015","provider":"meta","costEstimate":0.0015,"visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":63.2},"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B":{"totalParams":70,"name":"Nemotron Tenyxchat Storybreaker 70b","model":"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B","description":"Overall it provides a solid option for RP and creative writing while still functioning as an assistant model, if desired. If used to continue a roleplay it will generally follow the ongoing cadence of the conversation.","cost":"Average cost: $0.0011","provider":"meta","costEstimate":0.0011,"visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":128.5},"inflatebot/MN-12B-Mag-Mell-R1":{"totalParams":12,"name":"Mag Mell R1","model":"inflatebot/MN-12B-Mag-Mell-R1","description":"Mag Mell demonstrates worldbuilding capabilities unlike any model in its class, comparable to old adventuring models like Tiefighter, and prose that exhibits minimal slop.","cost":"Average cost: $0.0018","provider":"meta","isOpenSource":true,"costEstimate":0.0018,"visible":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":309.4},"Steelskull/L3.3-MS-Evayale-70B":{"totalParams":70,"name":"Llama 3.3 70B Evayale","model":"Steelskull/L3.3-MS-Evayale-70B","description":"Combination of EVA and Euryale.","cost":"Average cost: $0.0013","provider":"meta","isOpenSource":true,"costEstimate":0.0013,"visible":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"featherless-ai/Qwerky-72B":{"totalParams":72,"name":"Qwerky 72B","model":"featherless-ai/Qwerky-72B","description":"Linear models offer a promising approach to significantly reduce computational costs at scale, particularly for large context lengths. Enabling a >1000x improvement in inference costs, enabling o1 inference time thinking and wider AI accessibility.","cost":"Average cost: $0.0016","provider":"meta","isOpenSource":true,"costEstimate":0.0016,"visible":true,"maxInputTokens":32000,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":5e-7,"input_price_per_million":0.5,"output_price_per_million":0.5,"input":0.5,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000005","input":0.5,"output":0.5,"prompt_per_million":0.5,"completion_per_million":0.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000005","per_input_token":5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"TheDrummer/Anubis-70B-v1":{"totalParams":70,"name":"Anubis 70B v1","model":"TheDrummer/Anubis-70B-v1","description":"L3.3 finetune for roleplaying.","cost":"Average cost: $0.0012","provider":"meta","costEstimate":0.0012,"visible":true,"isOpenSource":true,"maxInputTokens":65536,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.1e-7,"output_price":3.1e-7,"input_price_per_million":0.31,"output_price_per_million":0.31,"input":0.31,"output":0.31,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000031","completion":"0.00000031","input":0.31,"output":0.31,"prompt_per_million":0.31,"completion_per_million":0.31,"prompt_per_token":"0.00000031","completion_per_token":"0.00000031","per_input_token":3.1e-7,"per_output_token":3.1e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00031,"outputPer1kTokens":0.00031},"effective_price":{"inputPer1kTokens":0.00031,"outputPer1kTokens":0.00031},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":422.7},"TheDrummer/Anubis-70B-v1.1":{"totalParams":70,"name":"Anubis 70B v1.1","model":"TheDrummer/Anubis-70B-v1.1","description":"L3.3 finetune for roleplaying – updated v1.1 with improved reasoning.","cost":"Average cost: $0.0016","provider":"meta","costEstimate":0.0016,"visible":true,"isOpenSource":true,"maxInputTokens":32000,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.1e-7,"output_price":3.1e-7,"input_price_per_million":0.31,"output_price_per_million":0.31,"input":0.31,"output":0.31,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000031","completion":"0.00000031","input":0.31,"output":0.31,"prompt_per_million":0.31,"completion_per_million":0.31,"prompt_per_token":"0.00000031","completion_per_token":"0.00000031","per_input_token":3.1e-7,"per_output_token":3.1e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00031,"outputPer1kTokens":0.00031},"effective_price":{"inputPer1kTokens":0.00031,"outputPer1kTokens":0.00031},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":224.6},"meta-llama/llama-3.2-3b-instruct":{"totalParams":3,"name":"Llama 3.2 3b Instruct","model":"meta-llama/llama-3.2-3b-instruct","description":"Small model optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization","cost":"Average cost: $0.0010","provider":"meta","costEstimate":0.001,"visible":true,"isOpenSource":true,"capabilities":["pdf-upload"],"maxInputTokens":131072,"maxOutputTokens":8192,"category":"More","preferredProviders":["Parasail","Cloudflare"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.06e-8,"output_price":4.93e-8,"input_price_per_million":0.0306,"output_price_per_million":0.0493,"input":0.0306,"output":0.0493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000000306","completion":"0.0000000493","input":0.0306,"output":0.0493,"prompt_per_million":0.0306,"completion_per_million":0.0493,"prompt_per_token":"0.0000000306","completion_per_token":"0.0000000493","per_input_token":3.06e-8,"per_output_token":4.93e-8},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0000306,"outputPer1kTokens":0.0000493},"effective_price":{"inputPer1kTokens":0.0000306,"outputPer1kTokens":0.0000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":118.9},"Meta-Llama-3-1-8B-Instruct-FP8":{"totalParams":8,"name":"Llama 3.1 8B (decentralized)","usageName":"Llama 3.1 8B","model":"Meta-Llama-3-1-8B-Instruct-FP8","description":"Meta's Llama 3.1 8B model on an open permissionless network","cost":"Average cost: $0.0010","costEstimate":0.001,"visible":true,"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","provider":"meta","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-8,"output_price":3e-8,"input_price_per_million":0.02,"output_price_per_million":0.03,"input":0.02,"output":0.03,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000002","completion":"0.00000003","input":0.02,"output":0.03,"prompt_per_million":0.02,"completion_per_million":0.03,"prompt_per_token":"0.00000002","completion_per_token":"0.00000003","per_input_token":2e-8,"per_output_token":3e-8},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0.00003},"effective_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0.00003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"Sao10K/L3.1-70B-Hanami-x1":{"totalParams":70,"name":"Llama 3.1 70B Hanami","model":"Sao10K/L3.1-70B-Hanami-x1","description":"Euryale v2.2-based finetune.","cost":"Average cost: $0.0014","costEstimate":0.0014,"provider":"meta","visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":337.8},"TheDrummer/Rocinante-12B-v1.1":{"totalParams":12,"name":"Rocinante 12b","model":"TheDrummer/Rocinante-12B-v1.1","description":"Designed for engaging storytelling and rich prose. Expanded vocabulary with unique and expressive word choices, enhanced creativity and captivating stories.","cost":"Average cost: $0.0022","costEstimate":0.0022,"provider":"mistral","isOpenSource":true,"visible":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.08e-7,"output_price":5.95e-7,"input_price_per_million":0.408,"output_price_per_million":0.595,"input":0.408,"output":0.595,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000408","completion":"0.000000595","input":0.408,"output":0.595,"prompt_per_million":0.408,"completion_per_million":0.595,"prompt_per_token":"0.000000408","completion_per_token":"0.000000595","per_input_token":4.08e-7,"per_output_token":5.95e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000408,"outputPer1kTokens":0.000595},"effective_price":{"inputPer1kTokens":0.000408,"outputPer1kTokens":0.000595},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":314.1},"Sao10K/L3.3-70B-Euryale-v2.3":{"totalParams":70,"name":"Llama 3.3 70B Euryale","model":"Sao10K/L3.3-70B-Euryale-v2.3","description":"A 70B parameter model from SAO10K based on Llama 3.3 70B, offering high-quality text generation.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"meta","visible":true,"isOpenSource":true,"maxInputTokens":20480,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":172.7},"Sao10K/L3.1-70B-Euryale-v2.2":{"totalParams":70,"name":"Llama 3.1 70B Euryale","model":"Sao10K/L3.1-70B-Euryale-v2.2","description":"A 70B parameter model from SAO10K based on Llama 3.1 70B, offering high-quality text generation.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"meta","visible":true,"isOpenSource":true,"maxInputTokens":20480,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3.06e-7,"output_price":3.57e-7,"input_price_per_million":0.306,"output_price_per_million":0.357,"input":0.306,"output":0.357,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000357","input":0.306,"output":0.357,"prompt_per_million":0.306,"completion_per_million":0.357,"prompt_per_token":"0.000000306","completion_per_token":"0.000000357","per_input_token":3.06e-7,"per_output_token":3.57e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000357},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000357},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":271.9},"Steelskull/L3.3-Cu-Mai-R1-70b":{"totalParams":70,"name":"Llama 3.3 70B Cu Mai","model":"Steelskull/L3.3-Cu-Mai-R1-70b","description":"A 70B parameter model from Steelskull based on Llama 3.3 70B, offering high-quality text generation.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"meta","visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"TheDrummer/UnslopNemo-12B-v4.1":{"totalParams":12,"name":"UnslopNemo 12b v4","model":"TheDrummer/UnslopNemo-12B-v4.1","description":"UnslopNemo v4 is the previous version from the creator of Rocinante, designed for adventure writing and role-play scenarios.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"mistral","isOpenSource":true,"visible":true,"capabilities":["pdf-upload"],"maxInputTokens":8192,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":89.8},"MarinaraSpaghetti/NemoMix-Unleashed-12B":{"totalParams":12,"name":"NemoMix 12B Unleashed","model":"MarinaraSpaghetti/NemoMix-Unleashed-12B","description":"Great for RP and storytelling.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"mistral","isOpenSource":true,"visible":true,"maxInputTokens":32768,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":204.5},"VongolaChouko/Starcannon-Unleashed-12B-v1.0":{"totalParams":12,"name":"Mistral Nemo Starcannon 12b v1","model":"VongolaChouko/Starcannon-Unleashed-12B-v1.0","description":"Mistral Nemo finetine that offers improvements on roleplay.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"mistral","visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":302.9},"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16":{"totalParams":70,"name":"Llama 3.1 70B Celeste v0.1","model":"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16","description":"Creative model based on Llama 3.1 70B","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"meta","visible":true,"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.93e-7,"output_price":4.93e-7,"input_price_per_million":0.493,"output_price_per_million":0.493,"input":0.493,"output":0.493,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000493","completion":"0.000000493","input":0.493,"output":0.493,"prompt_per_million":0.493,"completion_per_million":0.493,"prompt_per_token":"0.000000493","completion_per_token":"0.000000493","per_input_token":4.93e-7,"per_output_token":4.93e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"effective_price":{"inputPer1kTokens":0.000493,"outputPer1kTokens":0.000493},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"anthropic/claude-opus-5.5":{"name":"Claude Opus 5.5","model":"anthropic/claude-opus-5.5","description":"Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.","cost":"Average cost: $0.020","costEstimate":0.02,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-09-22","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"adaptive","effort":"high"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"high"},"verbosity":true},"tags":["advanced","reasoning","coding","agents","long-context"],"api":"chat","input_price":0.000004,"output_price":0.00002,"input_price_per_million":4,"output_price_per_million":20,"input":4,"output":20,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000004","completion":"0.00002","input":4,"output":20,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":4,"completion_per_million":20,"prompt_per_token":"0.000004","completion_per_token":"0.00002","per_input_token":0.000004,"per_output_token":0.00002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.005,"cacheWriteInputPer1kTokens1h":0.008},"effective_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.005,"cacheWriteInputPer1kTokens1h":0.008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":2010.5},"anthropic/claude-opus-5":{"name":"Claude Opus 5","model":"anthropic/claude-opus-5","description":"Claude Opus 5 is Anthropic's flagship model for advanced coding, long-running agentic tasks, research, and complex knowledge work.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-07-24","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"adaptive","effort":"high"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"high"},"verbosity":true},"tags":["advanced","reasoning","coding","agents","long-context"],"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokens":0.00625,"cacheWriteInputPer1kTokens1h":0.01},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005,"cacheWriteInputPer1kTokens":0.00625,"cacheWriteInputPer1kTokens1h":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":1502.8},"anthropic/claude-fable-5.1":{"name":"Claude Fable 5.1","model":"anthropic/claude-fable-5.1","description":"Claude Fable 5.1 improves on Fable 5 across agentic coding, long-running workflows, front-end and visual code generation, finance, analysis, and knowledge work, with more concise plans and summaries. Anthropic retains prompts and outputs for 30 days; Zero Data Retention is not available.","cost":"Average cost: $0.05","costEstimate":0.05,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-09-01","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"adaptive","effort":"high"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"high"}},"tags":["advanced","reasoning","coding","agents","long-context","vision"],"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokens1h":0.02},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokens1h":0.02},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":2335.2},"anthropic/claude-opus-4.8":{"name":"Claude Opus 4.8","model":"anthropic/claude-opus-4.8","description":"Anthropic Claude Opus 4.8 with text, image, and file inputs and a 1M-token context window.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-05-28","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":360.1},"anthropic/claude-opus-4.8:thinking":{"name":"Claude Opus 4.8 Thinking","model":"anthropic/claude-opus-4.8:thinking","description":"Anthropic Claude Opus 4.8 with thinking enabled.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-05-28","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"adaptive","effort":"high"},"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":1348.5},"anthropic/claude-fable-5":{"name":"Claude Fable 5","model":"anthropic/claude-fable-5","description":"Anthropic Claude Fable 5 for long-running coding, research, and knowledge-work tasks. Anthropic retains prompts and outputs for 30 days under its Covered Models policy; Zero Data Retention is not available.","cost":"Average cost: $0.05","costEstimate":0.05,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-06-09","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"high"}},"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.001,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"cacheReadInputPer1kTokens":0.001,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokens1h":0.02},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"cacheReadInputPer1kTokens":0.001,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokens1h":0.02},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"},"avgOutputTokens":1230.3},"anthropic/claude-fable-latest":{"name":"Claude Fable Latest","model":"anthropic/claude-fable-latest","description":"Compatibility alias for Claude Fable 5.1. Anthropic retains prompts and outputs for 30 days under its Covered Models policy; Zero Data Retention is not available.","cost":"Average cost: $0.05","costEstimate":0.05,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-06-09","maxInputTokens":1000000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"high"}},"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.00025,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokens1h":0.02},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"cacheReadInputPer1kTokens":0.00025,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokens1h":0.02},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.385Z"}},"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated":{"totalParams":32,"name":"DeepSeek R1 Qwen Abliterated","model":"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated","description":"Uncensored version of the Deepseek R1 Qwen 32B model","cost":"Average cost: $0.0026","costEstimate":0.0026,"provider":"deepseek","visible":true,"capabilities":["reasoning"],"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Uncensored","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000014,"output_price":0.0000014,"input_price_per_million":1.4,"output_price_per_million":1.4,"input":1.4,"output":1.