{"models":[{"modelId":"anthropic/claude-fable-5","inputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":50000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":1000,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Fable 5","modelDescription":"Anthropic's most capable widely released model for long-running agents, advanced reasoning, coding, and demanding knowledge work.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-fable-5","fable-5"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-fable-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"]}},{"modelId":"anthropic/claude-fable-5-1","inputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":50000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":250,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Fable 5.1","modelDescription":"Anthropic's most capable model for real-world agents and coding.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-fable-5-1","fable-5-1"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-fable-5-1"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"]}},{"modelId":"anthropic/claude-fable-5-2","inputCostPerToken":{"amount":8000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":40000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Fable 5.2","modelDescription":"Anthropic's most capable model for real-world agents and coding.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-fable-5-2","fable-5-2"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-fable-5-2"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"]}},{"modelId":"anthropic/claude-haiku-4-5","inputCostPerToken":{"amount":1000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":5000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":200000,"modelDisplayName":"Claude Haiku 4.5","modelDescription":"Anthropic's fastest model with near-frontier intelligence for high-throughput, cost-sensitive workloads.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-haiku-4-5","haiku-4-5"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-haiku-4-5-20251001"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":64000,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"anthropic/claude-haiku-5-5","inputCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":100000,"tiers":{"default":{"short":{"uncachedInput":"0.10","cachedInput":"0.01","cacheWrite":"0.125","output":"0.50"},"long":{"uncachedInput":"0.50","cachedInput":"0.05","cacheWrite":"0.625","output":"2.50"}}}},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Haiku 5.5","modelDescription":"Anthropic's fastest and most cost-efficient model for high-volume work such as classification, extraction, routing, and sub-agent tasks, with adaptive reasoning and a 1M-token context window. Prompts over 100K tokens are billed at a higher rate.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-haiku-5-5","haiku-5-5","claude-haiku-latest"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-haiku-5-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"]}},{"modelId":"anthropic/claude-opus-4-6","inputCostPerToken":{"amount":5000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":25000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":200000,"modelDisplayName":"Claude Opus 4.6","modelDescription":"Anthropic's most intelligent model for building agents and coding","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-opus-4-6","opus-4-6"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-opus-4-6"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":32768,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"anthropic/claude-opus-4-7","inputCostPerToken":{"amount":5000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":25000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Opus 4.7","modelDescription":"Anthropic's most capable model. Next-generation built for long-running agents and complex coding tasks. 1M token context window with 128K max output.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-opus-4-7","opus-4-7"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-opus-4-7"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":32768,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"anthropic/claude-opus-4-8","inputCostPerToken":{"amount":5000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":25000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Opus 4.8","modelDescription":"Anthropic's most capable model. Next-generation built for long-running agents and complex coding tasks. 1M token context window with 128K max output.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-opus-4-8","opus-4-8"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-opus-4-8"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]}}},{"modelId":"anthropic/claude-opus-5","inputCostPerToken":{"amount":5000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":25000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Opus 5","modelDescription":"Anthropic model for complex agentic coding and enterprise work, with adaptive reasoning and a 1M-token context window.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-opus-5","opus-5"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-opus-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"]}},{"modelId":"anthropic/claude-opus-5-5","inputCostPerToken":{"amount":4000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":20000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Opus 5.5","modelDescription":"Anthropic model for long-running agentic coding and knowledge work, with always-on adaptive reasoning and a 1M-token context window.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-opus-5-5","opus-5-5","claude-opus-latest"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-opus-5-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":true}},{"modelId":"anthropic/claude-sonnet-4-5","inputCostPerToken":{"amount":3000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":15000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":200000,"modelDisplayName":"Claude Sonnet 4.5","modelDescription":"Anthropic's Claude Sonnet 4.5 - a powerful, efficient model balancing intelligence and speed. Excels at complex reasoning, coding, and creative tasks with 200K context window. Anonymized, not TEE-protected.