{"meta/muse-spark-1.2-contributor":{"name":"Meta: Muse Spark 1.2 Contributor","maxTokens":0,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.002,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v4-flash-vision-exp":{"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","maxTokens":384000,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.44,"outputPrice":1.32,"cacheReadsPrice":0.014,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","thinkingConfig":{"maxBudget":6000}},"stealth/ox-alpha":{"name":"Ox Alpha","maxTokens":131072,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...","thinkingConfig":{"maxBudget":6000}},"tencent/hy-mt2-1.8b":{"name":"Tencent: Hy-MT2-1.8B","maxTokens":4096,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.044,"outputPrice":0.17700000000000002,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided..."},"tencent/hy-mt2-30b-a3b":{"name":"Tencent: Hy-MT2-30B-A3B","maxTokens":4096,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.074,"outputPrice":0.295,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and..."},"~z-ai/glm-latest":{"name":"Z.ai: GLM Latest","maxTokens":131072,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.4,"outputPrice":4.4,"cacheReadsPrice":0.26,"description":"This model always redirects to the latest GLM model from Z.ai.","thinkingConfig":{"maxBudget":6000}},"tencent/hy-mt2-7b":{"name":"Tencent: Hy-MT2-7B","maxTokens":4096,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.074,"outputPrice":0.295,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation."},"z-ai/glm-5.3":{"name":"Z.ai: GLM 5.3","maxTokens":131072,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.4,"outputPrice":4.4,"cacheReadsPrice":0.26,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.8-27b":{"name":"Qwen: Qwen3.8 27B","maxTokens":131072,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.425,"outputPrice":2.5500000000000003,"cacheReadsPrice":0.08499999999999999,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","thinkingConfig":{"maxBudget":6000}},"dots-studio/dots-3-note-preview:free":{"name":"Dots Studio: Dots3-Note Preview (free)","maxTokens":512000,"contextWindow":512000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.7-flash":{"name":"Google: Gemini 3.7 Flash","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.375,"outputPrice":1.875,"cacheReadsPrice":0.0375,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.7-flash:batch":{"name":"Google: Gemini 3.7 Flash (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.1875,"outputPrice":0.9375,"cacheReadsPrice":0.01875,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","thinkingConfig":{"maxBudget":6000}},"bytedance-seed/seed-2-1-turbo":{"name":"ByteDance Seed: Seed 2.1 Turbo","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":2.5,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.8-2.4t-a95b":{"name":"Qwen: Qwen3.8 2.4T A95B","maxTokens":131072,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.25,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","thinkingConfig":{"maxBudget":6000}},"bytedance-seed/seed-2.0-code":{"name":"ByteDance Seed: Seed-2.0-Code","maxTokens":131072,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":3,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v4-pro-0813":{"name":"DeepSeek: DeepSeek V4 Pro 0813","maxTokens":0,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.122,"outputPrice":3.366,"cacheReadsPrice":0.037399999999999996,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","thinkingConfig":{"maxBudget":6000}},"x-ai/grok-4.6":{"name":"SpaceXAI: Grok 4.6","maxTokens":0,"contextWindow":500000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.5,"description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","thinkingConfig":{"maxBudget":6000}},"liquid/lfm-2.5-2.6b:free":{"name":"LiquidAI: LFM2.5-2.6B (free)","maxTokens":8192,"contextWindow":65536,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3.5-lightning":{"name":"NVIDIA: Nemotron 3.5 Lightning","maxTokens":131072,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.08,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.04,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3.5-lightning:free":{"name":"NVIDIA: Nemotron 3.5 Lightning (free)","maxTokens":65536,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","thinkingConfig":{"maxBudget":6000}},"sakana/sakana-namazu":{"name":"Sakana: Sakana Namazu","maxTokens":65536,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.95,"outputPrice":4,"cacheReadsPrice":0.15,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","thinkingConfig":{"maxBudget":6000}},"upstage/solar-pro4":{"name":"Upstage: Solar Pro 4","maxTokens":131072,"contextWindow":524288,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.03,"outputPrice":0.12,"cacheReadsPrice":0.006,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","thinkingConfig":{"maxBudget":6000}},"meta/muse-glimmer-30b":{"name":"Meta: Muse Glimmer 30B","maxTokens":0,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.35,"outputPrice":1.5,"cacheReadsPrice":0.04,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","thinkingConfig":{"maxBudget":6000}},"meta/muse-spark-1.2":{"name":"Meta: Muse Spark 