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000014","completion":"0.0000014","input":1.4,"output":1.4,"prompt_per_million":1.4,"completion_per_million":1.4,"prompt_per_token":"0.0000014","completion_per_token":"0.0000014","per_input_token":0.0000014,"per_output_token":0.0000014},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0014},"effective_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0014},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":200.1},"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated":{"totalParams":70,"name":"DeepSeek R1 Llama 70B Abliterated","model":"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","description":"Uncensored version of the Deepseek R1 Llama 70B model","cost":"Average cost: $0.0019","costEstimate":0.0019,"provider":"deepseek","visible":true,"capabilities":["reasoning"],"isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":8192,"category":"Uncensored","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":341},"huihui-ai/Qwen2.5-32B-Instruct-abliterated":{"totalParams":32,"name":"Qwen 2.5 32B Abliterated","model":"huihui-ai/Qwen2.5-32B-Instruct-abliterated","description":"Uncensored version of Qwen 2.5 32B Instruct with restrictions removed.","cost":"Average cost: $0.0026","costEstimate":0.0026,"provider":"qwen","visible":true,"isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":8192,"category":"Uncensored","dateAdded":"2025-01-06","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0007,"outputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":805.6},"aion-labs/aion-rp-llama-3.1-8b":{"totalParams":8,"name":"Llama 3.1 8b (uncensored)","model":"aion-labs/aion-rp-llama-3.1-8b","description":"This is a truly uncensored model, trained to excel at roleplaying and creative writing. However, it can also do other things!","cost":"Average cost: $0.0024","costEstimate":0.0024,"visible":true,"isOpenSource":false,"maxInputTokens":32768,"maxOutputTokens":16384,"category":"Uncensored","provider":"aionlabs","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":8e-7,"output_price":0.0000016,"input_price_per_million":0.8,"output_price_per_million":1.6,"input":0.8,"output":1.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000008","completion":"0.0000016","input":0.8,"output":1.6,"prompt_per_million":0.8,"completion_per_million":1.6,"prompt_per_token":"0.0000008","completion_per_token":"0.0000016","per_input_token":8e-7,"per_output_token":0.0000016},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0008,"outputPer1kTokens":0.0016},"effective_price":{"inputPer1kTokens":0.0008,"outputPer1kTokens":0.0016},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":393.5},"LatitudeGames/Wayfarer-Large-70B-Llama-3.3":{"totalParams":70,"name":"Llama 3.3 70B Wayfarer","model":"LatitudeGames/Wayfarer-Large-70B-Llama-3.3","description":"Llama 3.3 70B Wayfarer is a fine-tuned version of Llama 3.3 70B, trained on a diverse set of creative writing and RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive by making sure no two entries in the dataset have repeated characters or situations, which makes sure the model does not latch on to a certain personality and be capable of understanding and acting appropriately to any characters or situations.","cost":"Average cost: $0.0013","provider":"meta","costEstimate":0.0013,"visible":true,"dateAdded":"2025-02-20","isOpenSource":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7e-7,"output_price":7e-7,"input_price_per_million":0.7,"output_price_per_million":0.7,"input":0.7,"output":0.7,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000007","completion":"0.0000007","input":0.7,"output":0.7,"prompt_per_million":0.7,"completion_per_million":0.7,"prompt_per_token":"0.0000007","completion_per_token":"0.0000007","per_input_token":7e-7,"per_output_token":7e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000700000007,"outputPer1kTokens":0.000700000007},"effective_price":{"inputPer1kTokens":0.000700000007,"outputPer1kTokens":0.000700000007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":264.7},"claude-opus-4-thinking:1024":{"name":"Claude 4 Opus Thinking (1K)","model":"anthropic/claude-opus-4:thinking:1024","description":"Claude 4 Opus with minimal thinking budget (1,024 tokens).","cost":"Average cost: $0.1249","costEstimate":0.1249,"provider":"anthropic","visible":true,"disabled":true,"apiOnly":true,"dateAdded":"2025-08-05","labelVariant":"outline","category":"More","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":1024}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"claude-opus-4-thinking:8192":{"name":"Claude 4 Opus Thinking (8K)","model":"anthropic/claude-opus-4:thinking:8192","description":"Claude 4 Opus with reduced thinking budget (8,192 tokens).","cost":"Average cost: $0.1449","costEstimate":0.1449,"provider":"anthropic","visible":true,"disabled":true,"apiOnly":true,"dateAdded":"2025-08-05","category":"More","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":8192}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"claude-opus-4-thinking:32768":{"name":"Claude 4 Opus Thinking (32K)","model":"anthropic/claude-opus-4:thinking:32768","description":"Claude 4 Opus with extended thinking budget (32,768 tokens).","cost":"Average cost: $0.247","costEstimate":0.247,"provider":"anthropic","visible":true,"disabled":true,"apiOnly":true,"dateAdded":"2025-08-05","category":"More","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":32768}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"anthropic/claude-opus-4.6":{"name":"Claude 4.6 Opus","model":"anthropic/claude-opus-4.6","description":"Claude Opus 4.6 supports advanced coding, agentic workflows, and long-context analysis with up to a 1M-token context window.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"labelVariant":"outline","dateAdded":"2026-02-05","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":1440.2},"anthropic/claude-opus-4.6:thinking":{"name":"Claude 4.6 Opus Thinking","model":"anthropic/claude-opus-4.6:thinking","description":"Claude Opus 4.6 with adaptive thinking enabled (default effort: high).","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-02-05","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":1388.1},"anthropic/claude-opus-latest":{"name":"Claude Opus Latest","model":"anthropic/claude-opus-latest","description":"Compatibility alias that routes to the newest version of Claude Opus. Currently routes to Claude Opus 5.5.","cost":"Input $4/M, Output $20/M","costEstimate":0.024,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-03-29","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high","thinking":{"type":"adaptive","effort":"high"}},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"thinking":{"type":"adaptive","effort":"high"},"verbosity":true},"api":"chat","input_price":0.000004,"output_price":0.00002,"input_price_per_million":4,"output_price_per_million":20,"input":4,"output":20,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000004","completion":"0.00002","input":4,"output":20,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":4,"completion_per_million":20,"prompt_per_token":"0.000004","completion_per_token":"0.00002","per_input_token":0.000004,"per_output_token":0.00002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.005,"cacheWriteInputPer1kTokens1h":0.008},"effective_price":{"inputPer1kTokens":0.004,"outputPer1kTokens":0.02,"cacheReadInputPer1kTokens":0.0002,"cacheWriteInputPer1kTokens":0.005,"cacheWriteInputPer1kTokens1h":0.008},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"anthropic/claude-opus-4.6:thinking:max":{"name":"Claude 4.6 Opus Thinking Max","model":"anthropic/claude-opus-4.6:thinking:max","description":"Claude Opus 4.6 with adaptive thinking (effort: max).","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-02-05","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":3305.1},"anthropic/claude-opus-4.6:thinking:medium":{"name":"Claude 4.6 Opus Thinking Medium","model":"anthropic/claude-opus-4.6:thinking:medium","description":"Claude Opus 4.6 with adaptive thinking (effort: medium).","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-02-05","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":3195.6},"anthropic/claude-opus-4.6:thinking:low":{"name":"Claude 4.6 Opus Thinking Low","model":"anthropic/claude-opus-4.6:thinking:low","description":"Claude Opus 4.6 with adaptive thinking (effort: low).","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-02-05","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":1576.4},"anthropic/claude-opus-4.7":{"name":"Claude 4.7 Opus","model":"anthropic/claude-opus-4.7","description":"Claude Opus 4.7 is a major upgrade for advanced software engineering, long-running complex tasks, and high-resolution vision understanding.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"labelVariant":"outline","dateAdded":"2026-04-16","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":741.7},"anthropic/claude-opus-4.7:thinking":{"name":"Claude 4.7 Opus Thinking","model":"anthropic/claude-opus-4.7:thinking","description":"Claude Opus 4.7 with thinking enabled (default budget: 16k tokens).","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2026-04-16","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":1860.5},"anthropic/claude-sonnet-4.6":{"name":"Claude Sonnet 4.6","model":"anthropic/claude-sonnet-4.6","description":"Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long-context reasoning, agent planning, and design. Supports up to a 1M-token context window at Sonnet pricing.","cost":"Average cost: $0.0263","costEstimate":0.0263,"labelVariant":"outline","provider":"anthropic","visible":true,"dateAdded":"2026-02-17","capabilities":["vision","pdf-upload","tool-calling","structured-output","reasoning"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000003,"output_price":0.000015,"input_price_per_million":3,"output_price_per_million":15,"input":3,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000015","input":3,"output":15,"cacheReadInputPer1kTokens":0.00030000000000000003,"prompt_per_million":3,"completion_per_million":15,"prompt_per_token":"0.000003","completion_per_token":"0.000015","per_input_token":0.000003,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":400.7},"anthropic/claude-sonnet-4.6:thinking":{"name":"Claude Sonnet 4.6 Thinking","model":"anthropic/claude-sonnet-4.6:thinking","description":"Claude Sonnet 4.6 with extended thinking enabled for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows and complex problem solving.","cost":"Average cost: $0.04","costEstimate":0.04,"provider":"anthropic","visible":true,"dateAdded":"2026-02-17","category":"More","labelVariant":"outline","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":1000000,"maxOutputTokens":128000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000003,"output_price":0.000015,"input_price_per_million":3,"output_price_per_million":15,"input":3,"output":15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000003","completion":"0.000015","input":3,"output":15,"cacheReadInputPer1kTokens":0.00030000000000000003,"prompt_per_million":3,"completion_per_million":15,"prompt_per_token":"0.000003","completion_per_token":"0.000015","per_input_token":0.000003,"per_output_token":0.000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"effective_price":{"inputPer1kTokens":0.003,"outputPer1kTokens":0.015,"cacheReadInputPer1kTokens":0.00030000000000000003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":597.7},"claude-opus-4-5-20251101":{"name":"Claude 4.5 Opus","model":"anthropic/claude-opus-4.5","description":"Claude Opus 4.5 is the top model for coding, agentic workflows, and computer use—now stronger at deep research, slides, and spreadsheets. It pushes state-of-the-art software engineering and lifts vision, reasoning, and math across the board.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2025-11-01","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":64000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":552.6},"claude-opus-4-5-20251101:thinking":{"name":"Claude 4.5 Opus Thinking","model":"anthropic/claude-opus-4.5:thinking","description":"Claude Opus 4.5 with visible thinking for tougher coding, agent, and research work—built to show its reasoning while tackling long, complex tasks.","cost":"Average cost: $0.025","costEstimate":0.025,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","dateAdded":"2025-11-01","capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"maxInputTokens":200000,"maxOutputTokens":64000,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000},"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"api":"chat","input_price":0.000005,"output_price":0.000025,"input_price_per_million":5,"output_price_per_million":25,"input":5,"output":25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000005","completion":"0.000025","input":5,"output":25,"cacheReadInputPer1kTokens":0.0005,"prompt_per_million":5,"completion_per_million":25,"prompt_per_token":"0.000005","completion_per_token":"0.000025","per_input_token":0.000005,"per_output_token":0.000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.005,"outputPer1kTokens":0.025,"cacheReadInputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":2277.2},"claude-opus-4-1-20250805":{"name":"Claude 4.1 Opus","model":"anthropic/claude-opus-4.1","description":"Claude Opus 4.1 is a powerful model from Anthropic that delivers sustained performance for complex coding and other long-running tasks that require thousands of steps, expanding the capabilities of AI agents.","cost":"Average cost: $0.1149","costEstimate":0.1149,"category":"More","labelVariant":"outline","provider":"anthropic","visible":true,"maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":725},"claude-opus-4-1-thinking":{"name":"Claude 4.1 Opus Thinking","model":"anthropic/claude-opus-4.1:thinking","description":"Anthropic's Claude 4.1 Opus with the ability to show its thinking process step by step.","cost":"Average cost: $0.1749","costEstimate":0.1749,"provider":"anthropic","visible":true,"category":"More","labelVariant":"outline","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":16000}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":492.8},"claude-opus-4-1-thinking:1024":{"name":"Claude 4.1 Opus Thinking (1K)","model":"anthropic/claude-opus-4.1:thinking:1024","description":"Claude 4.1 Opus with minimal thinking budget (1,024 tokens).","cost":"Average cost: $0.1249","costEstimate":0.1249,"provider":"anthropic","visible":true,"apiOnly":true,"labelVariant":"outline","category":"More","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":1024}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"claude-opus-4-1-thinking:8192":{"name":"Claude 4.1 Opus Thinking (8K)","model":"anthropic/claude-opus-4.1:thinking:8192","description":"Claude 4.1 Opus with reduced thinking budget (8,192 tokens).","cost":"Average cost: $0.1449","costEstimate":0.1449,"provider":"anthropic","visible":true,"apiOnly":true,"category":"More","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":8192}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"claude-opus-4-1-thinking:32768":{"name":"Claude 4.1 Opus Thinking (32K)","model":"anthropic/claude-opus-4.1:thinking:32768","description":"Claude 4.1 Opus with extended thinking budget (32,768 tokens).","cost":"Average cost: $0.247","costEstimate":0.247,"provider":"anthropic","visible":true,"apiOnly":true,"category":"More","maxInputTokens":200000,"maxOutputTokens":32000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"thinking":{"type":"enabled","budget_tokens":32768}},"api":"chat","input_price":0.000015,"output_price":0.000075,"input_price_per_million":15,"output_price_per_million":75,"input":15,"output":75,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.000075","input":15,"output":75,"cacheReadInputPer1kTokens":0.0015,"prompt_per_million":15,"completion_per_million":75,"prompt_per_token":"0.000015","completion_per_token":"0.000075","per_input_token":0.000015,"per_output_token":0.000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.075,"cacheReadInputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"ernie-5.1":{"name":"ERNIE 5.1","model":"ernie-5.1","description":"ERNIE 5.1 is the latest Wenxin model, with broad upgrades to agentic workflows, knowledge, reasoning, and deep search. ⚠️ Note: privacy and logging guarantees may be limited.