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-sonnet-4-5-20250929"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs"],"isReady":false}},{"modelId":"anthropic/claude-sonnet-4-6","inputCostPerToken":{"amount":3000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":15000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Sonnet 4.6","modelDescription":"Anthropic's best balance of speed and intelligence. Extended thinking support with 1M token context window and 64K max output. Ideal for most production workloads.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-sonnet-4-6","sonnet-4-6"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-sonnet-4-6"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"anthropic/claude-sonnet-5","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Sonnet 5","modelDescription":"Anthropic's best combination of speed and intelligence for coding, agents, and professional workloads, with adaptive reasoning.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-sonnet-5","sonnet-5"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-sonnet-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"]}},{"modelId":"anthropic/claude-sonnet-5-5","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Claude Sonnet 5.5","modelDescription":"Anthropic's latest Sonnet model, balancing speed and intelligence for everyday coding, agents, and enterprise work, with adaptive reasoning and a 1M-token context window.","modelIcon":"https://avatars.githubusercontent.com/u/76263028?v=4","ownedBy":"anthropic","aliases":["claude-sonnet-5-5","sonnet-5-5","claude-sonnet-latest"],"providerType":"external","providerConfig":{"backend":"anthropic","base_url":"https://api.anthropic.com/v1","model_name":"claude-sonnet-5-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":true}},{"modelId":"black-forest-labs/FLUX.2-klein-4B","inputCostPerToken":{"amount":1000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1000,"scale":9,"currency":"USD"},"costPerImage":{"amount":12000000,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":128000,"modelDisplayName":"FLUX.2-klein-4B","modelDescription":"The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference in as low as under a second. Built for applications that require real-time image generation without sacrificing quality.","modelIcon":"https://cdn-avatars.huggingface.co/v1/production/uploads/633f7a8f4be90e06da248e0f/m5YoF33abJ09vcwFxt1Mj.png","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["image"]},"huggingFaceId":"black-forest-labs/FLUX.2-klein-4B","quantization":"bf16","maxOutputLength":1,"supportedSamplingParameters":["seed"],"datacenters":[{"country_code":"US"}]}},{"modelId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","inputCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1200,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":6,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":1048576,"modelDisplayName":"DeepSeek V4.1 Flash 1017","modelDescription":"October 17, 2026 snapshot of DeepSeek V4.1 Flash, a reasoning and coding model. Served privately from NEAR AI's attested TEE infrastructure.","modelIcon":"https://avatars.githubusercontent.com/u/148330874?v=4","ownedBy":"nearai","aliases":["deepseek-ai/DeepSeek-V4-Flash"],"providerType":"vllm","providerConfig":{},"attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"supportedFeatures":["tools","reasoning"]}},{"modelId":"deepseek-ai/DeepSeek-V4.1-Flash-1017-abliterated","inputCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1200,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":6,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":1048576,"modelDisplayName":"DeepSeek V4.1 Flash 1017 Abliterated","modelDescription":"DeepSeek V4.1 Flash (October 17, 2026 snapshot) with refusal behavior removed (abliterated), for red teaming, security research and evaluations. Reasoning, coding and tool use, text only, 1M context window. Served privately from NEAR AI's attested TEE infrastructure.","modelIcon":"https://avatars.githubusercontent.com/u/148330874?v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"supportedFeatures":["tools","reasoning"],"datacenters":[{"country_code":"US"}]}},{"modelId":"deepseek/deepseek-v3.2","inputCostPerToken":{"amount":1100,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1100,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":550,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":128000,"modelDisplayName":"deepseek-v3.2","modelDescription":"Attested model served via Chutes TEE (verified end-to-end by NEAR AI).","modelIcon":"https://avatars.githubusercontent.com/u/148330874?v=4","ownedBy":"attested 3p","providerType":"chutes","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","stop","seed","max_tokens"],"supportedFeatures":["tools","json_mode"],"isReady":false}},{"modelId":"deepseek/deepseek-v4.1-flash","inputCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1200,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":6,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1048576,"modelDisplayName":"DeepSeek V4.1 Flash","modelDescription":"DeepSeek reasoning and coding model with image understanding. Served through OpenRouter using ZDR inference endpoints.","modelIcon":"https://avatars.githubusercontent.com/u/148330874?v=4","ownedBy":"deepseek","aliases":["deepseek-v4.1-flash"],"providerType":"external","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1","model_name":"deepseek/deepseek-v4.1-flash","extra_request_body":{"provider":{"zdr":true,"only":["novita/fp8"],"allow_fallbacks":false,"data_collection":"deny"}},"enforced_request_body":{"provider":{"zdr":true,"only":["novita/fp8"],"allow_fallbacks":false,"data_collection":"deny"}}},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"deepseek-ai/DeepSeek-V4.1-Flash","maxOutputLength":393216,"supportedSamplingParameters":["temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens"],"supportedFeatures":["tools","json_mode","reasoning"],"isReady":true}},{"modelId":"deepseek/deepseek-v4.1-flash-1017","inputCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1200,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":6,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1048576,"modelDisplayName":"DeepSeek