1.2","maxTokens":0,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":4.25,"cacheReadsPrice":0.15,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.8-max":{"name":"Qwen: Qwen3.8 Max","maxTokens":131072,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.25,"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...","thinkingConfig":{"maxBudget":6000}},"~deepseek/deepseek-v4-flash-latest":{"name":"DeepSeek V4 Flash Latest","maxTokens":1048576,"contextWindow":1310720,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.035,"outputPrice":0.09999999999999999,"cacheReadsPrice":0.008,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v4-flash-0731":{"name":"DeepSeek: DeepSeek V4 Flash 0731","maxTokens":131072,"contextWindow":1310720,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.14,"outputPrice":0.28,"cacheReadsPrice":0.028,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","thinkingConfig":{"maxBudget":6000}},"thinkingmachines/inkling-small":{"name":"Thinking Machines: Inkling Small","maxTokens":262144,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.44999999999999996,"outputPrice":1.2,"cacheReadsPrice":0.09999999999999999,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","thinkingConfig":{"maxBudget":6000}},"thinkingmachines/inkling-small:free":{"name":"Thinking Machines: Inkling Small (free)","maxTokens":262144,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.7-flash":{"name":"Qwen: Qwen3.7 Flash","maxTokens":65536,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.03,"outputPrice":0.13,"cacheReadsPrice":0.006,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-5-fast":{"name":"Claude Opus 5 (Fast)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":10,"outputPrice":50,"cacheReadsPrice":1,"description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-5":{"name":"Claude Opus 5","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-5:1m":{"name":"Claude Opus 5","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5},{"contextWindow":9007199254740991,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5}]},"anthropic/claude-opus-5:batch":{"name":"Claude Opus 5 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":12.5,"cacheReadsPrice":0.25,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","thinkingConfig":{"maxBudget":6000}},"inclusionai/ling-3.0-flash":{"name":"Ling-3.0-flash","maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.020999999999999998,"outputPrice":0.063,"cacheReadsPrice":0.004200000000000001,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","thinkingConfig":{"maxBudget":6000}},"poolside/laguna-s-2.1":{"name":"Poolside: Laguna S 2.1","maxTokens":131072,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.09,"outputPrice":0.18,"cacheReadsPrice":0.009,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","thinkingConfig":{"maxBudget":6000}},"poolside/laguna-s-2.1:free":{"name":"Poolside: Laguna S 2.1 (free)","maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.6-flash":{"name":"Google: Gemini 3.6 Flash","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.75,"outputPrice":3.75,"cacheReadsPrice":0.075,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.6-flash:batch":{"name":"Google: Gemini 3.6 Flash (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.375,"outputPrice":1.875,"cacheReadsPrice":0.0375,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.5-flash-lite":{"name":"Google: Gemini 3.5 Flash Lite","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":2.5,"cacheReadsPrice":0.03,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.5-flash-lite:batch":{"name":"Google: Gemini 3.5 Flash Lite (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":1.25,"cacheReadsPrice":0.015,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","thinkingConfig":{"maxBudget":6000}},"meituan/longcat-2.0":{"name":"Meituan: LongCat 2.0","maxTokens":262144,"contextWindow":1048756,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.006,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","thinkingConfig":{"maxBudget":6000}},"thinkingmachines/inkling":{"name":"Thinking Machines: Inkling","maxTokens":262144,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.95,"outputPrice":4.05,"cacheReadsPrice":0.16,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","thinkingConfig":{"maxBudget":6000}},"thinkingmachines/inkling:batch":{"name":"Thinking Machines: Inkling (batch)","maxTokens":0,"contextWindow":524288,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":4.05,"cacheReadsPrice":0.16999999999999998,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","thinkingConfig":{"maxBudget":6000}},"thinkingmachines/inkling:free":{"name":"Thinking Machines: Inkling (free)","maxTokens":262144,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","thinkingConfig":{"maxBudget":6000}},"openrouter/auto-beta":{"name":"Auto Router (Beta)","maxTokens":0,"contextWindow":2000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":-1000000,"outputPrice":-1000000,"description":"Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...","thinkingConfig":{"maxBudget":6000}},"moonshotai/kimi-k3":{"name":"MoonshotAI: Kimi K3","maxTokens":1048576,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheReadsPrice":0.3,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","thinkingConfig":{"maxBudget":6000}},"meta/muse-spark-1.1":{"name":"Meta: Muse Spark 1.1","maxTokens":0,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":4.25,"cacheReadsPrice":0.15,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...","thinkingConfig":{"maxBudget":6000}},"kwaipilot/kat-coder-air-v2.5":{"name":"Kwaipilot: KAT-Coder-Air V2.5","maxTokens":80000,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":0.6,"cacheReadsPrice":0.03,"description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make..."