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"baidu","visible":true,"dateAdded":"2026-05-10","maxInputTokens":119000,"maxOutputTokens":64000,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.5e-7,"output_price":0.000003,"input_price_per_million":0.75,"output_price_per_million":3,"input":0.75,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.000003","input":0.75,"output":3,"cacheReadInputPer1kTokens":0.00075,"prompt_per_million":0.75,"completion_per_million":3,"prompt_per_token":"0.00000075","completion_per_token":"0.000003","per_input_token":7.5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00075},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":1859.3},"ernie-5.1:thinking":{"name":"ERNIE 5.1 Thinking","model":"ernie-5.1:thinking","description":"ERNIE 5.1 Thinking is the latest Wenxin model with explicit reasoning enabled for harder planning, coding, math, and agentic tasks. ⚠️ Note: privacy and logging guarantees may be limited.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"baidu","visible":true,"dateAdded":"2026-05-10","capabilities":["reasoning"],"maxInputTokens":119000,"maxOutputTokens":64000,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":7.5e-7,"output_price":0.000003,"input_price_per_million":0.75,"output_price_per_million":3,"input":0.75,"output":3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000075","completion":"0.000003","input":0.75,"output":3,"cacheReadInputPer1kTokens":0.00075,"prompt_per_million":0.75,"completion_per_million":3,"prompt_per_token":"0.00000075","completion_per_token":"0.000003","per_input_token":7.5e-7,"per_output_token":0.000003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00075},"effective_price":{"inputPer1kTokens":0.00075,"outputPer1kTokens":0.003,"cacheReadInputPer1kTokens":0.00075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"gemini-2.0-pro-reasoner":{"name":"Gemini 2.0 Pro Reasoner","model":"gemini-2.0-pro-reasoner","description":"Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement. 'DeepGemini', fusion of Gemini 2.5 Pro and Deepseek R1.","cost":"Average cost: $0.0369","costEstimate":0.0369,"category":"More","provider":"gemini","visible":true,"maxInputTokens":128000,"maxOutputTokens":65536,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001292,"output_price":0.000004998,"input_price_per_million":1.292,"output_price_per_million":4.998,"input":1.292,"output":4.998,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001292","completion":"0.000004998","input":1.292,"output":4.998,"cacheReadInputPer1kTokens":0.000323,"prompt_per_million":1.292,"completion_per_million":4.998,"prompt_per_token":"0.000001292","completion_per_token":"0.000004998","per_input_token":0.000001292,"per_output_token":0.000004998},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001292,"outputPer1kTokens":0.004998,"cacheReadInputPer1kTokens":0.000323},"effective_price":{"inputPer1kTokens":0.001292,"outputPer1kTokens":0.004998,"cacheReadInputPer1kTokens":0.000323},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"}},"unsloth/gemma-3-27b-it":{"totalParams":27,"name":"Gemma 3 27B IT","model":"unsloth/gemma-3-27b-it","description":"Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"gemini","visible":true,"capabilities":["pdf-upload"],"maxInputTokens":128000,"maxOutputTokens":96000,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.992e-7,"output_price":2.992e-7,"input_price_per_million":0.2992,"output_price_per_million":0.2992,"input":0.2992,"output":0.2992,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002992","completion":"0.0000002992","input":0.2992,"output":0.2992,"prompt_per_million":0.2992,"completion_per_million":0.2992,"prompt_per_token":"0.0000002992","completion_per_token":"0.0000002992","per_input_token":2.992e-7,"per_output_token":2.992e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002992,"outputPer1kTokens":0.0002992},"effective_price":{"inputPer1kTokens":0.0002992,"outputPer1kTokens":0.0002992},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":122},"unsloth/gemma-3-12b-it":{"totalParams":12,"name":"Gemma 3 12B IT","model":"unsloth/gemma-3-12b-it","description":"Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"gemini","visible":true,"capabilities":["pdf-upload"],"maxInputTokens":128000,"maxOutputTokens":131072,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.72e-7,"output_price":2.72e-7,"input_price_per_million":0.272,"output_price_per_million":0.272,"input":0.272,"output":0.272,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000272","completion":"0.000000272","input":0.272,"output":0.272,"prompt_per_million":0.272,"completion_per_million":0.272,"prompt_per_token":"0.000000272","completion_per_token":"0.000000272","per_input_token":2.72e-7,"per_output_token":2.72e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000272,"outputPer1kTokens":0.000272},"effective_price":{"inputPer1kTokens":0.000272,"outputPer1kTokens":0.000272},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":167.8},"unsloth/gemma-3-4b-it":{"totalParams":4,"name":"Gemma 3 4B IT","model":"unsloth/gemma-3-4b-it","description":"Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"gemini","visible":true,"capabilities":["pdf-upload"],"maxInputTokens":128000,"maxOutputTokens":8192,"isOpenSource":true,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.006e-7,"output_price":2.006e-7,"input_price_per_million":0.2006,"output_price_per_million":0.2006,"input":0.2006,"output":0.2006,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002006","completion":"0.0000002006","input":0.2006,"output":0.2006,"prompt_per_million":0.2006,"completion_per_million":0.2006,"prompt_per_token":"0.0000002006","completion_per_token":"0.0000002006","per_input_token":2.006e-7,"per_output_token":2.006e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"effective_price":{"inputPer1kTokens":0.0002006,"outputPer1kTokens":0.0002006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.386Z"},"avgOutputTokens":115.2},"qwen25-vl-72b-instruct":{"totalParams":72,"name":"Qwen25 VL 72b","model":"qwen/qwen2.5-vl-72b-instruct","description":"Qwen25 VL 72b model with 32k context window","provider":"qwen","cost":"$0.005","costEstimate":0.0012,"visible":true,"dateAdded":"2025-05-10","isOpenSource":true,"capabilities":["vision"],"category":"More","maxInputTokens":32000,"maxOutputTokens":32768,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6.9989e-7,"output_price":6.9989e-7,"input_price_per_million":0.69989,"output_price_per_million":0.69989,"input":0.69989,"output":0.69989,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000069989","completion":"0.00000069989","input":0.69989,"output":0.69989,"prompt_per_million":0.69989,"completion_per_million":0.69989,"prompt_per_token":"0.00000069989","completion_per_token":"0.00000069989","per_input_token":6.9989e-7,"per_output_token":6.9989e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00069989,"outputPer1kTokens":0.00069989},"effective_price":{"inputPer1kTokens":0.00069989,"outputPer1kTokens":0.00069989},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":222.6},"holo3-35b-a3b":{"totalParams":35,"activeParams":3,"name":"Holo3-35B-A3B","model":"holo3-35b-a3b","description":"Efficient multimodal Holo model for text and image inputs with structured outputs and thinking disabled by default.","provider":"holo","cost":"Average cost: $0.00205","costEstimate":0.00205,"category":"More","visible":true,"isOpenSource":true,"maxInputTokens":65536,"maxOutputTokens":65536,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":0.0000018,"input_price_per_million":0.25,"output_price_per_million":1.8,"input":0.25,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000018","input":0.25,"output":1.8,"prompt_per_million":0.25,"completion_per_million":1.8,"prompt_per_token":"0.00000025","completion_per_token":"0.0000018","per_input_token":2.5e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":141.4},"holo3-35b-a3b:thinking":{"totalParams":35,"activeParams":3,"name":"Holo3-35B-A3B Thinking","model":"holo3-35b-a3b:thinking","description":"Holo3-35B-A3B with thinking enabled, returning separate reasoning content alongside the answer.","provider":"holo","cost":"Average cost: $0.00205","costEstimate":0.00205,"category":"More","visible":true,"isOpenSource":true,"maxInputTokens":65536,"maxOutputTokens":65536,"tags":["Thinking"],"labelVariant":"outline","capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.5e-7,"output_price":0.0000018,"input_price_per_million":0.25,"output_price_per_million":1.8,"input":0.25,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000025","completion":"0.0000018","input":0.25,"output":1.8,"prompt_per_million":0.25,"completion_per_million":1.8,"prompt_per_token":"0.00000025","completion_per_token":"0.0000018","per_input_token":2.5e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.00025,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":921.3},"deepcogito/cogito-v1-preview-qwen-32B":{"totalParams":32,"name":"Cogito v1 Preview Qwen 32B","model":"deepcogito/cogito-v1-preview-qwen-32B","description":"32-B parameter reasoning model from DeepCogito (Qwen backbone) – strong general reasoning & coding at low price.","cost":"Average cost: $0.00162","costEstimate":0.001,"provider":"alibaba","visible":true,"dateAdded":"2025-05-10","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":32768,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000018,"output_price":0.0000018,"input_price_per_million":1.8,"output_price_per_million":1.8,"input":1.8,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000018","completion":"0.0000018","input":1.8,"output":1.8,"prompt_per_million":1.8,"completion_per_million":1.8,"prompt_per_token":"0.0000018","completion_per_token":"0.0000018","per_input_token":0.0000018,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0018,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0018,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"Salesforce/Llama-xLAM-2-70b-fc-r":{"totalParams":70,"name":"Llama-xLAM-2 70B fc-r","model":"Salesforce/Llama-xLAM-2-70b-fc-r","description":"Salesforce’s 70-B frontier model focused on function-calling & retrieval-augmented generation.","cost":"Average cost: $0.00228","costEstimate":0.001,"provider":"meta","visible":true,"dateAdded":"2025-04-13","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000025,"output_price":0.0000025,"input_price_per_million":2.5,"output_price_per_million":2.5,"input":2.5,"output":2.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.0000025","input":2.5,"output":2.5,"prompt_per_million":2.5,"completion_per_million":2.5,"prompt_per_token":"0.0000025","completion_per_token":"0.0000025","per_input_token":0.0000025,"per_output_token":0.0000025},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0025},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.0025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"mistral-small-31-24b-instruct":{"totalParams":24,"name":"Mistral Small 3.1 24B (2503)","model":"mistralai/mistral-small-3.1-24b-instruct","description":"Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.","provider":"mistral","cost":"Average cost: $0.003","costEstimate":0.0011,"category":"More","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":131072,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":3e-7,"input_price_per_million":0.1,"output_price_per_million":0.3,"input":0.1,"output":0.3,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000003","input":0.1,"output":0.3,"prompt_per_million":0.1,"completion_per_million":0.3,"prompt_per_token":"0.0000001","completion_per_token":"0.0000003","per_input_token":1e-7,"per_output_token":3e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":102.4},"chutesai/Mistral-Small-3.2-24B-Instruct-2506":{"totalParams":24,"name":"Mistral Small 3.2 24B (2506)","model":"mistralai/mistral-small-3.2-24b-instruct","description":"The latest iteration of Mistral Small, version 3.2 (2506) brings enhanced performance and capabilities. With 24 billion parameters, this model delivers state-of-the-art results across text generation tasks with improved efficiency.","provider":"mistral","cost":"Average cost: $0.003","costEstimate":0.0012,"category":"More","visible":true,"dateAdded":"2025-04-15","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":131072,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":4e-7,"input_price_per_million":0.2,"output_price_per_million":0.4,"input":0.2,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000004","input":0.2,"output":0.4,"prompt_per_million":0.2,"completion_per_million":0.4,"prompt_per_token":"0.0000002","completion_per_token":"0.0000004","per_input_token":2e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":140.6},"asi1-mini":{"name":"ASI1 Mini","model":"asi1-mini","description":"ASI-1 Mini introduces next-level adaptive reasoning, context-aware decision-making. It features native reasoning support with four dynamic reasoning modes, intelligently selecting from Multi-Step, Complete, Optimized, and Short Reasoning, balancing depth, efficiency, and precision. Whether tackling complex, multi-layered problems or delivering concise, high-impact insights, ASI-1 Mini ensures reasoning is always tailored to the task at hand. Note: this model is rate limited at the moment.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"fetchai","visible":true,"dateAdded":"2025-03-25","capabilities":["pdf-upload"],"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.000001,"output_price":0.000001,"input_price_per_million":1,"output_price_per_million":1,"input":1,"output":1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000001","completion":"0.000001","input":1,"output":1,"prompt_per_million":1,"completion_per_million":1,"prompt_per_token":"0.000001","completion_per_token":"0.000001","per_input_token":0.000001,"per_output_token":0.000001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.001},"effective_price":{"inputPer1kTokens":0.001,"outputPer1kTokens":0.001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"nvidia/Llama-3.3-Nemotron-Super-49B-v1":{"totalParams":49,"name":"Nvidia Nemotron Super 49B","model":"nvidia/Llama-3.3-Nemotron-Super-49B-v1","description":"Llama-3.3-Nemotron-Super-49B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model's memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. For more information on the NAS approach, please refer to this paper.","cost":"Average cost: $0.0013","costEstimate":0.0013,"provider":"nvidia","visible":true,"dateAdded":"2025-08-08","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":1.5e-7,"input_price_per_million":0.15,"output_price_per_million":0.15,"input":0.15,"output":0.15,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.00000015","input":0.15,"output":0.15,"prompt_per_million":0.15,"completion_per_million":0.15,"prompt_per_token":"0.00000015","completion_per_token":"0.00000015","per_input_token":1.5e-7,"per_output_token":1.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00015},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.00015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"totalParams":235,"activeParams":22,"name":"Qwen3 VL 235B A22B Instruct","model":"qwen/qwen3-vl-235b-a22b-instruct","description":"Routed across multiple providers, which may include Alibaba, a Chinese entity; provider-specific privacy and logging guarantees may vary. Qwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts/diagrams, and multi‑image context.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"qwen","visible":true,"isOpenSource":true,"maxInputTokens":131072,"maxOutputTokens":32768,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":0.0000019,"input_price_per_million":0.3,"output_price_per_million":1.9,"input":0.3,"output":1.