V4.1 Flash 1017","modelDescription":"October 17, 2026 snapshot of DeepSeek V4.1 Flash, a reasoning and coding model with image understanding. Served through OpenRouter using zero data retention inference endpoints.","modelIcon":"https://avatars.githubusercontent.com/u/148330874?v=4","ownedBy":"deepseek","aliases":["deepseek-v4.1-flash-1017","deepseek-flash-latest","deepseek/deepseek-flash-latest"],"providerType":"external","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1","model_name":"deepseek/deepseek-v4.1-flash-1017","extra_request_body":{"provider":{"zdr":true,"ignore":["relace"],"max_price":{"prompt":0.3,"completion":1.2},"data_collection":"deny","require_parameters":true}},"enforced_request_body":{"provider":{"zdr":true,"max_price":{"prompt":0.3,"completion":1.2},"data_collection":"deny"}}},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","maxOutputLength":393216,"supportedSamplingParameters":["temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens"],"supportedFeatures":["tools","json_mode","reasoning"],"isReady":true}},{"modelId":"google/gemini-2.5-flash","inputCostPerToken":{"amount":300,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":2500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Gemini 2.5 Flash","modelDescription":"Google's fast hybrid reasoning model with 1M token context window. Optimized for speed and cost while maintaining strong performance across tasks.","modelIcon":"https://avatars.githubusercontent.com/u/1342004?v=4","ownedBy":"google","aliases":["gemini-2.5-flash"],"providerType":"external","providerConfig":{"backend":"gemini","base_url":"https://generativelanguage.googleapis.com/v1beta","model_name":"gemini-2.5-flash"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"google/gemini-2.5-flash-lite","inputCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":400,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1048576,"modelDisplayName":"Gemini 2.5 Flash Lite","modelDescription":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","modelIcon":"https://avatars.githubusercontent.com/u/1342004?v=4","ownedBy":"google","providerType":"external","providerConfig":{"backend":"gemini","base_url":"https://generativelanguage.googleapis.com/v1beta","model_name":"gemini-2.5-flash-lite"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"google/gemini-2.5-pro","inputCostPerToken":{"amount":1250,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Gemini 2.5 Pro","modelDescription":"Google's strongest reasoning model. Excels at coding, math, and complex analysis with 1M token context window. Supports text and image input.","modelIcon":"https://avatars.githubusercontent.com/u/1342004?v=4","ownedBy":"google","aliases":["gemini-2.5-pro"],"providerType":"external","providerConfig":{"backend":"gemini","base_url":"https://generativelanguage.googleapis.com/v1beta","model_name":"gemini-2.5-pro"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"google/gemini-3.1-flash-lite","inputCostPerToken":{"amount":250,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1048576,"modelDisplayName":"Gemini 3.1 Flash Lite","modelDescription":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","modelIcon":"https://avatars.githubusercontent.com/u/1342004?v=4","ownedBy":"google","providerType":"external","providerConfig":{"backend":"gemini","base_url":"https://generativelanguage.googleapis.com/v1beta","model_name":"gemini-3.1-flash-lite"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"google/gemini-3.5-flash","inputCostPerToken":{"amount":1500,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":9000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":150,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Gemini 3.5 Flash","modelDescription":"Google's high-efficiency multimodal model with 1M token context. Strong agentic and coding performance, rivaling larger flagship models on many tasks.","modelIcon":"https://avatars.githubusercontent.com/u/1342004?v=4","ownedBy":"google","aliases":["gemini-3.5-flash"],"providerType":"external","providerConfig":{"backend":"gemini","base_url":"https://generativelanguage.googleapis.com/v1beta","model_name":"gemini-3.5-flash"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"google/gemini-3.8-flash","inputCostPerToken":{"amount":750,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":3750,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":75,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Gemini 3.8 Flash","modelDescription":"Google's stable, high-efficiency Gemini 3.8 Flash model for agentic coding, multimodal understanding, and high-throughput workloads, with a 1M-token context window.","modelIcon":"https://avatars.githubusercontent.com/u/1342004?v=4","ownedBy":"google","aliases":["gemini-3.8-flash"],"providerType":"external","providerConfig":{"backend":"gemini","base_url":"https://generativelanguage.googleapis.com/v1beta","model_name":"gemini-3.8-flash"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]}}},{"modelId":"levanto/sage-2","inputCostPerToken":{"amount":70,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":32768,"modelDisplayName":"Levanto Sage 2","modelDescription":"Sage is a decision model: send text and typed questions (yes/no, choice, score) and get calibrated probabilities back instead of generated text. Choice and score distributions sum to 1. Call it through /v1/systemone.","modelIcon":"https://avatars.githubusercontent.com/u/301166351?s=200&v=4","ownedBy":"levanto","aliases":["levanto/sage-1.4"],"providerType":"external","providerConfig":{"api_key":"***","backend":"typesafe","base_url":"https://private.sage.levanto.ai/v1","model_name":"levanto-sage-2"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["decisions"]},"isReady":true}},{"modelId":"moonshotai/kimi-k2.6","inputCostPerToken":{"amount":810,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":3850,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":410,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":262144,"modelDisplayName":"Kimi K2.6","modelDescription":"Moonshot AI's frontier MoE model with 256K context window. Excels