},"kwaipilot/kat-coder-pro-v2.5":{"name":"Kwaipilot: KAT-Coder-Pro V2.5","maxTokens":80000,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.74,"outputPrice":2.96,"cacheReadsPrice":0.15,"description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make..."},"openai/gpt-5.6-luna-pro":{"name":"OpenAI: GPT-5.6 Luna Pro","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":1.2,"cacheReadsPrice":0.02,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-luna-pro:batch":{"name":"OpenAI: GPT-5.6 Luna Pro (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.6,"cacheReadsPrice":0.01,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-luna":{"name":"OpenAI: GPT-5.6 Luna","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":1.2,"cacheReadsPrice":0.02,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-luna:batch":{"name":"OpenAI: GPT-5.6 Luna (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.6,"cacheReadsPrice":0.01,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-terra-pro":{"name":"OpenAI: GPT-5.6 Terra Pro","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-terra-pro:batch":{"name":"OpenAI: GPT-5.6 Terra Pro (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":6,"cacheReadsPrice":0.09999999999999999,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-terra":{"name":"OpenAI: GPT-5.6 Terra","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-terra:batch":{"name":"OpenAI: GPT-5.6 Terra (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":6,"cacheReadsPrice":0.09999999999999999,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-sol-pro":{"name":"OpenAI: GPT-5.6 Sol Pro","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":10,"cacheReadsPrice":0.19999999999999998,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-sol-pro:batch":{"name":"OpenAI: GPT-5.6 Sol Pro (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":5,"cacheReadsPrice":0.09999999999999999,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-sol":{"name":"OpenAI: GPT-5.6 Sol","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":10,"cacheReadsPrice":0.19999999999999998,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.6-sol:batch":{"name":"OpenAI: GPT-5.6 Sol (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":5,"cacheReadsPrice":0.09999999999999999,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","thinkingConfig":{"maxBudget":6000}},"x-ai/grok-4.5":{"name":"SpaceXAI: Grok 4.5","maxTokens":0,"contextWindow":500000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.3,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","thinkingConfig":{"maxBudget":6000}},"~x-ai/grok-latest":{"name":"xAI: Grok Latest","maxTokens":0,"contextWindow":500000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.5,"description":"This model always redirects to the latest Grok model from xAI.","thinkingConfig":{"maxBudget":6000}},"aion-labs/aion-3.0-mini":{"name":"AionLabs: Aion-3.0-Mini","maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.7,"outputPrice":1.4,"cacheReadsPrice":0.18,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","thinkingConfig":{"maxBudget":6000}},"aion-labs/aion-3.0":{"name":"AionLabs: Aion-3.0","maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":3,"outputPrice":6,"cacheReadsPrice":0.75,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","thinkingConfig":{"maxBudget":6000}},"tencent/hy3":{"name":"Tencent: Hy3","maxTokens":128000,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.13199999999999998,"outputPrice":0.5279999999999999,"cacheReadsPrice":0.032999999999999995,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","thinkingConfig":{"maxBudget":6000}},"poolside/laguna-xs-2.1":{"name":"Poolside: Laguna XS 2.1","maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.06,"outputPrice":0.12,"cacheReadsPrice":0.03,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","thinkingConfig":{"maxBudget":6000}},"poolside/laguna-xs-2.1:free":{"name":"Poolside: Laguna XS 2.1 (free)","maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-5":{"name":"Anthropic: Claude Sonnet 5","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":10,"cacheWritesPrice":2.5,"cacheReadsPrice":0.2,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-5:1m":{"name":"Anthropic: Claude Sonnet 5","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":10,"cacheWritesPrice":2.5,"cacheReadsPrice":0.2,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3},{"contextWindow":9007199254740991,"inputPrice":6,"outputPrice":22.5,"cacheWritesPrice":7.5,"cacheReadsPrice":0.6}]},"anthropic/claude-sonnet-5:batch":{"name":"Anthropic: Claude Sonnet 5 