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000019","input":0.3,"output":1.9,"prompt_per_million":0.3,"completion_per_million":1.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000019","per_input_token":3e-7,"per_output_token":0.0000019},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0019},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":105.8},"shisa-ai/shisa-v2-llama3.3-70b":{"totalParams":70,"name":"Shisa V2 Llama 3.3 70B","model":"shisa-ai/shisa-v2-llama3.3-70b","description":"Shisa V2 is a family of bilingual Japanese/English language models ranging from 7B to 70B parameters, optimized for high-quality Japanese language capabilities while maintaining strong English performance.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"shisa","visible":true,"dateAdded":"2025-07-26","isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":5e-7,"input_price_per_million":0.5,"output_price_per_million":0.5,"input":0.5,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000005","input":0.5,"output":0.5,"prompt_per_million":0.5,"completion_per_million":0.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000005","per_input_token":5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"shisa-ai/shisa-v2.1-llama3.3-70b":{"totalParams":70,"name":"Shisa V2.1 Llama 3.3 70B","model":"shisa-ai/shisa-v2.1-llama3.3-70b","description":"70B parameter Llama 3.3-based chat model optimized for bilingual Japanese and English tasks, with strong instruction following, translation quality, and polite responses.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"shisa","visible":true,"isOpenSource":true,"maxInputTokens":32768,"maxOutputTokens":4096,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":5e-7,"input_price_per_million":0.5,"output_price_per_million":0.5,"input":0.5,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000005","input":0.5,"output":0.5,"prompt_per_million":0.5,"completion_per_million":0.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000005","per_input_token":5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"THUDM/GLM-Z1-9B-0414":{"totalParams":9,"name":"GLM Z1 9B 0414","model":"THUDM/GLM-Z1-9B-0414","description":"9B small-sized model maintaining the open-source tradition. Despite its smaller scale, GLM-Z1-9B-0414 still exhibits excellent capabilities in mathematical reasoning and general tasks. Its overall performance is already at a leading level among open-source models of the same size.","cost":"Average cost: $0.0011","costEstimate":0.0011,"visible":true,"isOpenSource":true,"maxInputTokens":32000,"maxOutputTokens":8000,"category":"More","provider":"zhipu","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":2e-7,"input_price_per_million":0.2,"output_price_per_million":0.2,"input":0.2,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000002","input":0.2,"output":0.2,"prompt_per_million":0.2,"completion_per_million":0.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000002","per_input_token":2e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"}},"THUDM/GLM-4-9B-0414":{"totalParams":9,"name":"GLM 4 9B 0414","model":"THUDM/GLM-4-9B-0414","description":"A 9B parameter version of the GLM-4 series, offering a balance of performance and efficiency.","cost":"Average cost: $0.0011","costEstimate":0.0011,"visible":true,"isOpenSource":true,"maxInputTokens":32000,"maxOutputTokens":8000,"category":"More","provider":"zhipu","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":2e-7,"input_price_per_million":0.2,"output_price_per_million":0.2,"input":0.2,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000002","input":0.2,"output":0.2,"prompt_per_million":0.2,"completion_per_million":0.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000002","per_input_token":2e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":83.3},"THUDM/GLM-4-32B-0414":{"totalParams":32,"name":"GLM 4 32B 0414","model":"THUDM/GLM-4-32B-0414","description":"Features 32 billion parameters. Performance is comparable to OpenAI's GPT series and DeepSeek's V3/R1 series. Pre-trained on 15T of high-quality data, including reasoning-type synthetic data. Enhanced performance in instruction following, engineering code, and function calling.","cost":"Average cost: $0.0011","costEstimate":0.0011,"visible":true,"isOpenSource":true,"maxInputTokens":128000,"maxOutputTokens":65536,"category":"More","provider":"zhipu","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":2e-7,"input_price_per_million":0.2,"output_price_per_million":0.2,"input":0.2,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000002","input":0.2,"output":0.2,"prompt_per_million":0.2,"completion_per_million":0.2,"prompt_per_token":"0.0000002","completion_per_token":"0.0000002","per_input_token":2e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":152.5},"Qwen3.5-27B-Blossom-V6.4-Derestricted":{"totalParams":27,"name":"Qwen3.5 27B Blossom V6.4 Derestricted","model":"Qwen3.5-27B-Blossom-V6.4-Derestricted","description":"Qwen3.5 27B Blossom V6.4 Derestricted is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":534.9},"Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted":{"totalParams":27,"name":"Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted","model":"Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted","description":"Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"cacheReadInputPer1kTokens":0.000030600000000000005,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.000030600000000000005},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.000030600000000000005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":529.5},"Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted-Lite":{"totalParams":27,"name":"Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite","model":"Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted-Lite","description":"Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite is a lighter-tuned community finetune for responsive multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"cacheReadInputPer1kTokens":0.000030600000000000005,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.000030600000000000005},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.000030600000000000005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":252.8},"Gemma-4-31B-Agares-v1":{"totalParams":31,"name":"Gemma 4 31B Agares v1","model":"Gemma-4-31B-Agares-v1","description":"Gemma 4 31B Agares v1 is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":128.5},"Gemma-4-31B-Animus-V14.1":{"totalParams":31,"name":"Gemma 4 31B Animus V14.1","model":"Gemma-4-31B-Animus-V14.1","description":"Gemma 4 31B Animus V14.1 is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":482.4},"Gemma-4-31B-AssGuard":{"totalParams":31,"name":"Gemma 4 31B AssGuard","model":"Gemma-4-31B-AssGuard","description":"Gemma 4 31B AssGuard is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":560.7},"Gemma-4-31B-Dark-Gemistry":{"totalParams":31,"name":"Gemma 4 31B Dark Gemistry","model":"Gemma-4-31B-Dark-Gemistry","description":"Gemma 4 31B Dark Gemistry is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":398.4},"Gemma-4-31B-Gembrain-uncensored-heretic":{"totalParams":31,"name":"Gemma 4 31B Gembrain Uncensored Heretic","model":"Gemma-4-31B-Gembrain-uncensored-heretic","description":"Gemma 4 31B Gembrain Uncensored Heretic is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":432},"Gemma-4-31B-Gembrain-X-Core":{"totalParams":31,"name":"Gemma 4 31B Gembrain X Core","model":"Gemma-4-31B-Gembrain-X-Core","description":"Gemma 4 31B Gembrain X Core is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":665.3},"Gemma-4-31B-Isometry-RP":{"totalParams":31,"name":"Gemma 4 31B Isometry RP","model":"Gemma-4-31B-Isometry-RP","description":"Gemma 4 31B Isometry RP is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":492.1},"Gemma-4-31B-Novelist":{"totalParams":31,"name":"Gemma 4 31B Novelist (ArliAI)","model":"Gemma-4-31B-Novelist","description":"Gemma 4 31B Novelist is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":1175.3},"Gemma-4-31B-SDFT-Heretic-RP":{"totalParams":31,"name":"Gemma 4 31B SDFT Heretic RP","model":"Gemma-4-31B-SDFT-Heretic-RP","description":"Gemma 4 31B SDFT Heretic RP is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":308.7},"Gemma-4-31B-StyleTune":{"totalParams":31,"name":"Gemma 4 31B StyleTune","model":"Gemma-4-31B-StyleTune","description":"Gemma 4 31B StyleTune is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-15","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":470},"Qwen3.5-27B-BlueStar-v3-Derestricted":{"totalParams":27,"name":"Qwen3.5 27B BlueStar v3 Derestricted","model":"Qwen3.5-27B-BlueStar-v3-Derestricted","description":"Third-generation BlueStar finetune for creative roleplay, narrative prose, and multimodal Qwen3.5 27B workflows.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-04-30","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.387Z"},"avgOutputTokens":412.3},"Qwen3.5-27B-Queen-Derestricted":{"totalParams":27,"name":"Qwen3.5 27B Queen Derestricted","model":"Qwen3.5-27B-Queen-Derestricted","description":"Queen finetune for derestricted creative writing, roleplay, and expressive character dialogue.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"qwen","visible":true,"isOpenSource":true,"dateAdded":"2026-04-30","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":420.6},"Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled":{"defaultThinkingEnabled":true,"totalParams":31,"name":"Gemma 4 31B Claude 4.6 Opus Reasoning Distilled","model":"Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled","description":"ArliAI-hosted Gemma 4 31B reasoning-distilled finetune for structured scene planning, dialogue, and multimodal chat.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-01","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"cacheReadInputPer1kTokens":0.000030600000000000005,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.000030600000000000005},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306,"cacheReadInputPer1kTokens":0.000030600000000000005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":198.7},"Gemma-4-31B-Cognitive-Unshackled":{"totalParams":31,"name":"Gemma 4 31B Cognitive Unshackled","model":"Gemma-4-31B-Cognitive-Unshackled","description":"ArliAI-hosted Gemma 4 31B finetune for open-ended reasoning, character chat, and multimodal creative work.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-01","maxInputTokens":262144,"category":"Uncensored","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":873.4},"Gemma-4-31B-DarkIdol":{"totalParams":31,"name":"Gemma 4 31B DarkIdol (ArliAI)","model":"Gemma-4-31B-DarkIdol","description":"ArliAI-hosted Gemma 4 31B DarkIdol finetune for dramatic tone, expressive dialogue, and multimodal roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-01","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":573.9},"Gemma-4-31B-Fabled":{"totalParams":31,"name":"Gemma 4 31B Fabled (ArliAI)","model":"Gemma-4-31B-Fabled","description":"ArliAI-hosted Gemma 4 31B Fabled finetune for mythic narrative writing, adventure scenes, and multimodal roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-02","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":246.6},"Gemma-4-31B-GarnetV2":{"totalParams":31,"name":"Gemma 4 31B Garnet V2","model":"Gemma-4-31B-GarnetV2","description":"ArliAI-hosted Gemma 4 31B Garnet V2 finetune for polished prose, character consistency, and multimodal roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-01","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":299},"Gemma-4-31B-K1-v5":{"totalParams":31,"name":"Gemma 4 31B K1 v5","model":"Gemma-4-31B-K1-v5","description":"ArliAI-hosted Gemma 4 31B K1 v5 finetune for plot progression, action scenes, and multimodal roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-02","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1389.7},"Gemma-4-31B-MeroMero":{"totalParams":31,"name":"Gemma 4 31B MeroMero","model":"Gemma-4-31B-MeroMero","description":"Gemma 4 31B MeroMero is a community creative finetune for emotive dialogue, relationship scenes, and multimodal roleplay.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-02","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":612.9},"Gemma-4-31B-Queen":{"totalParams":31,"name":"Gemma 4 31B Queen","model":"Gemma-4-31B-Queen","description":"Gemma 4 31B Queen is a community creative finetune for commanding character voices, expressive dialogue, and multimodal chat.","cost":"Average cost: $0.0010","costEstimate":0.001,"provider":"google","visible":true,"isOpenSource":true,"dateAdded":"2026-05-01","maxInputTokens":262144,"category":"Roleplay/storytelling models","tags":["Thinking"],"labelVariant":"outline","capabilities":["reasoning","vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":3.06e-7,"output_price":3.06e-7,"input_price_per_million":0.306,"output_price_per_million":0.306,"input":0.306,"output":0.306,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000306","completion":"0.000000306","input":0.306,"output":0.306,"prompt_per_million":0.306,"completion_per_million":0.306,"prompt_per_token":"0.000000306","completion_per_token":"0.000000306","per_input_token":3.06e-7,"per_output_token":3.06e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"effective_price":{"inputPer1kTokens":0.000306,"outputPer1kTokens":0.000306},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":429.5},"GLM-4.6-Derestricted-v5":{"totalParams":357,"activeParams":32,"name":"GLM 4.6 Derestricted v5","model":"GLM-4.6-Derestricted-v5","description":"Derestricted GLM 4.6 tuned for open-ended creative writing and roleplay with relaxed filters.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"zhipu","visible":true,"isOpenSource":true,"maxInputTokens":131072,"category":"Uncensored","dateAdded":"2025-12-23","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":4e-7,"output_price":0.0000015,"input_price_per_million":0.4,"output_price_per_million":1.5,"input":0.4,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000015","input":0.4,"output":1.5,"prompt_per_million":0.4,"completion_per_million":1.5,"prompt_per_token":"0.0000004","completion_per_token":"0.0000015","per_input_token":4e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":851.7},"TEE/kimi-k2.6":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.6 TEE","model":"TEE/kimi-k2.6","description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model designed for long-horizon coding and agentic orchestration. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0028","costEstimate":0.00285,"label":"TEE","labelColor":"green","provider":"moonshot","visible":true,"isOpenSource":true,"capabilities":["vision","tool-calling"],"maxInputTokens":262144,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-04-21","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000015,"output_price":0.00000525,"input_price_per_million":1.5,"output_price_per_million":5.25,"input":1.5,"output":5.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.00000525","input":1.5,"output":5.25,"cacheReadInputPer1kTokens":0.000375,"prompt_per_million":1.5,"completion_per_million":5.25,"prompt_per_token":"0.0000015","completion_per_token":"0.00000525","per_input_token":0.0000015,"per_output_token":0.00000525},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.00525,"cacheReadInputPer1kTokens":0.000375},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.00525,"cacheReadInputPer1kTokens":0.000375},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":3135.7},"TEE/kimi-k2.7-code":{"totalParams":1000,"activeParams":32,"name":"Kimi K2.7 Code TEE","model":"TEE/kimi-k2.7-code","description":"Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode while running inside a Trusted Execution Environment (TEE) with attestation support.","cost":"Average cost: $0.0084","costEstimate":0.0084,"label":"TEE","labelColor":"green","provider":"moonshot","visible":true,"isOpenSource":true,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls"],"maxInputTokens":262144,"maxOutputTokens":65536,"category":"Private/TEE","dateAdded":"2026-08-15","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":9.5e-7,"output_price":0.000004,"input_price_per_million":0.95,"output_price_per_million":4,"input":0.95,"output":4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000095","completion":"0.000004","input":0.95,"output":4,"cacheReadInputPer1kTokens":0.00019,"prompt_per_million":0.95,"completion_per_million":4,"prompt_per_token":"0.00000095","completion_per_token":"0.000004","per_input_token":9.5e-7,"per_output_token":0.000004},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00095,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00019},"effective_price":{"inputPer1kTokens":0.00095,"outputPer1kTokens":0.004,"cacheReadInputPer1kTokens":0.00019},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1141.8},"TEE/glm-5.1":{"totalParams":744,"activeParams":40,"name":"GLM 5.1 TEE","model":"TEE/glm-5.1","description":"GLM-5.1 is Z.AI's next-gen model optimized for long-horizon agent workflows and deep reasoning. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0034","costEstimate":0.0034,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"isOpenSource":true,"maxInputTokens":202752,"maxOutputTokens":65535,"category":"Private/TEE","dateAdded":"2026-04-20","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"capabilities":["reasoning"],"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.0000015,"output_price":0.00000525,"input_price_per_million":1.5,"output_price_per_million":5.25,"input":1.5,"output":5.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.00000525","input":1.5,"output":5.25,"cacheReadInputPer1kTokens":0.0003,"prompt_per_million":1.5,"completion_per_million":5.25,"prompt_per_token":"0.0000015","completion_per_token":"0.00000525","per_input_token":0.0000015,"per_output_token":0.00000525},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.00525,"cacheReadInputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.00525,"cacheReadInputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":675.1},"TEE/glm-5.1-thinking":{"totalParams":744,"activeParams":40,"name":"GLM 5.1 Thinking TEE","model":"TEE/glm-5.1-thinking","description":"GLM-5.1 with extended reasoning mode for multi-step planning and tool-heavy workflows. Running inside a TEE (Trusted Execution Environment), with provider attestation support.","cost":"Average cost: $0.0034","costEstimate":0.0034,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":202752,"maxOutputTokens":65535,"category":"Private/TEE","dateAdded":"2026-04-20","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.0000015,"output_price":0.00000525,"input_price_per_million":1.5,"output_price_per_million":5.25,"input":1.5,"output":5.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.00000525","input":1.5,"output":5.25,"cacheReadInputPer1kTokens":0.0003,"prompt_per_million":1.5,"completion_per_million":5.25,"prompt_per_token":"0.0000015","completion_per_token":"0.00000525","per_input_token":0.0000015,"per_output_token":0.00000525},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.00525,"cacheReadInputPer1kTokens":0.0003},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.00525,"cacheReadInputPer1kTokens":0.0003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1261.2},"TEE/glm-5.2":{"totalParams":744,"activeParams":40,"name":"GLM 5.2 TEE","model":"TEE/glm-5.2","description":"GLM-5.2 is Z.AI's flagship model for long-horizon tasks and autonomous workflows, with a 1M-token context window. Running inside a TEE (Trusted Execution Environment), with attestation support.","cost":"Average cost: $0.0030","costEstimate":0.003,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"Private/TEE","dateAdded":"2026-06-16","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000014,"output_price":0.0000044,"input_price_per_million":1.4,"output_price_per_million":4.4,"input":1.4,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000014","completion":"0.0000044","input":1.4,"output":4.4,"cacheReadInputPer1kTokens":0.0007,"prompt_per_million":1.4,"completion_per_million":4.4,"prompt_per_token":"0.0000014","completion_per_token":"0.0000044","per_input_token":0.0000014,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1461.7},"TEE/glm-5.2:thinking":{"totalParams":744,"activeParams":40,"name":"GLM 5.2 Thinking TEE","model":"TEE/glm-5.2:thinking","description":"GLM-5.2 with thinking enabled for harder long-horizon coding, autonomous agent workflows, and complex engineering tasks. Running inside a TEE (Trusted Execution Environment), with attestation support.","cost":"Average cost: $0.0030","costEstimate":0.003,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"isOpenSource":true,"capabilities":["reasoning","tool-calling","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"Private/TEE","dateAdded":"2026-06-16","dsDelta":{"thinking":{"type":"enabled"},"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]}},"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000014,"output_price":0.0000044,"input_price_per_million":1.4,"output_price_per_million":4.4,"input":1.4,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000014","completion":"0.0000044","input":1.4,"output":4.4,"cacheReadInputPer1kTokens":0.0007,"prompt_per_million":1.4,"completion_per_million":4.4,"prompt_per_token":"0.0000014","completion_per_token":"0.0000044","per_input_token":0.0000014,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.0007},"effective_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.0007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1997.2},"TEE/glm-5.3":{"totalParams":744,"activeParams":40,"name":"GLM 5.3 TEE","model":"TEE/glm-5.3","description":"GLM-5.3 is Z.AI's open-weight reasoning model for complex software engineering, autonomous agents, vulnerability research, and long-horizon tasks. Reasoning is always on; choose low, high, or max reasoning effort (defaults to max). This text-only TEE deployment is verified through the selected provider: Redpill attestation with signed completion receipts or the official Tinfoil SDK's ATC/EHBP verification.","cost":"Input $1.40/m, Cached input $0.26/m, Output $4.40/m","costEstimate":0.0029,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"isOpenSource":true,"capabilities":["reasoning","tool-calling","parallel-tool-calls","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"Private/TEE","dateAdded":"2026-08-31","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":0.0000014,"output_price":0.0000044,"input_price_per_million":1.4,"output_price_per_million":4.4,"input":1.4,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000014","completion":"0.0000044","input":1.4,"output":4.4,"cacheReadInputPer1kTokens":0.00026,"prompt_per_million":1.4,"completion_per_million":4.4,"prompt_per_token":"0.0000014","completion_per_token":"0.0000044","per_input_token":0.0000014,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00026},"effective_price":{"inputPer1kTokens":0.0014,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00026},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1183.1},"TEE/glm-5.3-flash":{"totalParams":320,"activeParams":18,"name":"GLM 5.3 Flash TEE","model":"TEE/glm-5.3-flash","description":"GLM-5.3 Flash is Z.AI's natively multimodal 320B MoE reasoning model with 18B active parameters. This TEE deployment is verified through Redpill attestation with signed completion receipts.","cost":"Input $0.15/m, Cached input $0.03/m, Output $0.50/m","costEstimate":0.000325,"label":"TEE","labelColor":"green","provider":"zhipu","visible":true,"isOpenSource":true,"capabilities":["vision","reasoning","tool-calling","parallel-tool-calls","structured-output"],"maxInputTokens":1048576,"maxOutputTokens":131072,"category":"Private/TEE","dateAdded":"2026-08-28","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":0.95,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"max","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":1.5e-7,"output_price":5e-7,"input_price_per_million":0.15,"output_price_per_million":0.5,"input":0.15,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000005","input":0.15,"output":0.5,"cacheReadInputPer1kTokens":0.00003,"prompt_per_million":0.15,"completion_per_million":0.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000005","per_input_token":1.5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.00003},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.00003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":844.8},"venice-uncensored":{"totalParams":24,"name":"Venice Uncensored","model":"venice-uncensored","description":"Venice's uncensored model. Built on the Dolphin Mistral 24b model with a very low refusal rate.","cost":"Average cost: $0.0020","costEstimate":0.002,"dateAdded":"2025-10-01","provider":"venice","visible":true,"category":"Uncensored","maxInputTokens":128000,"maxOutputTokens":8192,"isOpenSource":true,"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000018,"input_price_per_million":0.4,"output_price_per_million":1.8,"input":0.4,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000018","input":0.4,"output":1.8,"cacheReadInputPer1kTokens":0.0004,"prompt_per_million":0.4,"completion_per_million":1.8,"prompt_per_token":"0.0000004","completion_per_token":"0.0000018","per_input_token":4e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018,"cacheReadInputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018,"cacheReadInputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":238.6},"kimi-k2-instruct-fast":{"totalParams":1000,"activeParams":32,"name":"Kimi K2 0711 Fast","model":"kimi-k2-instruct-fast","description":"Deprecated. This model now routes to Kimi K2 0711.","cost":"Average cost: $0.006","costEstimate":0.006,"dateAdded":"2025-12-15","provider":"moonshot","isOpenSource":true,"visible":true,"category":"More","capabilities":["pdf-upload"],"maxInputTokens":131072,"maxOutputTokens":16384,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.0000018,"input_price_per_million":0.4,"output_price_per_million":1.8,"input":0.4,"output":1.8,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.0000018","input":0.4,"output":1.8,"prompt_per_million":0.4,"completion_per_million":1.8,"prompt_per_token":"0.0000004","completion_per_token":"0.0000018","per_input_token":4e-7,"per_output_token":0.0000018},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.0018},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"}},"thinkingmachines/Inkling-Small":{"totalParams":276,"activeParams":12,"name":"Inkling Small","model":"thinkingmachines/Inkling-Small","description":"The direct-answer version of Thinking Machines' 276B-parameter open-weights multimodal Mixture-of-Experts model with 12B active parameters. It accepts text and images, and is designed for coding, tool use, instruction following, and general conversational work.","cost":"Input $0.50/m, Output $1.20/m, Cached input $0.10/m","costEstimate":0.0012,"provider":"together","visible":true,"maxInputTokens":524288,"maxOutputTokens":32768,"category":"More","dateAdded":"2026-07-31","capabilities":["vision","tool-calling","audio-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none","thinking":{"type":"disabled"}},"isOpenSource":true,"tags":["chat","vision","coding","agent"],"api":"chat","input_price":5e-7,"output_price":0.0000012,"input_price_per_million":0.5,"output_price_per_million":1.2,"input":0.5,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000012","input":0.5,"output":1.2,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":0.5,"completion_per_million":1.2,"prompt_per_token":"0.0000005","completion_per_token":"0.0000012","per_input_token":5e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":577},"thinkingmachines/Inkling-Small:thinking":{"totalParams":276,"activeParams":12,"name":"Inkling Small Thinking","model":"thinkingmachines/Inkling-Small:thinking","description":"The reasoning version of Thinking Machines' 276B-parameter open-weights multimodal Mixture-of-Experts model with 12B active parameters. It reasons over text and images, and is designed for agentic coding, tool use, instruction following, and long workflows with controllable thinking effort.","cost":"Input $0.50/m, Output $1.20/m, Cached input $0.10/m","costEstimate":0.0012,"provider":"together","visible":true,"maxInputTokens":524288,"maxOutputTokens":32768,"category":"More","dateAdded":"2026-07-31","capabilities":["vision","reasoning","tool-calling","audio-input"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","thinking":{"type":"enabled"}},"additionalParams":{"reasoning_effort":{"levels":["minimal","low","medium","high","max"]}},"isOpenSource":true,"tags":["chat","reasoning","vision","coding","agent"],"api":"chat","input_price":5e-7,"output_price":0.0000012,"input_price_per_million":0.5,"output_price_per_million":1.2,"input":0.5,"output":1.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000012","input":0.5,"output":1.2,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":0.5,"completion_per_million":1.2,"prompt_per_token":"0.0000005","completion_per_token":"0.0000012","per_input_token":5e-7,"per_output_token":0.0000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0012,"cacheReadInputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"}},"google/gemma-4-26b-a4b-it":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B","model":"google/gemma-4-26b-a4b-it","description":"Google's Gemma 4 26B A4B instruction-tuned model built for scalable reasoning, coding, long-context, and multimodal workflows. This route is tuned for faster direct answers while preserving multimodal and structured output support. Requests containing video cost $0.10 per million input tokens and $0.40 per million output tokens.","cost":"Input $0.12/m, Cached input $0.06/m, Output $0.38/m","costEstimate":0.00038,"dateAdded":"2026-04-02","provider":"google","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":131072,"capabilities":["vision","reasoning","structured-output","video-input"],"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.2e-7,"output_price":3.8e-7,"input_price_per_million":0.12,"output_price_per_million":0.38,"input":0.12,"output":0.38,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000012","completion":"0.00000038","input":0.12,"output":0.38,"cacheReadInputPer1kTokens":0.00006,"prompt_per_million":0.12,"completion_per_million":0.38,"prompt_per_token":"0.00000012","completion_per_token":"0.00000038","per_input_token":1.2e-7,"per_output_token":3.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"effective_price":{"inputPer1kTokens":0.00012,"outputPer1kTokens":0.00038,"cacheReadInputPer1kTokens":0.00006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":130.7},"google/gemma-4-26b-a4b-it:thinking":{"totalParams":26,"activeParams":4,"name":"Gemma 4 26B A4B Thinking","model":"google/gemma-4-26b-a4b-it:thinking","description":"Google's Gemma 4 26B A4B instruction-tuned model with structured reasoning for more deliberate coding, multimodal analysis, and long-context problem solving. Requests containing video cost $0.10 per million input tokens and $0.40 per million output tokens.","cost":"Average cost: $0.00027","costEstimate":0.000265,"dateAdded":"2026-04-02","provider":"google","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":131072,"capabilities":["vision","reasoning","structured-output","video-input"],"labelVariant":"outline","category":"More","tags":["Thinking"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.3e-7,"output_price":4e-7,"input_price_per_million":0.13,"output_price_per_million":0.4,"input":0.13,"output":0.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000013","completion":"0.0000004","input":0.13,"output":0.4,"prompt_per_million":0.13,"completion_per_million":0.4,"prompt_per_token":"0.00000013","completion_per_token":"0.0000004","per_input_token":1.3e-7,"per_output_token":4e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.0004},"effective_price":{"inputPer1kTokens":0.00013,"outputPer1kTokens":0.0004},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1077.5},"tencent/hy3":{"totalParams":295,"activeParams":21,"name":"Tencent Hy3","model":"tencent/hy3","description":"Hy3 is Tencent's 295B-parameter Mixture-of-Experts model with 21B active parameters, native 256K context, and configurable reasoning modes. It is built for coding, long-context comprehension, multi-turn dialogue, and agentic task execution with a focus on high-throughput production workloads.","cost":"Average cost: $0.00075","costEstimate":0.00075,"dateAdded":"2026-07-06","provider":"tencent","isOpenSource":false,"visible":true,"maxInputTokens":262144,"maxOutputTokens":262144,"capabilities":["reasoning","tool-calling","structured-output"],"labelVariant":"outline","category":"More","tags":["Thinking"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["none","low","high"]}},"api":"chat","input_price":6.6e-8,"output_price":2.6e-7,"input_price_per_million":0.066,"output_price_per_million":0.26,"input":0.066,"output":0.26,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000066","completion":"0.00000026","input":0.066,"output":0.26,"cacheReadInputPer1kTokens":0.000029,"prompt_per_million":0.066,"completion_per_million":0.26,"prompt_per_token":"0.000000066","completion_per_token":"0.00000026","per_input_token":6.6e-8,"per_output_token":2.