at complex reasoning, math, coding, and multilingual tasks with native vision support.","modelIcon":"https://avatars.githubusercontent.com/u/129152888?s=200&v=4","ownedBy":"attested 3p","aliases":["kimi-k2.6"],"providerType":"chutes","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1","model_name":"moonshotai/kimi-k2.6"},"attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"moonshotai/Kimi-K2.6","maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs"],"isReady":true}},{"modelId":"moonshotai/kimi-k3","inputCostPerToken":{"amount":3300,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":16500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":330,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":1048576,"modelDisplayName":"Kimi K3","modelDescription":"Moonshot AI native multimodal agentic model with a 1M-token context window, built for long-horizon coding, knowledge work, and reasoning.","modelIcon":"https://avatars.githubusercontent.com/u/129152888?s=200&v=4","ownedBy":"attested 3p","aliases":["kimi-k3"],"providerType":"chutes","attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"quantization":"fp4","maxOutputLength":65535,"supportedSamplingParameters":["temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","max_tokens"],"supportedFeatures":["tools","json_mode","structured_outputs","reasoning"],"isReady":true}},{"modelId":"moonshotai/kimi-k3.1-pro","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Kimi K3.1 Pro","modelDescription":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.","modelIcon":"https://avatars.githubusercontent.com/u/129152888?s=200&v=4","ownedBy":"moonshotai","providerType":"external","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]}}},{"modelId":"openai/gpt-4.1","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":8000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"2.00","cachedInput":"0.50","output":"8.00"}},"priority":{"short":{"uncachedInput":"3.50","cachedInput":"0.875","output":"14.00"}}}},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"OpenAI GPT-4.1","modelDescription":"OpenAI's flagship production model with 1M token context window. Excels at instruction following, coding, and long-context tasks. 75% cheaper cached input reads.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["gpt-4.1"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-4.1"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"openai/gpt-4.1-mini","inputCostPerToken":{"amount":400,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1600,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"0.40","cachedInput":"0.10","output":"1.60"}},"priority":{"short":{"uncachedInput":"0.70","cachedInput":"0.175","output":"2.80"}}}},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"OpenAI GPT-4.1 Mini","modelDescription":"Cost-effective version of GPT-4.1 with the same 1M token context window. Great balance of capability and cost for production workloads.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["gpt-4.1-mini"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-4.1-mini"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"openai/gpt-5","inputCostPerToken":{"amount":1250,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":125,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"1.25","cachedInput":"0.125","output":"10.00"}},"flex":{"short":{"uncachedInput":"0.625","cachedInput":"0.0625","output":"5.00"}},"priority":{"short":{"uncachedInput":"2.50","cachedInput":"0.25","output":"20.00"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"OpenAI GPT-5","modelDescription":"OpenAI's next-generation model with enhanced reasoning and 400K context window. Strong performance across coding, math, and creative tasks.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["gpt-5"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.1","inputCostPerToken":{"amount":1250,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":125,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"1.25","cachedInput":"0.125","output":"10.00"}},"flex":{"short":{"uncachedInput":"0.625","cachedInput":"0.0625","output":"5.00"}},"priority":{"short":{"uncachedInput":"2.50","cachedInput":"0.25","output":"20.00"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"GPT-5.1","modelDescription":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.1"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.2","inputCostPerToken":{"amount":1750,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":14000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":175,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"1.75","cachedInput":"0.175","output":"14.00"}},"flex":{"short":{"uncachedInput":"0.875","cachedInput":"0.0875","output":"7.00"}},"priority":{"short":{"uncachedInput":"3.50","cachedInput":"0.35","output":"28.00"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"OpenAI GPT-5.2","modelDescription":"OpenAI GPT-5.2 with 400k context window. Anonymized endpoint optimized for deep reasoning and large-context workflows.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["openai-gpt-5.2","gpt-5.2","gpt-5.2-400k"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.2"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.4","inputCostPerToken":{"amount":2500,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":15000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":250,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"2.50","cachedInput":"0.25","output":"15.00"},"long":{"uncachedInput":"5.00","cachedInput":"0.50","output":"22.50"}},"flex":{"short":{"uncachedInput":"1.25","cachedInput":"0.13","output":"7.50"},"long":{"uncachedInput":"2.50","cachedInput":"0.25","output":"11.25"}},"priority":{"short":{"uncachedInput":"5.00","cachedInput":"0.50","output":"30.00"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-5.4","modelDescription":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.4"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.4-mini","inputCostPerToken":{"amount":750,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":4500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":75,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"0.75","cachedInput":"0.075","output":"4.50"}},"flex":{"short":{"uncachedInput":"0.375","cachedInput":"0.0375","output":"2.25"}},"priority":{"short":{"uncachedInput":"1.50","cachedInput":"0.15","output":"9.00"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"GPT-5.4 Mini","modelDescription":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.4-mini"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.4-nano","inputCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1250,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":20,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"0.20","cachedInput":"0.02","output":"1.25"}},"flex":{"short":{"uncachedInput":"0.10","cachedInput":"0.01","output":"0.625"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"GPT-5.4 Nano","modelDescription":"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. It supports text and image inputs and is designed for low-latency...