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000066,"outputPer1kTokens":0.00026,"cacheReadInputPer1kTokens":0.000029},"effective_price":{"inputPer1kTokens":0.000066,"outputPer1kTokens":0.00026,"cacheReadInputPer1kTokens":0.000029},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":1390.2},"qwen/qwen3-coder-next":{"totalParams":80,"activeParams":3,"name":"Qwen3 Coder Next","model":"qwen/qwen3-coder-next","description":"Qwen3 Coder Next is an open-weight coding model built on Qwen3-Next-80B-A3B-Base (hybrid attention + MoE). It is agentically trained at scale on executable tasks and environment interaction, delivering strong coding and tool-use performance at lower inference cost. Native 256K context.","cost":"Average cost: $0.00085","costEstimate":0.00085,"dateAdded":"2025-12-08","provider":"qwen","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":65536,"capabilities":["tool-calling","structured-output"],"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-7,"output_price":0.0000015,"input_price_per_million":0.2,"output_price_per_million":1.5,"input":0.2,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000002","completion":"0.0000015","input":0.2,"output":1.5,"prompt_per_million":0.2,"completion_per_million":1.5,"prompt_per_token":"0.0000002","completion_per_token":"0.0000015","per_input_token":2e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.0002,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.388Z"},"avgOutputTokens":182.1},"inclusionai/ling-3.1-flash":{"name":"Ling 3.1 Flash","model":"inclusionai/ling-3.1-flash","description":"Ling 3.1 Flash is inclusionAI's hybrid reasoning model for coding, tool use, planning, and long-context agent workflows. It has 560B total parameters with 25B active parameters per token. Thinking is enabled by default and can be turned off in settings.","cost":"Input $0.075/M, Output $0.22/M, Cached input $0.015/M","costEstimate":0.0001475,"dateAdded":"2026-09-30","provider":"novita","isOpenSource":true,"visible":true,"totalParams":560,"activeParams":25,"maxInputTokens":262144,"maxOutputTokens":32768,"capabilities":["reasoning","tool-calling","structured-output"],"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":7.5e-8,"output_price":2.2e-7,"input_price_per_million":0.075,"output_price_per_million":0.22,"input":0.075,"output":0.22,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000075","completion":"0.00000022","input":0.075,"output":0.22,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.075,"completion_per_million":0.22,"prompt_per_token":"0.000000075","completion_per_token":"0.00000022","per_input_token":7.5e-8,"per_output_token":2.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00022,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00022,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":7787.5},"inclusionai/ling-3.0-flash-vl":{"name":"Ling 3.0 Flash VL","model":"inclusionai/ling-3.0-flash-vl","description":"Ling 3.0 Flash VL is inclusionAI's native multimodal Mixture-of-Experts model with 124B total parameters and 5.5B active parameters per token. It combines image and video understanding with reasoning and tool use for document analysis, charts, visual verification, and interface-based agent tasks. Thinking is enabled by default and can be turned off in settings.","cost":"Input $0.06/M, Output $0.18/M, Cached input $0.012/M","costEstimate":0.00012,"dateAdded":"2026-09-09","provider":"novita","isOpenSource":true,"visible":true,"totalParams":124,"activeParams":5.5,"maxInputTokens":262144,"maxOutputTokens":32768,"unsupportedResponseFormatTypes":["json_object","json_schema"],"capabilities":["vision","video-input","reasoning","tool-calling"],"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":6e-8,"output_price":1.8e-7,"input_price_per_million":0.06,"output_price_per_million":0.18,"input":0.06,"output":0.18,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000006","completion":"0.00000018","input":0.06,"output":0.18,"cacheReadInputPer1kTokens":0.000012,"prompt_per_million":0.06,"completion_per_million":0.18,"prompt_per_token":"0.00000006","completion_per_token":"0.00000018","per_input_token":6e-8,"per_output_token":1.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0.00018,"cacheReadInputPer1kTokens":0.000012},"effective_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0.00018,"cacheReadInputPer1kTokens":0.000012},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":842.5},"inclusionai/ling-3.0-flash":{"name":"Ling 3.0 Flash","model":"inclusionai/ling-3.0-flash","description":"Ling-3.0-flash is a 124B-parameter Mixture-of-Experts model with approximately 5.1B parameters active per token. It prioritizes token efficiency and production-scale agentic inference, helping coding and tool-using agents complete more work within constrained latency and serving budgets.","cost":"Input $0.075/M, Output $0.22/M","costEstimate":0.0001475,"dateAdded":"2026-07-23","provider":"novita","isOpenSource":false,"visible":true,"maxInputTokens":262144,"maxOutputTokens":32768,"capabilities":["tool-calling"],"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"none"},"api":"chat","input_price":7.5e-8,"output_price":2.2e-7,"input_price_per_million":0.075,"output_price_per_million":0.22,"input":0.075,"output":0.22,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000075","completion":"0.00000022","input":0.075,"output":0.22,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.075,"completion_per_million":0.22,"prompt_per_token":"0.000000075","completion_per_token":"0.00000022","per_input_token":7.5e-8,"per_output_token":2.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00022,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00022,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":1145.3},"inclusionai/ling-3.0-flash:thinking":{"name":"Ling 3.0 Flash Thinking","model":"inclusionai/ling-3.0-flash:thinking","description":"Ling-3.0-flash Thinking enables visible reasoning on inclusionAI's token-efficient 124B-parameter Mixture-of-Experts model for harder coding, tool use, planning, and production-scale agent workflows.","cost":"Input $0.075/M, Output $0.22/M","costEstimate":0.0001475,"dateAdded":"2026-07-23","provider":"novita","isOpenSource":false,"visible":true,"maxInputTokens":262144,"maxOutputTokens":32768,"capabilities":["reasoning","tool-calling"],"labelVariant":"outline","category":"More","tags":["Thinking"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","minimal","low","medium","high","xhigh"]}},"api":"chat","input_price":7.5e-8,"output_price":2.2e-7,"input_price_per_million":0.075,"output_price_per_million":0.22,"input":0.075,"output":0.22,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000075","completion":"0.00000022","input":0.075,"output":0.22,"cacheReadInputPer1kTokens":0.000015,"prompt_per_million":0.075,"completion_per_million":0.22,"prompt_per_token":"0.000000075","completion_per_token":"0.00000022","per_input_token":7.5e-8,"per_output_token":2.2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00022,"cacheReadInputPer1kTokens":0.000015},"effective_price":{"inputPer1kTokens":0.000075,"outputPer1kTokens":0.00022,"cacheReadInputPer1kTokens":0.000015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":242.9},"google/gemma-4-31b-it":{"totalParams":31,"name":"Gemma 4 31B","model":"google/gemma-4-31b-it","description":"Google's Gemma 4 31B instruction-tuned model for heavier reasoning, coding, agentic workflows, and long-context multimodal understanding. This route keeps tokenizer thinking disabled for faster direct answers. Requests containing video cost $0.14 per million input tokens and $0.40 per million output tokens.","cost":"Input $0.10/m, Cached input $0.05/m, Output $0.45/m","costEstimate":0.00045,"dateAdded":"2026-04-02","provider":"google","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":131072,"capabilities":["vision","reasoning","structured-output","video-input"],"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":4.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.45,"input":0.1,"output":0.45,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000045","input":0.1,"output":0.45,"cacheReadInputPer1kTokens":0.00005,"prompt_per_million":0.1,"completion_per_million":0.45,"prompt_per_token":"0.0000001","completion_per_token":"0.00000045","per_input_token":1e-7,"per_output_token":4.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00045,"cacheReadInputPer1kTokens":0.00005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":338.2},"google/gemma-4-31b-it:thinking":{"totalParams":31,"name":"Gemma 4 31B Thinking","model":"google/gemma-4-31b-it:thinking","description":"Google's Gemma 4 31B instruction-tuned model with thinking explicitly enabled, exposing reasoning traces for complex multimodal and coding workflows. Requests containing video cost $0.14 per million input tokens and $0.40 per million output tokens.","cost":"Average cost: $0.00027","costEstimate":0.00027,"dateAdded":"2026-04-02","provider":"google","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":131072,"capabilities":["vision","reasoning","structured-output","video-input"],"labelVariant":"outline","category":"More","tags":["Thinking"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":3.5e-7,"input_price_per_million":0.1,"output_price_per_million":0.35,"input":0.1,"output":0.35,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.00000035","input":0.1,"output":0.35,"prompt_per_million":0.1,"completion_per_million":0.35,"prompt_per_token":"0.0000001","completion_per_token":"0.00000035","per_input_token":1e-7,"per_output_token":3.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00035},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.00035},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":1117.1},"nvidia/nemotron-3-nano-30b-a3b":{"totalParams":30,"activeParams":3,"name":"Nvidia Nemotron 3 Nano 30B","model":"nvidia/nemotron-3-nano-30b-a3b","description":"Nvidia's latest Nemotron 3 Nano model with 30B total parameters (3B active) using hybrid Mamba-Transformer MoE architecture. Features excellent throughput and strong reasoning capabilities.","cost":"Average cost: $0.00015","costEstimate":0.00015,"dateAdded":"2026-03-01","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":256000,"maxOutputTokens":262144,"labelVariant":"outline","category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.7e-7,"output_price":6.8e-7,"input_price_per_million":0.17,"output_price_per_million":0.68,"input":0.17,"output":0.68,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000017","completion":"0.00000068","input":0.17,"output":0.68,"prompt_per_million":0.17,"completion_per_million":0.68,"prompt_per_token":"0.00000017","completion_per_token":"0.00000068","per_input_token":1.7e-7,"per_output_token":6.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00068},"effective_price":{"inputPer1kTokens":0.00017,"outputPer1kTokens":0.00068},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":563.8},"nvidia/nemotron-3-super-120b-a12b":{"totalParams":120,"activeParams":12,"name":"Nvidia Nemotron 3 Super 120B","model":"nvidia/nemotron-3-super-120b-a12b","description":"Nvidia's Nemotron 3 Super 120B A12B model from the March 2026 Nemotron 3 release. It uses a hybrid Mamba-Transformer MoE architecture and targets agentic and coding workloads with a 262K context window here.","cost":"Average cost: $0.0018","costEstimate":0.0018,"dateAdded":"2026-03-01","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":16384,"labelVariant":"outline","category":"More","toolCallingUnsupported":true,"capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":2.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.25,"input":0.05,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000025","input":0.05,"output":0.25,"prompt_per_million":0.05,"completion_per_million":0.25,"prompt_per_token":"0.00000005","completion_per_token":"0.00000025","per_input_token":5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":431.4},"nvidia/nemotron-3-super-120b-a12b:thinking":{"totalParams":120,"activeParams":12,"name":"Nvidia Nemotron 3 Super 120B Thinking","model":"nvidia/nemotron-3-super-120b-a12b:thinking","description":"Nvidia Nemotron 3 Super 120B with reasoning content enabled. Returns separate thinking content when requested.","cost":"Average cost: $0.0018","costEstimate":0.0018,"dateAdded":"2026-03-01","provider":"nvidia","isOpenSource":true,"visible":true,"maxInputTokens":262144,"maxOutputTokens":16384,"labelVariant":"outline","category":"More","tags":["Thinking"],"toolCallingUnsupported":true,"capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-8,"output_price":2.5e-7,"input_price_per_million":0.05,"output_price_per_million":0.25,"input":0.05,"output":0.25,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000005","completion":"0.00000025","input":0.05,"output":0.25,"prompt_per_million":0.05,"completion_per_million":0.25,"prompt_per_token":"0.00000005","completion_per_token":"0.00000025","per_input_token":5e-8,"per_output_token":2.5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025},"effective_price":{"inputPer1kTokens":0.00005,"outputPer1kTokens":0.00025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":620.8},"meganova-ai/manta-mini-1.0":{"name":"Manta Mini 1.0","model":"meganova-ai/manta-mini-1.0","description":"Lightweight tier optimized for speed and cost.","cost":"Average cost: $0.00009","costEstimate":0.00009,"dateAdded":"2025-09-20","provider":"meganova","visible":true,"maxInputTokens":8192,"maxOutputTokens":8192,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-8,"output_price":1.6e-7,"input_price_per_million":0.02,"output_price_per_million":0.16,"input":0.02,"output":0.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000002","completion":"0.00000016","input":0.02,"output":0.16,"prompt_per_million":0.02,"completion_per_million":0.16,"prompt_per_token":"0.00000002","completion_per_token":"0.00000016","per_input_token":2e-8,"per_output_token":1.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0.00016},"effective_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0.00016},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":34.5},"meganova-ai/manta-flash-1.0":{"name":"Manta Flash 1.0","model":"meganova-ai/manta-flash-1.0","description":"The flagship model for balanced reasoning and context-rich dialogue. Perfect for AI roleplay, storytelling, and assistant tasks with a 16K window.","cost":"Average cost: $0.00016","costEstimate":0.00016,"dateAdded":"2025-09-20","provider":"meganova","visible":true,"maxInputTokens":16384,"maxOutputTokens":16384,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2e-8,"output_price":1.6e-7,"input_price_per_million":0.02,"output_price_per_million":0.16,"input":0.02,"output":0.16,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000002","completion":"0.00000016","input":0.02,"output":0.16,"prompt_per_million":0.02,"completion_per_million":0.16,"prompt_per_token":"0.00000002","completion_per_token":"0.00000016","per_input_token":2e-8,"per_output_token":1.6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0.00016},"effective_price":{"inputPer1kTokens":0.00002,"outputPer1kTokens":0.00016},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":190.5},"meganova-ai/manta-pro-1.0":{"name":"Manta Pro 1.0","model":"meganova-ai/manta-pro-1.0","description":"Tailored for deep reasoning, long-form generation, and RAG workloads. 