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.4-nano"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.5","inputCostPerToken":{"amount":5000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":30000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"5.00","cachedInput":"0.50","output":"30.00"},"long":{"uncachedInput":"10.00","cachedInput":"1.00","output":"45.00"}},"flex":{"short":{"uncachedInput":"2.50","cachedInput":"0.25","output":"15.00"},"long":{"uncachedInput":"5.00","cachedInput":"0.50","output":"22.50"}},"priority":{"short":{"uncachedInput":"12.50","cachedInput":"1.25","output":"75.00"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-5.5","modelDescription":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.5"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5.6-luna","inputCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1200,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":20,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"0.20","cachedInput":"0.02","cacheWrite":"0.25","output":"1.20"},"long":{"uncachedInput":"0.40","cachedInput":"0.04","cacheWrite":"0.50","output":"1.80"}},"flex":{"short":{"uncachedInput":"0.10","cachedInput":"0.01","cacheWrite":"0.125","output":"0.60"},"long":{"uncachedInput":"0.20","cachedInput":"0.02","cacheWrite":"0.25","output":"0.90"}},"priority":{"short":{"uncachedInput":"0.40","cachedInput":"0.04","cacheWrite":"0.50","output":"2.40"},"long":{"uncachedInput":"0.80","cachedInput":"0.08","cacheWrite":"1.00","output":"3.60"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-5.6 Luna","modelDescription":"OpenAI GPT-5.6 model optimized for cost-sensitive workloads","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["gpt-4.1-nano","openai/gpt-4.1-nano"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.6-luna"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","stop","seed","max_tokens","logit_bias"],"supportedFeatures":["tools","json_mode","structured_outputs","logprobs","reasoning"]}},{"modelId":"openai/gpt-5.6-sol","inputCostPerToken":{"amount":4000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":20000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":400,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"4.00","cachedInput":"0.40","cacheWrite":"5.00","output":"20.00"},"long":{"uncachedInput":"8.00","cachedInput":"0.80","cacheWrite":"10.00","output":"30.00"}},"flex":{"short":{"uncachedInput":"2.00","cachedInput":"0.20","cacheWrite":"2.50","output":"10.00"},"long":{"uncachedInput":"4.00","cachedInput":"0.40","cacheWrite":"5.00","output":"15.00"}},"priority":{"short":{"uncachedInput":"8.00","cachedInput":"0.80","cacheWrite":"10.00","output":"40.00"},"long":{"uncachedInput":"16.00","cachedInput":"1.60","cacheWrite":"20.00","output":"60.00"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-5.6 Sol","modelDescription":"OpenAI frontier model for complex professional work","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["openai/gpt-5.6"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5.6-sol"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","stop","seed","max_tokens","logit_bias"],"supportedFeatures":["tools","json_mode","structured_outputs","logprobs","reasoning"]}},{"modelId":"openai/gpt-5-mini","inputCostPerToken":{"amount":250,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":25,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"0.25","cachedInput":"0.025","output":"2.00"}},"flex":{"short":{"uncachedInput":"0.125","cachedInput":"0.0125","output":"1.00"}},"priority":{"short":{"uncachedInput":"0.45","cachedInput":"0.045","output":"3.60"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"GPT-5 Mini","modelDescription":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5-mini"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-5-nano","inputCostPerToken":{"amount":50,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":400,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":5,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"0.05","cachedInput":"0.005","output":"0.40"}},"flex":{"short":{"uncachedInput":"0.025","cachedInput":"0.0025","output":"0.20"}}}},"metadata":{"verifiable":false,"contextLength":400000,"modelDisplayName":"GPT-5 Nano","modelDescription":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-5-nano"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":false}},{"modelId":"openai/gpt-6.1-sol","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"2.00","cachedInput":"0.10","cacheWrite":"2.50","output":"10.00"},"long":{"uncachedInput":"4.00","cachedInput":"0.20","cacheWrite":"5.00","output":"15.00"}},"flex":{"short":{"uncachedInput":"1.00","cachedInput":"0.05","cacheWrite":"1.25","output":"5.00"},"long":{"uncachedInput":"2.00","cachedInput":"0.10","cacheWrite":"2.50","output":"7.50"}},"priority":{"short":{"uncachedInput":"4.00","cachedInput":"0.20","cacheWrite":"5.00","output":"20.00"},"long":{"uncachedInput":"8.00","cachedInput":"0.40","cacheWrite":"10.00","output":"30.00"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-6.1 Sol","modelDescription":"OpenAI GPT-6.1 model for complex coding and agentic workflows. Tool calling is not currently advertised through NEAR AI Cloud.