32K token context window.","cost":"Average cost: $0.00028","costEstimate":0.00028,"dateAdded":"2025-09-20","provider":"meganova","visible":true,"maxInputTokens":32768,"maxOutputTokens":32768,"category":"Roleplay/storytelling models","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":6e-8,"output_price":5e-7,"input_price_per_million":0.06,"output_price_per_million":0.5,"input":0.06,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000006","completion":"0.0000005","input":0.06,"output":0.5,"prompt_per_million":0.06,"completion_per_million":0.5,"prompt_per_token":"0.00000006","completion_per_token":"0.0000005","per_input_token":6e-8,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0.0005},"effective_price":{"inputPer1kTokens":0.00006,"outputPer1kTokens":0.0005},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":198.4},"openai/gpt-4o":{"name":"GPT-4o","model":"openai/gpt-4o","description":"OpenAI's flagship multimodal model, handling text, images, and audio. Exceptional at understanding context and generating human-like responses.","cost":"Average cost: $0.0075","costEstimate":0.0075,"dateAdded":"2025-05-13","provider":"openai","visible":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00125,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00125},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":101.4},"openai/gpt-4o-mini":{"name":"GPT-4o mini","model":"openai/gpt-4o-mini","description":"OpenAI's most cost-efficient small model. Cheaper and smarter than GPT-3.5 (the original ChatGPT), but less performant than gpt-4o.","cost":"Average cost: $0.0011","costEstimate":0.0011,"provider":"openai","visible":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1.5e-7,"output_price":6e-7,"input_price_per_million":0.15,"output_price_per_million":0.6,"input":0.15,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000006","input":0.15,"output":0.6,"cacheReadInputPer1kTokens":0.000075,"prompt_per_million":0.15,"completion_per_million":0.6,"prompt_per_token":"0.00000015","completion_per_token":"0.0000006","per_input_token":1.5e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000075},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0006,"cacheReadInputPer1kTokens":0.000075},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":29.3},"openai/gpt-4o-2024-08-06":{"name":"GPT-4o (2024-08-06)","model":"openai/gpt-4o-2024-08-06","description":"OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.","cost":"Average cost: $0.0075","costEstimate":0.0075,"provider":"openai","visible":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00125,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00125},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":44.2},"openai/gpt-4o-2024-11-20":{"name":"GPT-4o (2024-11-20)","model":"openai/gpt-4o-2024-11-20","description":"OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.","cost":"Average cost: $0.0075","costEstimate":0.0075,"provider":"openai","visible":true,"maxInputTokens":128000,"maxOutputTokens":16384,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.0000025,"output_price":0.00001,"input_price_per_million":2.5,"output_price_per_million":10,"input":2.5,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000025","completion":"0.00001","input":2.5,"output":10,"cacheReadInputPer1kTokens":0.00125,"prompt_per_million":2.5,"completion_per_million":10,"prompt_per_token":"0.0000025","completion_per_token":"0.00001","per_input_token":0.0000025,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00125},"effective_price":{"inputPer1kTokens":0.0025,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.00125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":54.3},"openai/gpt-4-turbo":{"name":"GPT-4 Turbo","model":"openai/gpt-4-turbo","description":"Can take in the largest messages (up to 300 pages of context), and all round seen as one of the best in class models.","cost":"Average cost: $0.02","costEstimate":0.02,"provider":"openai","visible":true,"maxInputTokens":128000,"maxOutputTokens":4096,"category":"More","capabilities":["vision"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":0.00001,"output_price":0.00003,"input_price_per_million":10,"output_price_per_million":30,"input":10,"output":30,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00003","input":10,"output":30,"prompt_per_million":10,"completion_per_million":30,"prompt_per_token":"0.00001","completion_per_token":"0.00003","per_input_token":0.00001,"per_output_token":0.00003},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.03},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.03},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"}},"openai/gpt-3.5-turbo":{"name":"GPT-3.5 Turbo","model":"openai/gpt-3.5-turbo","description":"Older model. Brought ChatGPT to the mainstream, seen as dated nowadays. 90% cheaper than GPT-4-Turbo, recommended for very simple tasks.","cost":"Average cost: $0.0015","costEstimate":0.0015,"provider":"openai","visible":true,"maxInputTokens":16385,"maxOutputTokens":4096,"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":5e-7,"output_price":0.0000015,"input_price_per_million":0.5,"output_price_per_million":1.5,"input":0.5,"output":1.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000005","completion":"0.0000015","input":0.5,"output":1.5,"prompt_per_million":0.5,"completion_per_million":1.5,"prompt_per_token":"0.0000005","completion_per_token":"0.0000015","per_input_token":5e-7,"per_output_token":0.0000015},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015},"effective_price":{"inputPer1kTokens":0.0005,"outputPer1kTokens":0.0015},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"}},"openai/o1":{"name":"OpenAI o1","model":"openai/o1","description":"Useful when tackling complex problems in science, coding, math, and similar fields. Outdated compared to the newer o3 and o4 models.","cost":"Average cost: $0.045","costEstimate":0.045,"provider":"openai","visible":true,"maxInputTokens":200000,"maxOutputTokens":100000,"category":"More","capabilities":["reasoning"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000015,"output_price":0.00006,"input_price_per_million":15,"output_price_per_million":60,"input":15,"output":60,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000015","completion":"0.00006","input":15,"output":60,"cacheReadInputPer1kTokens":0.0075,"prompt_per_million":15,"completion_per_million":60,"prompt_per_token":"0.000015","completion_per_token":"0.00006","per_input_token":0.000015,"per_output_token":0.00006},"effective_pricing":{"list_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.06,"cacheReadInputPer1kTokens":0.0075},"effective_price":{"inputPer1kTokens":0.015,"outputPer1kTokens":0.06,"cacheReadInputPer1kTokens":0.0075},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"},"avgOutputTokens":27.8},"openai/o3-mini":{"name":"OpenAI o3-mini","model":"openai/o3-mini","description":"OpenAI o3-mini is a compact reasoning model for math, science, and coding, with up to 100,000 output tokens.","cost":"Average cost: $0.0033","costEstimate":0.0033,"provider":"openai","visible":true,"maxInputTokens":200000,"maxOutputTokens":100000,"category":"More","capabilities":["vision-by-description","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000044,"input_price_per_million":1.1,"output_price_per_million":4.4,"input":1.1,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000044","input":1.1,"output":4.4,"cacheReadInputPer1kTokens":0.00055,"prompt_per_million":1.1,"completion_per_million":4.4,"prompt_per_token":"0.0000011","completion_per_token":"0.0000044","per_input_token":0.0000011,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"}},"openai/o3-mini-high":{"name":"OpenAI o3-mini (High)","model":"openai/o3-mini-high","description":"OpenAI's o3-mini reasoning model with reasoning effort set to high.","cost":"Average cost: $0.009","costEstimate":0.009,"provider":"openai","visible":true,"maxInputTokens":200000,"maxOutputTokens":100000,"category":"More","capabilities":["vision-by-description","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000044,"input_price_per_million":1.1,"output_price_per_million":4.4,"input":1.1,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000044","input":1.1,"output":4.4,"cacheReadInputPer1kTokens":0.00055,"prompt_per_million":1.1,"completion_per_million":4.4,"prompt_per_token":"0.0000011","completion_per_token":"0.0000044","per_input_token":0.0000011,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"}},"openai/o3-mini-low":{"name":"OpenAI o3-mini (Low)","model":"openai/o3-mini-low","description":"OpenAI's o3-mini reasoning model with reasoning effort set to low.","cost":"Average cost: $0.002","costEstimate":0.002,"dateAdded":"2026-01-31","provider":"openai","visible":true,"maxInputTokens":200000,"maxOutputTokens":100000,"category":"More","capabilities":["vision-by-description","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.0000011,"output_price":0.0000044,"input_price_per_million":1.1,"output_price_per_million":4.4,"input":1.1,"output":4.4,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000011","completion":"0.0000044","input":1.1,"output":4.4,"cacheReadInputPer1kTokens":0.00055,"prompt_per_million":1.1,"completion_per_million":4.4,"prompt_per_token":"0.0000011","completion_per_token":"0.0000044","per_input_token":0.0000011,"per_output_token":0.0000044},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"effective_price":{"inputPer1kTokens":0.0011,"outputPer1kTokens":0.0044,"cacheReadInputPer1kTokens":0.00055},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"}},"openai/o3-pro-2025-06-10":{"name":"OpenAI o3-pro (2025-06-10)","model":"openai/o3-pro-2025-06-10","description":"The pro version of the already fantastic o3.","cost":"Average cost: $0.60","costEstimate":0.6,"provider":"openai","visible":true,"maxInputTokens":200000,"maxOutputTokens":100000,"category":"More","capabilities":["vision-by-description","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":0.000022,"output_price":0.000088,"input_price_per_million":22,"output_price_per_million":88,"input":22,"output":88,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000022","completion":"0.000088","input":22,"output":88,"cacheReadInputPer1kTokens":0.011,"prompt_per_million":22,"completion_per_million":88,"prompt_per_token":"0.000022","completion_per_token":"0.000088","per_input_token":0.000022,"per_output_token":0.000088},"effective_pricing":{"list_price":{"inputPer1kTokens":0.022,"outputPer1kTokens":0.088,"cacheReadInputPer1kTokens":0.011},"effective_price":{"inputPer1kTokens":0.022,"outputPer1kTokens":0.088,"cacheReadInputPer1kTokens":0.011},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.389Z"}},"openai/gpt-5.1-2025-11-13":{"name":"GPT-5.1 (2025-11-13)","model":"openai/gpt-5.1-2025-11-13","description":"Version-pinned snapshot of GPT-5.1 from the November 13, 2025 release. Use this when audits or regulated workflows require deterministic behavior.","cost":"Average cost: $0.006","costEstimate":0.006,"provider":"openai","visible":true,"maxInputTokens":1000000,"maxOutputTokens":32768,"capabilities":["reasoning","tool-calling","structured-output"],"category":"More","defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]},"reasoning_summary":true,"verbosity":true},"api":"chat","input_price":0.00000125,"output_price":0.00001,"input_price_per_million":1.25,"output_price_per_million":10,"input":1.25,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000125","completion":"0.00001","input":1.25,"output":10,"cacheReadInputPer1kTokens":0.000125,"prompt_per_million":1.25,"completion_per_million":10,"prompt_per_token":"0.00000125","completion_per_token":"0.00001","per_input_token":0.00000125,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"effective_price":{"inputPer1kTokens":0.00125,"outputPer1kTokens":0.01,"cacheReadInputPer1kTokens":0.000125},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"}},"mistral-code-agent-latest":{"totalParams":123,"name":"Mistral Code Agent Latest","model":"mistral-code-agent-latest","description":"Mistral Code Agent Latest is Mistral's direct API alias for devstral-2512, an agentic coding model built for autonomous software engineering, tool use, and long-running code tasks.","cost":"Average cost: $0.0024","costEstimate":0.0024,"provider":"mistral","labelVariant":"outline","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-06-02","maxInputTokens":262144,"maxOutputTokens":32768,"capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":0.2,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4e-7,"output_price":0.000002,"input_price_per_million":0.4,"output_price_per_million":2,"input":0.4,"output":2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000004","completion":"0.000002","input":0.4,"output":2,"prompt_per_million":0.4,"completion_per_million":2,"prompt_per_token":"0.0000004","completion_per_token":"0.000002","per_input_token":4e-7,"per_output_token":0.000002},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.002},"effective_price":{"inputPer1kTokens":0.0004,"outputPer1kTokens":0.002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":315.5},"mistral-code-latest":{"name":"Mistral Code Latest","model":"mistral-code-latest","description":"Mistral Code Latest is Mistral's direct API alias for codestral-2508, a low-latency coding model for code generation, completion, fill-in-the-middle workflows, function calling, and structured output.","cost":"Average cost: $0.0012","costEstimate":0.0012,"provider":"mistral","labelVariant":"outline","visible":true,"category":"More","isOpenSource":false,"dateAdded":"2026-06-02","maxInputTokens":256000,"maxOutputTokens":32768,"capabilities":["tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":0.3,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":9e-7,"input_price_per_million":0.3,"output_price_per_million":0.9,"input":0.3,"output":0.9,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000009","input":0.3,"output":0.9,"prompt_per_million":0.3,"completion_per_million":0.9,"prompt_per_token":"0.0000003","completion_per_token":"0.0000009","per_input_token":3e-7,"per_output_token":9e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0009},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0009},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"}},"mistral/mistral-large-4":{"totalParams":1050,"name":"Mistral Large 4","model":"mistralai/mistral-large-4","description":"Mistral Large 4 is an open-weight multimodal mixture-of-experts model with 1.05T total and 49B active parameters, built for reasoning, coding, tool use, and structured output. It supports a 512K-token context window.","cost":"Average cost: $0.00277","costEstimate":0.00277,"provider":"mistral","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-10-06","maxInputTokens":524288,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":6.8e-7,"output_price":0.00000209,"input_price_per_million":0.68,"output_price_per_million":2.09,"input":0.68,"output":2.09,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000068","completion":"0.00000209","input":0.68,"output":2.09,"cacheReadInputPer1kTokens":0.00007,"prompt_per_million":0.68,"completion_per_million":2.09,"prompt_per_token":"0.00000068","completion_per_token":"0.00000209","per_input_token":6.8e-7,"per_output_token":0.00000209},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00068,"outputPer1kTokens":0.00209,"cacheReadInputPer1kTokens":0.00007},"effective_price":{"inputPer1kTokens":0.00068,"outputPer1kTokens":0.00209,"cacheReadInputPer1kTokens":0.00007},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":3299.9},"mistral/mistral-medium-3.5":{"totalParams":128,"name":"Mistral Medium 3.5","model":"mistralai/mistral-medium-3.5","description":"Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.","cost":"Average cost: $0.009","costEstimate":0.009,"provider":"mistral","labelVariant":"outline","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-04-29","maxInputTokens":256000,"maxOutputTokens":32768,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.0000015,"output_price":0.0000075,"input_price_per_million":1.5,"output_price_per_million":7.5,"input":1.5,"output":7.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.0000075","input":1.5,"output":7.5,"prompt_per_million":1.5,"completion_per_million":7.5,"prompt_per_token":"0.0000015","completion_per_token":"0.0000075","per_input_token":0.0000015,"per_output_token":0.0000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.0075},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.0075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":451.3},"mistral/mistral-medium-3.5:thinking":{"totalParams":128,"name":"Mistral Medium 3.5 Thinking","model":"mistralai/mistral-medium-3.5:thinking","description":"Mistral Medium 3.5 with reasoning enabled by default (reasoning_effort=high), for complex coding, agentic, and multi-step reasoning prompts.","cost":"Average cost: $0.009","costEstimate":0.009,"provider":"mistral","labelVariant":"outline","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-04-30","maxInputTokens":256000,"maxOutputTokens":32768,"capabilities":["vision","reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"high"},"additionalParams":{"reasoning_effort":{"levels":["none","high"]}},"api":"chat","input_price":0.0000015,"output_price":0.0000075,"input_price_per_million":1.5,"output_price_per_million":7.5,"input":1.5,"output":7.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000015","completion":"0.0000075","input":1.5,"output":7.5,"prompt_per_million":1.5,"completion_per_million":7.5,"prompt_per_token":"0.0000015","completion_per_token":"0.0000075","per_input_token":0.0000015,"per_output_token":0.0000075},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.0075},"effective_price":{"inputPer1kTokens":0.0015,"outputPer1kTokens":0.0075},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":349.2},"synth-2.5-flash":{"name":"Synth 2.5 Flash Preview","model":"synth-2.5-flash","description":"Synth 2.5 Flash Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.","cost":"Average cost: $0.00008","costEstimate":0.00008,"provider":"lucidity","visible":true,"category":"Roleplay/storytelling models","dateAdded":"2026-09-05","maxInputTokens":30000,"toolCallingUnsupported":true,"unsupportedResponseFormatTypes":["json_object","json_schema"],"capabilities":[],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-8,"output_price":1e-7,"input_price_per_million":0.03,"output_price_per_million":0.1,"input":0.03,"output":0.1,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000003","completion":"0.0000001","input":0.03,"output":0.1,"prompt_per_million":0.03,"completion_per_million":0.1,"prompt_per_token":"0.00000003","completion_per_token":"0.0000001","per_input_token":3e-8,"per_output_token":1e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.0001},"effective_price":{"inputPer1kTokens":0.00003,"outputPer1kTokens":0.0001},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"}},"synth-2.5-pro":{"name":"Synth 2.5 Pro Preview","model":"synth-2.5-pro","description":"Synth 2.5 Pro Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.","cost":"Average cost: $0.00015","costEstimate":0.00015,"provider":"lucidity","visible":true,"category":"Roleplay/storytelling models","dateAdded":"2026-09-05","maxInputTokens":30000,"toolCallingUnsupported":true,"unsupportedResponseFormatTypes":["json_object","json_schema"],"capabilities":[],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":1e-7,"output_price":2e-7,"input_price_per_million":0.1,"output_price_per_million":0.2,"input":0.1,"output":0.2,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000002","input":0.1,"output":0.2,"prompt_per_million":0.1,"completion_per_million":0.2,"prompt_per_token":"0.0000001","completion_per_token":"0.0000002","per_input_token":1e-7,"per_output_token":2e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0002},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"}},"ultramarine-1-flash":{"name":"Ultramarine 1 Flash","model":"paperinstruments/ultramarine-1-flash","description":"Paper Instruments’ reasoning model for writing, knowledge work, and document tasks. Supports image inputs, tools, structured output, and low, high, or max reasoning effort. Reasoning is always enabled.","cost":"Average cost: $0.0004","costEstimate":0.0004,"provider":"paperinstruments","visible":true,"category":"More","dateAdded":"2026-10-15","maxOutputTokens":32768,"maxImageInputs":16,"isOpenSource":false,"capabilities":["reasoning","vision","tool-calling","parallel-tool-calls","structured-output"],"defaultThinkingEnabled":true,"defaultReasoningEffort":"max","defaultSettings":{"stream":true,"reasoning_effort":"max"},"additionalParams":{"reasoning_effort":{"levels":["low","high","max"]}},"api":"chat","input_price":1.5e-7,"output_price":5e-7,"input_price_per_million":0.15,"output_price_per_million":0.5,"input":0.15,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000015","completion":"0.0000005","input":0.15,"output":0.5,"cacheReadInputPer1kTokens":0.00003,"prompt_per_million":0.15,"completion_per_million":0.5,"prompt_per_token":"0.00000015","completion_per_token":"0.0000005","per_input_token":1.5e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.00003},"effective_price":{"inputPer1kTokens":0.00015,"outputPer1kTokens":0.0005,"cacheReadInputPer1kTokens":0.00003},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":1353.4},"aisingapore/Qwen-SEA-LION-v4-32B-IT":{"name":"Qwen SEA-LION v4 32B","model":"aisingapore/qwen-sea-lion-v4-32b-it","isOpenSource":true,"description":"AI Singapore’s Qwen-based multilingual model, adapted for Southeast Asian languages and cultural contexts. Supports text chat and tool calling with a 128K context window.","totalParams":32,"cost":"Average cost: $0.0004","costEstimate":0.0004,"provider":"publicai","visible":true,"category":"More","dateAdded":"2026-10-15","maxInputTokens":131072,"capabilities":["tool-calling"],"toolCallingUnsupported":false,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":3e-7,"output_price":6e-7,"input_price_per_million":0.3,"output_price_per_million":0.6,"input":0.3,"output":0.6,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000003","completion":"0.0000006","input":0.3,"output":0.6,"prompt_per_million":0.3,"completion_per_million":0.6,"prompt_per_token":"0.0000003","completion_per_token":"0.0000006","per_input_token":3e-7,"per_output_token":6e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0006},"effective_price":{"inputPer1kTokens":0.0003,"outputPer1kTokens":0.0006},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":30.6},"aisingapore/Gemma-SEA-LION-v4-27B-IT":{"name":"Gemma SEA-LION v4 27B","model":"aisingapore/gemma-sea-lion-v4-27b-it","isOpenSource":false,"description":"AI Singapore’s Gemma-based model for text chat in Southeast Asian languages, with a 128K context window. Open weights under the Gemma license; this route supports text input only.","totalParams":27,"cost":"Average cost: $0.0003","costEstimate":0.0003,"provider":"publicai","visible":true,"category":"More","dateAdded":"2026-10-15","maxInputTokens":131072,"capabilities":[],"toolCallingUnsupported":true,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":2.4e-7,"output_price":4.8e-7,"input_price_per_million":0.24,"output_price_per_million":0.48,"input":0.24,"output":0.48,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000024","completion":"0.00000048","input":0.24,"output":0.48,"prompt_per_million":0.24,"completion_per_million":0.48,"prompt_per_token":"0.00000024","completion_per_token":"0.00000048","per_input_token":2.4e-7,"per_output_token":4.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00024,"outputPer1kTokens":0.00048},"effective_price":{"inputPer1kTokens":0.00024,"outputPer1kTokens":0.00048},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":198.7},"speakleash/Bielik-11B-v3.0-Instruct":{"name":"Bielik 11B v3.0","model":"speakleash/bielik-11b-v3.0-instruct","isOpenSource":true,"description":"SpeakLeash’s Polish-focused multilingual model for conversation, writing and text analysis across European languages. Supports tool calling with a 32K context window.","totalParams":11,"cost":"Average cost: $0.0004","costEstimate":0.0004,"provider":"publicai","visible":true,"category":"More","dateAdded":"2026-10-15","maxInputTokens":32768,"capabilities":["tool-calling"],"toolCallingUnsupported":false,"unsupportedResponseFormatTypes":["json_object","json_schema"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"api":"chat","input_price":4.8e-7,"output_price":4.8e-7,"input_price_per_million":0.48,"output_price_per_million":0.48,"input":0.48,"output":0.48,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00000048","completion":"0.00000048","input":0.48,"output":0.48,"prompt_per_million":0.48,"completion_per_million":0.48,"prompt_per_token":"0.00000048","completion_per_token":"0.00000048","per_input_token":4.8e-7,"per_output_token":4.8e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.00048,"outputPer1kTokens":0.00048},"effective_price":{"inputPer1kTokens":0.00048,"outputPer1kTokens":0.00048},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":181.1},"aleph-alpha/kolibri-1":{"name":"Kolibri 1","model":"aleph-alpha/kolibri-1","description":"Kolibri 1 is Aleph Alpha’s open-weight reasoning model for German and English, hosted by Munito in the EU. It supports a one-million-token context, tool calling, structured output, and adjustable reasoning.","cost":"Average cost: $0.00067","costEstimate":0.000672,"provider":"aleph-alpha","visible":true,"category":"More","isOpenSource":true,"dateAdded":"2026-10-17","maxInputTokens":1048576,"maxOutputTokens":943718,"capabilities":["reasoning","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"low"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high"]}},"api":"chat","input_price":1.68e-7,"output_price":5.88e-7,"input_price_per_million":0.168,"output_price_per_million":0.588,"input":0.168,"output":0.588,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000168","completion":"0.000000588","input":0.168,"output":0.588,"cacheReadInputPer1kTokens":0.0000987,"prompt_per_million":0.168,"completion_per_million":0.588,"prompt_per_token":"0.000000168","completion_per_token":"0.000000588","per_input_token":1.68e-7,"per_output_token":5.88e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000168,"outputPer1kTokens":0.000588,"cacheReadInputPer1kTokens":0.0000987},"effective_price":{"inputPer1kTokens":0.000168,"outputPer1kTokens":0.000588,"cacheReadInputPer1kTokens":0.0000987},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":1178.1},"sarvam-105b":{"totalParams":105,"name":"Sarvam 105B","model":"sarvam-105b","description":"Sarvam 105B is a 105B parameter chat completion model from Sarvam AI with multilingual support, streaming, tool calling, reasoning controls, and a 128k context window.","cost":"Average cost: $0.0002","costEstimate":0.0002,"provider":"sarvam","visible":true,"category":"More","dateAdded":"2026-05-12","maxInputTokens":131072,"maxOutputTokens":4096,"capabilities":["reasoning","tool-calling"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high"]}},"api":"chat","input_price":5.4e-8,"output_price":2.124e-7,"input_price_per_million":0.054,"output_price_per_million":0.2124,"input":0.054,"output":0.2124,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000000054","completion":"0.0000002124","input":0.054,"output":0.2124,"cacheReadInputPer1kTokens":0.0000336,"prompt_per_million":0.054,"completion_per_million":0.2124,"prompt_per_token":"0.000000054","completion_per_token":"0.0000002124","per_input_token":5.4e-8,"per_output_token":2.124e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.000054,"outputPer1kTokens":0.0002124,"cacheReadInputPer1kTokens":0.0000336},"effective_price":{"inputPer1kTokens":0.000054,"outputPer1kTokens":0.0002124,"cacheReadInputPer1kTokens":0.0000336},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":1116.8},"openai/gpt-astra-latest":{"name":"GPT Astra Latest","model":"openai/gpt-astra-latest","description":"Compatibility alias that routes to GPT 6 Astra, the latest supported GPT Astra model.","cost":"Average cost: $0.06","costEstimate":0.06,"dateAdded":"2026-09-11","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","cybersecurity","gpt-6","astra","latest"],"api":"chat","input_price":0.00001,"output_price":0.00005,"input_price_per_million":10,"output_price_per_million":50,"input":10,"output":50,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.00001","completion":"0.00005","input":10,"output":50,"cacheReadInputPer1kTokens":0.001,"prompt_per_million":10,"completion_per_million":50,"prompt_per_token":"0.00001","completion_per_token":"0.00005","per_input_token":0.00001,"per_output_token":0.00005},"effective_pricing":{"list_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"effective_price":{"inputPer1kTokens":0.01,"outputPer1kTokens":0.05,"inputPer1kTokensAbove200k":0.02,"outputPer1kTokensAbove200k":0.075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.001,"cacheReadInputPer1kTokensAbove200k":0.002,"cacheWriteInputPer1kTokens":0.0125,"cacheWriteInputPer1kTokensAbove200k":0.025},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":599.3},"openai/gpt-luna-latest":{"name":"GPT Luna Latest","model":"openai/gpt-luna-latest","description":"Compatibility alias that routes to GPT 6 Luna, the latest supported GPT Luna model.","cost":"Input $0.10/M, Cached input $0.01/M, Output $0.50/M; at 272K+ input tokens: Input $0.20/M, Cached input $0.02/M, Output $0.75/M","costEstimate":0.0006,"dateAdded":"2026-09-11","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"none","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["fast","reasoning","chat","agentic","gpt-6","luna","latest"],"api":"chat","input_price":1e-7,"output_price":5e-7,"input_price_per_million":0.1,"output_price_per_million":0.5,"input":0.1,"output":0.5,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.0000001","completion":"0.0000005","input":0.1,"output":0.5,"cacheReadInputPer1kTokens":0.00001,"prompt_per_million":0.1,"completion_per_million":0.5,"prompt_per_token":"0.0000001","completion_per_token":"0.0000005","per_input_token":1e-7,"per_output_token":5e-7},"effective_pricing":{"list_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.00075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAbove200k":0.00002,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"effective_price":{"inputPer1kTokens":0.0001,"outputPer1kTokens":0.0005,"inputPer1kTokensAbove200k":0.0002,"outputPer1kTokensAbove200k":0.00075,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.00001,"cacheReadInputPer1kTokensAbove200k":0.00002,"cacheWriteInputPer1kTokens":0.000125,"cacheWriteInputPer1kTokensAbove200k":0.00025},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":446.5},"openai/gpt-sol-latest":{"name":"GPT Sol Latest","model":"openai/gpt-sol-latest","description":"Compatibility alias that routes to GPT 6.1 Sol, the latest supported GPT Sol model.","cost":"Input $2.00/M, Cached input $0.10/M, Output $10.00/M","costEstimate":0.012,"dateAdded":"2026-09-11","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"none","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["advanced","reasoning","coding","agentic","gpt-6","sol","latest"],"api":"chat","input_price":0.000002,"output_price":0.00001,"input_price_per_million":2,"output_price_per_million":10,"input":2,"output":10,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.00001","input":2,"output":10,"cacheReadInputPer1kTokens":0.0001,"prompt_per_million":2,"completion_per_million":10,"prompt_per_token":"0.000002","completion_per_token":"0.00001","per_input_token":0.000002,"per_output_token":0.00001},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0001,"cacheReadInputPer1kTokensAbove200k":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.01,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.015,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0001,"cacheReadInputPer1kTokensAbove200k":0.0002,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":538.6},"openai/gpt-terra-latest":{"name":"GPT Terra Latest","model":"openai/gpt-terra-latest","description":"Compatibility alias that routes to GPT 5.6 Terra, the latest supported GPT Terra model.","cost":"Average cost: $0.014","costEstimate":0.014,"dateAdded":"2026-09-11","provider":"openai","visible":true,"maxInputTokens":1050000,"maxOutputTokens":128000,"capabilities":["vision","reasoning","pdf-upload","tool-calling","structured-output"],"defaultSettings":{"stream":true,"temperature":1,"minP":0,"topP":1,"topK":0,"topA":0,"frequencyPenalty":0,"presencePenalty":0,"repetitionPenalty":1,"motion":false,"responseFormat":null,"structuredOutputs":false,"reasoning_effort":"medium","reasoning_summary":"detailed","verbosity":"medium"},"additionalParams":{"reasoning_effort":{"levels":["none","low","medium","high","xhigh","max"]},"reasoning_summary":true,"verbosity":true},"tags":["preview","advanced","reasoning","coding","agentic","5.6","terra","latest"],"api":"chat","input_price":0.000002,"output_price":0.000012,"input_price_per_million":2,"output_price_per_million":12,"input":2,"output":12,"pricing":{"currency":"USD","unit":"per_million_tokens","prompt":"0.000002","completion":"0.000012","input":2,"output":12,"cacheReadInputPer1kTokens":0.0002,"prompt_per_million":2,"completion_per_million":12,"prompt_per_token":"0.000002","completion_per_token":"0.000012","per_input_token":0.000002,"per_output_token":0.000012},"effective_pricing":{"list_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"effective_price":{"inputPer1kTokens":0.002,"outputPer1kTokens":0.012,"inputPer1kTokensAbove200k":0.004,"outputPer1kTokensAbove200k":0.018,"highContextThresholdTokens":272000,"cacheReadInputPer1kTokens":0.0002,"cacheReadInputPer1kTokensAbove200k":0.0004,"cacheWriteInputPer1kTokens":0.0025,"cacheWriteInputPer1kTokensAbove200k":0.005},"list_additional_charges":{"searchPerRequest":0.01},"effective_additional_charges":{"searchPerRequest":0.01},"pricing_type":"static","currency":"USD","unit":"per_1k_tokens","discount_percentage":0,"source":"registry","updated_at":"2026-10-26T14:49:05.390Z"},"avgOutputTokens":223.1}}},"meta":{"generatedAt":"2026-10-26T14:49:05.349Z","pricingEffectiveAtMs":1793026145349,"source":"static-build+storage"}}