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-6.1-sol"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens"],"supportedFeatures":["structured_outputs","json_mode","reasoning"],"isReady":true}},{"modelId":"openai/gpt-6-astra","inputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":50000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":1000,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"10.00","cachedInput":"1.00","cacheWrite":"12.50","output":"50.00"},"long":{"uncachedInput":"20.00","cachedInput":"2.00","cacheWrite":"25.00","output":"75.00"}},"flex":{"short":{"uncachedInput":"5.00","cachedInput":"0.50","cacheWrite":"6.25","output":"25.00"},"long":{"uncachedInput":"10.00","cachedInput":"1.00","cacheWrite":"12.50","output":"37.50"}},"priority":{"short":{"uncachedInput":"20.00","cachedInput":"2.00","cacheWrite":"25.00","output":"100.00"},"long":{"uncachedInput":"40.00","cachedInput":"4.00","cacheWrite":"50.00","output":"150.00"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-6 Astra","modelDescription":"OpenAI model for complex reasoning, coding, research, and document creation. Tool calling is not currently supported through NEAR AI Cloud.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-6-astra"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens"],"supportedFeatures":["structured_outputs","json_mode","reasoning"]}},{"modelId":"openai/gpt-6-luna","inputCostPerToken":{"amount":100,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"0.10","cachedInput":"0.01","cacheWrite":"0.125","output":"0.50"},"long":{"uncachedInput":"0.20","cachedInput":"0.02","cacheWrite":"0.25","output":"0.75"}},"flex":{"short":{"uncachedInput":"0.05","cachedInput":"0.005","cacheWrite":"0.0625","output":"0.25"},"long":{"uncachedInput":"0.10","cachedInput":"0.01","cacheWrite":"0.125","output":"0.375"}},"priority":{"short":{"uncachedInput":"0.20","cachedInput":"0.02","cacheWrite":"0.25","output":"1.00"},"long":{"uncachedInput":"0.40","cachedInput":"0.04","cacheWrite":"0.50","output":"1.50"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-6 Luna","modelDescription":"OpenAI GPT-6 model optimized for focused, high-volume workloads. Tool calling is not currently advertised through NEAR AI Cloud.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-6-luna"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens"],"supportedFeatures":["structured_outputs","json_mode","reasoning"],"isReady":true}},{"modelId":"openai/gpt-6-sol","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":200,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":272000,"tiers":{"default":{"short":{"uncachedInput":"2.00","cachedInput":"0.20","cacheWrite":"2.50","output":"10.00"},"long":{"uncachedInput":"4.00","cachedInput":"0.40","cacheWrite":"5.00","output":"15.00"}},"flex":{"short":{"uncachedInput":"1.00","cachedInput":"0.10","cacheWrite":"1.25","output":"5.00"},"long":{"uncachedInput":"2.00","cachedInput":"0.20","cacheWrite":"2.50","output":"7.50"}},"priority":{"short":{"uncachedInput":"4.00","cachedInput":"0.40","cacheWrite":"5.00","output":"20.00"},"long":{"uncachedInput":"8.00","cachedInput":"0.80","cacheWrite":"10.00","output":"30.00"}}}},"metadata":{"verifiable":false,"contextLength":1050000,"modelDisplayName":"GPT-6 Sol","modelDescription":"OpenAI GPT-6 model for complex coding and agentic workflows. Tool calling is not currently advertised through NEAR AI Cloud.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"gpt-6-sol"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":128000,"supportedSamplingParameters":["max_tokens"],"supportedFeatures":["structured_outputs","json_mode","reasoning"],"isReady":true}},{"modelId":"openai/o3","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":8000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"2.00","cachedInput":"0.50","output":"8.00"}},"flex":{"short":{"uncachedInput":"1.00","cachedInput":"0.25","output":"4.00"}},"priority":{"short":{"uncachedInput":"3.50","cachedInput":"0.875","output":"14.00"}}}},"metadata":{"verifiable":false,"contextLength":200000,"modelDisplayName":"OpenAI o3","modelDescription":"OpenAI's flagship reasoning model. Uses chain-of-thought to solve complex math, coding, and logic problems. 200K context window.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["o3"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"o3"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":32768,"supportedSamplingParameters":["max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"openai/o3-mini","inputCostPerToken":{"amount":1100,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":4400,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":550,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"1.10","cachedInput":"0.55","output":"4.40"}}}},"metadata":{"verifiable":false,"contextLength":200000,"modelDisplayName":"o3 Mini","modelDescription":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"o3-mini"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":32768,"supportedSamplingParameters":["max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"openai/o4-mini","inputCostPerToken":{"amount":1100,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":4400,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":275,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","tiers":{"default":{"short":{"uncachedInput":"1.10","cachedInput":"0.275","output":"4.40"}},"flex":{"short":{"uncachedInput":"0.55","cachedInput":"0.138","output":"2.20"}},"priority":{"short":{"uncachedInput":"2.00","cachedInput":"0.50","output":"8.00"}}}},"metadata":{"verifiable":false,"contextLength":200000,"modelDisplayName":"OpenAI o4 Mini","modelDescription":"OpenAI's cost-effective reasoning model. Strong performance on math, coding, and scientific reasoning at a fraction of o3's cost. 200K context window.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"openai","aliases":["o4-mini"],"providerType":"external","providerConfig":{"backend":"openai_compatible","base_url":"https://api.openai.com/v1","model_name":"o4-mini"},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":32768,"supportedSamplingParameters":["max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","reasoning"],"isReady":false}},{"modelId":"openai/privacy-filter","inputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":0,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":128000,"modelDisplayName":"Privacy Filter","modelDescription":"PII detection (token classification) — returns spans for emails, phones, addresses, names, account numbers, secrets. NEAR AI runs this model in a TEE; prompts are not anonymized by the model itself, the cloud-api wraps it to do redaction.","modelIcon":"https://avatars.githubusercontent.com/u/29134221?v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":1024,"datacenters":[{"country_code":"US"}]}},{"modelId":"openai/whisper-large-v3","inputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":448,"modelDisplayName":"Whisper Large v3","modelDescription":"Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation.","modelIcon":"https://avatars.githubusercontent.com/u/14957082?s=200&v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["audio"],"outputModalities":["text"]},"huggingFaceId":"openai/whisper-large-v3","maxOutputLength":1024,"supportedSamplingParameters":["temperature"],"datacenters":[{"country_code":"US"}]}},{"modelId":"Qwen/Qwen3.6-35B-A3B-FP8","inputCostPerToken":{"amount":170,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1100,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":56,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":262144,"modelDisplayName":"Qwen 3.6 35B A3B FP8","modelDescription":"Qwen 3.6 35B is a fast mixture-of-experts language model with ~3B active parameters per token. Strong at reasoning, coding, and multilingual tasks with 32K context window.","modelIcon":"https://avatars.githubusercontent.com/u/141221163?s=200&v=4","ownedBy":"nearai","aliases":["qwen3.6-35b-a3b-fp8","qwen/qwen3.6-35b-a3b-fp8","Qwen/Qwen3-30B-A3B-Instruct-2507","qwen/qwen3-30b-a3b-instruct-2507","qwen3-30b-a3b-instruct-2507"],"providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"huggingFaceId":"Qwen/Qwen3.6-35B-A3B-FP8","quantization":"fp8","maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias"],"supportedFeatures":["tools","json_mode","structured_outputs","logprobs","reasoning"],"datacenters":[{"country_code":"US"}],"isReady":true,"openrouterSlug":"qwen/qwen3.6-35b-a3b"}},{"modelId":"qwen/qwen3.7-max","inputCostPerToken":{"amount":2800,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":7500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":1000000,"modelDisplayName":"Qwen3.7 Max","modelDescription":"Qwen's most capable proprietary model with 1M context window. Strong at reasoning, coding, math, and multilingual tasks.","modelIcon":"https://avatars.githubusercontent.com/u/141221163?s=200&v=4","ownedBy":"qwen","aliases":["qwen3.7-max"],"providerType":"external","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1","model_name":"qwen/qwen3.7-max"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"maxOutputLength":16384,"supportedSamplingParameters":["temperature","top_p","top_k","frequency_penalty","presence_penalty","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","json_mode"],"isReady":false}},{"modelId":"Qwen/Qwen3.8-27B","inputCostPerToken":{"amount":40,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1350,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":18,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":262144,"modelDisplayName":"Qwen 3.8 27B","modelDescription":"Qwen 3.8 27B is a dense FP8 multimodal model with reasoning, coding, tool use, vision, and a 262K context window.","modelIcon":"https://avatars.githubusercontent.com/u/141221163?v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"Qwen/Qwen3.8-27B-FP8","quantization":"fp8","maxOutputLength":65536,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"}],"isReady":true,"openrouterSlug":"qwen/qwen3.8-27b"}},{"modelId":"Qwen/Qwen3.8-27B-abliterated","inputCostPerToken":{"amount":40,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":1350,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":18,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":262144,"modelDisplayName":"Qwen 3.8 27B Abliterated","modelDescription":"Qwen 3.8 27B with refusal behavior removed (abliterated), for red teaming, security research and evaluations. Reasoning, tool use, vision and a 262K context window. Served privately from NEAR AI's attested TEE infrastructure.","modelIcon":"https://avatars.githubusercontent.com/u/141221163?v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"quantization":"fp8","maxOutputLength":65536,"supportedSamplingParameters":["temperature","top_p","top_k","max_tokens","stop","seed"],"supportedFeatures":["tools","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"IN"}]}},{"modelId":"Qwen/Qwen3-Embedding-0.6B","inputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":32768,"modelDisplayName":"Qwen3-Embedding-0.6B","modelDescription":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding tasks.","modelIcon":"https://avatars.githubusercontent.com/u/223098841?s=200&v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["embedding"]},"huggingFaceId":"Qwen/Qwen3-Embedding-0.6B","quantization":"bf16","maxOutputLength":1024,"datacenters":[{"country_code":"US"}]}},{"modelId":"Qwen/Qwen3-Reranker-0.6B","inputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":10,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":40960,"modelDisplayName":"Qwen3-Reranker-0.6B","modelDescription":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.","modelIcon":"https://avatars.githubusercontent.com/u/223098841?s=200&v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"huggingFaceId":"Qwen/Qwen3-Reranker-0.6B","quantization":"bf16","maxOutputLength":1024,"datacenters":[{"country_code":"US"}]}},{"modelId":"Qwen/Qwen3-VL-30B-A3B-Instruct","inputCostPerToken":{"amount":150,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":550,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":30,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":16384,"modelDisplayName":"Qwen3-VL-30B-A3B-Instruct","modelDescription":"Qwen3-VL-30B-A3B-Instruct is a vision-language model supporting text and image inputs.","modelIcon":"https://avatars.githubusercontent.com/u/141221163?s=200&v=4","ownedBy":"nearai","providerType":"vllm","attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"Qwen/Qwen3-VL-30B-A3B-Instruct","quantization":"fp8","maxOutputLength":8192,"supportedSamplingParameters":["temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","stop","seed","logit_bias"],"supportedFeatures":["structured_outputs","logprobs"],"datacenters":[{"country_code":"US"}],"isReady":true,"openrouterSlug":"qwen/qwen3-vl-30b-a3b-instruct"}},{"modelId":"typesafe/jev-1.13","inputCostPerToken":{"amount":42,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":0,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":0,"scale":9,"currency":"USD"},"metadata":{"verifiable":false,"contextLength":32000,"modelDisplayName":"Jev 1.13","modelDescription":"Jev is a structured decision model from TypeSafe, and the first of its System One models. System One models make fast, structured decisions for software, returning a typed choice rather than free-form text. It is suited for routing, classification, and other decision points inside an application where a fast, predictable answer matters more than generated prose.\n\nLearn more in TypeSafe's docs: https://docs.typesafe.ai/concepts/system-one","modelIcon":"https://avatars.githubusercontent.com/u/171090879?s=200&v=4","ownedBy":"typesafe","aliases":["typesafe/jev-latest"],"providerType":"external","providerConfig":{"api_key":"***","backend":"typesafe","base_url":"https://openrouter.ai/api/v1","model_name":"typesafe/jev-1.13"},"attestationSupported":false,"architecture":{"inputModalities":["text"],"outputModalities":["decisions"]}}},{"modelId":"x-ai/grok-4.6","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":6000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":199999,"tiers":{"default":{"short":{"uncachedInput":"2.00","cachedInput":"0.50","output":"6.00"},"long":{"uncachedInput":"4.00","cachedInput":"1.00","output":"12.00"}}}},"metadata":{"verifiable":false,"contextLength":500000,"modelDisplayName":"Grok 4.6","modelDescription":"xAI model for reasoning, coding, knowledge work, and image understanding.","modelIcon":"https://raw.githubusercontent.com/lobehub/lobe-icons/a94750e3f5f8fc33757b839d85030e742284e43a/packages/static-svg/icons/grok.svg","ownedBy":"x-ai","aliases":["grok-4.6"],"providerType":"external","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1","model_name":"x-ai/grok-4.6","extra_request_body":{"provider":{"zdr":true,"only":["xai/zdr"],"allow_fallbacks":false,"data_collection":"deny"}},"enforced_request_body":{"provider":{"zdr":true,"only":["xai/zdr"],"allow_fallbacks":false,"data_collection":"deny"}}},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":450000,"supportedSamplingParameters":["temperature","top_p","max_tokens","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning","logprobs"],"isReady":true}},{"modelId":"x-ai/grok-4.7","inputCostPerToken":{"amount":2000,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":6000,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"textPricing":{"version":1,"currency":"USD","unit":"million_tokens","longContextThreshold":199999,"tiers":{"default":{"short":{"uncachedInput":"2.00","cachedInput":"0.50","output":"6.00"},"long":{"uncachedInput":"4.00","cachedInput":"1.00","output":"12.00"}}}},"metadata":{"verifiable":false,"contextLength":500000,"modelDisplayName":"Grok 4.7","modelDescription":"xAI frontier model for coding, agentic tasks, knowledge work, and image understanding.","modelIcon":"https://raw.githubusercontent.com/lobehub/lobe-icons/a94750e3f5f8fc33757b839d85030e742284e43a/packages/static-svg/icons/grok.svg","ownedBy":"x-ai","aliases":["grok-4.7"],"providerType":"external","providerConfig":{"api_key":"***","backend":"openai_compatible","base_url":"https://openrouter.ai/api/v1","model_name":"x-ai/grok-4.7","extra_request_body":{"provider":{"zdr":true,"only":["xai/zdr"],"allow_fallbacks":false,"data_collection":"deny"}},"enforced_request_body":{"provider":{"zdr":true,"only":["xai/zdr"],"allow_fallbacks":false,"data_collection":"deny"}}},"attestationSupported":false,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"maxOutputLength":450000,"supportedSamplingParameters":["temperature","top_p","max_tokens","seed"],"supportedFeatures":["tools","structured_outputs","json_mode","reasoning"],"isReady":true}},{"modelId":"z-ai/glm-5.3","inputCostPerToken":{"amount":1800,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":5750,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":450,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":1048576,"modelDisplayName":"GLM 5.3","modelDescription":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks, with a 1M-token context window.","modelIcon":"https://avatars.githubusercontent.com/u/223098841?v=4","ownedBy":"attested 3p","providerType":"tinfoil","attestationSupported":true,"architecture":{"inputModalities":["text"],"outputModalities":["text"]},"supportedSamplingParameters":["temperature","top_p","max_tokens","stop","seed","frequency_penalty","presence_penalty"],"supportedFeatures":["tools","reasoning"],"openrouterSlug":"z-ai/glm-5.3"}},{"modelId":"z-ai/glm-5.3-flash","inputCostPerToken":{"amount":80,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":12,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":1048576,"modelDisplayName":"GLM 5.3 Flash","modelDescription":"GLM-5.3-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, reasoning, tool use, and visual understanding.","modelIcon":"https://avatars.githubusercontent.com/u/223098841?v=4","ownedBy":"nearai","aliases":["zai-org/GLM-5.3-Flash","GLM-5.3-Flash","glm-5.3-flash","zai-org/GLM-5.1-FP8","zai-org/GLM-5-FP8","glm-latest","zai-org/GLM-latest","GLM-5","zai-org/GLM-4.7","glm","GLM-5.1","zai-org/GLM-5.1","z-ai/glm-5.2"],"providerType":"vllm","providerConfig":{"long_context":{"inference_url":"https://glm-5-3-flash-long.completions.near.ai","max_context_tokens":1048576,"base_max_context_tokens":100000}},"attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"zai-org/GLM-5.3-Flash","quantization":"fp8","maxOutputLength":1048576,"supportedSamplingParameters":["temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","stop","seed","logit_bias"],"supportedFeatures":["tools","structured_outputs","reasoning","json_mode"],"isReady":true,"openrouterSlug":"z-ai/glm-5.3-flash"}}],"limit":100,"offset":0,"total":64}