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":5,"cacheReadsPrice":0.09999999999999999,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-flash-lite-image":{"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","maxTokens":8192,"contextWindow":65536,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":1.5,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","thinkingConfig":{"maxBudget":6000}},"nex-agi/nex-n2-mini":{"name":"Nex AGI: Nex-N2-Mini","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.024999999999999998,"outputPrice":0.09999999999999999,"cacheReadsPrice":0.0025,"description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...","thinkingConfig":{"maxBudget":6000}},"sakana/fugu-ultra":{"name":"Sakana: Fugu Ultra","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":30,"cacheReadsPrice":0.5,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-flash-image":{"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","maxTokens":8192,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":3,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3-pro-image":{"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","maxTokens":32768,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","thinkingConfig":{"maxBudget":6000}},"cohere/north-mini-code:free":{"name":"Cohere: North Mini Code (free)","maxTokens":64000,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5.2":{"name":"Z.ai: GLM 5.2","maxTokens":262144,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.19,"outputPrice":3.74,"cacheReadsPrice":0.221,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5.2:batch":{"name":"Z.ai: GLM 5.2 (batch)","maxTokens":0,"contextWindow":1048575,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.4,"outputPrice":4.4,"cacheReadsPrice":0.26,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5.2:free":{"name":"Z.ai: GLM 5.2 (free)","maxTokens":256000,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","thinkingConfig":{"maxBudget":6000}},"openrouter/fusion":{"name":"OpenRouter: Fusion","maxTokens":0,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":-1000000,"outputPrice":-1000000,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a..."},"moonshotai/kimi-k2.7-code":{"name":"MoonshotAI: Kimi K2.7 Code","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.67,"outputPrice":3.4,"cacheReadsPrice":0.19,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","thinkingConfig":{"maxBudget":6000}},"moonshotai/kimi-k2.7-code:batch":{"name":"MoonshotAI: Kimi K2.7 Code (batch)","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.95,"outputPrice":4,"cacheReadsPrice":0.19,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","thinkingConfig":{"maxBudget":6000}},"~anthropic/claude-fable-latest":{"name":"Anthropic: Claude Fable Latest","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":10,"outputPrice":50,"cacheReadsPrice":1,"description":"This model always redirects to the latest model in the Claude Fable family.","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-fable-5":{"name":"Anthropic: Claude Fable 5","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":10,"outputPrice":50,"cacheWritesPrice":12.5,"cacheReadsPrice":1,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-fable-5:1m":{"name":"Anthropic: Claude Fable 5","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":10,"outputPrice":50,"cacheWritesPrice":12.5,"cacheReadsPrice":1,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":10,"outputPrice":50,"cacheWritesPrice":12.5,"cacheReadsPrice":1},{"contextWindow":9007199254740991,"inputPrice":10,"outputPrice":50,"cacheWritesPrice":12.5,"cacheReadsPrice":1}]},"anthropic/claude-fable-5:batch":{"name":"Anthropic: Claude Fable 5 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheReadsPrice":0.5,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","thinkingConfig":{"maxBudget":6000}},"nex-agi/nex-n2-pro":{"name":"Nex AGI: Nex-N2-Pro","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":1,"cacheReadsPrice":0.024999999999999998,"description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3.5-content-safety:free":{"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","maxTokens":8192,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-ultra-550b-a55b":{"name":"NVIDIA: Nemotron 3 Ultra","maxTokens":0,"contextWindow":512288,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":3.5999999999999996,"cacheReadsPrice":0.19999999999999998,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-ultra-550b-a55b:batch":{"name":"NVIDIA: Nemotron 3 Ultra (batch)","maxTokens":0,"contextWindow":512288,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":3.5999999999999996,"cacheReadsPrice":0.19999999999999998,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-ultra-550b-a55b:free":{"name":"NVIDIA: Nemotron 3 Ultra (free)","maxTokens":65536,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.7-plus":{"name":"Qwen: Qwen3.7 Plus","maxTokens":131072,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.32,"outputPrice":1.28,"cacheReadsPrice":0.064,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m3":{"name":"MiniMax: MiniMax M3","maxTokens":512000,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.06,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m3:batch":{"name":"MiniMax: MiniMax M3 (batch)","maxTokens":0,"contextWindow":524288,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.06,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m3:free":{"name":"MiniMax: MiniMax M3 (free)","maxTokens":0,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","thinkingConfig":{"maxBudget":6000}},"stepfun/step-3.7-flash":{"name":"StepFun: Step 3.7 Flash","maxTokens":256000,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":1.15,"cacheReadsPrice":0.04,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.8-fast":{"name":"Anthropic: Claude Opus 4.8 (Fast)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":10,"outputPrice":50,"cacheReadsPrice":1,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.8":{"name":"Anthropic: Claude Opus 4.8","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.8:1m":{"name":"Anthropic: Claude Opus 4.8","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5},{"contextWindow":9007199254740991,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5}]},"anthropic/claude-opus-4.8:batch":{"name":"Anthropic: Claude Opus 4.8 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":12.5,"cacheReadsPrice":0.25,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.7-max":{"name":"Qwen: Qwen3.7 Max","maxTokens":131072,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.475,"outputPrice":4.425,"cacheReadsPrice":0.295,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","thinkingConfig":{"maxBudget":6000}},"x-ai/grok-build-0.1":{"name":"SpaceXAI: Grok Build 0.1","maxTokens":0,"contextWindow":256000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":2,"cacheReadsPrice":0.19999999999999998,"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...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.5-flash":{"name":"Google: Gemini 3.5 Flash","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.5,"outputPrice":9,"cacheReadsPrice":0.15,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.5-flash:batch":{"name":"Google: Gemini 3.5 Flash (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.75,"outputPrice":4.5,"cacheReadsPrice":0.075,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.7-fast":{"name":"Anthropic: Claude Opus 4.7 (Fast)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":30,"outputPrice":150,"cacheReadsPrice":3,"description":"Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","thinkingConfig":{"maxBudget":6000}},"perceptron/perceptron-mk1":{"name":"Perceptron: Perceptron Mk1","maxTokens":8192,"contextWindow":32768,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.15,"outputPrice":1.5,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-flash-lite":{"name":"Google: Gemini 3.1 Flash Lite","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":1.5,"cacheReadsPrice":0.024999999999999998,"description":"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...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-flash-lite:batch":{"name":"Google: Gemini 3.1 Flash Lite (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.125,"outputPrice":0.75,"cacheReadsPrice":0.012499999999999999,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-chat-latest":{"name":"OpenAI: GPT Chat Latest","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":30,"cacheReadsPrice":0.5,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates..."},"x-ai/grok-4.3":{"name":"SpaceXAI: Grok 4.3","maxTokens":0,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":2.5,"cacheReadsPrice":0.19999999999999998,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","thinkingConfig":{"maxBudget":6000}},"ibm-granite/granite-4.1-8b":{"name":"IBM: Granite 4.1 8B","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.049999999999999996,"outputPrice":0.09999999999999999,"cacheReadsPrice":0.049999999999999996,"description":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks..."},"mistralai/mistral-medium-3-5":{"name":"Mistral: Mistral Medium 3.5","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":1.5,"outputPrice":7.5,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"name":"NVIDIA: Nemotron 3 Nano Omni (free)","maxTokens":65536,"contextWindow":256000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...","thinkingConfig":{"maxBudget":6000}},"~anthropic/claude-haiku-latest":{"name":"Anthropic Claude Haiku Latest","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":5,"cacheReadsPrice":0.09999999999999999,"description":"This model always redirects to the latest model in the Anthropic Claude Haiku family.","thinkingConfig":{"maxBudget":6000}},"~openai/gpt-mini-latest":{"name":"OpenAI GPT Mini Latest","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.75,"outputPrice":4.5,"cacheReadsPrice":0.075,"description":"This model always redirects to the latest model in the OpenAI GPT Mini family.","thinkingConfig":{"maxBudget":6000}},"~google/gemini-pro-latest":{"name":"Google Gemini Pro Latest","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"This model always redirects to the latest model in the Google Gemini Pro family.","thinkingConfig":{"maxBudget":6000}},"~moonshotai/kimi-latest":{"name":"MoonshotAI Kimi Latest","maxTokens":1048576,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.8,"outputPrice":14,"cacheReadsPrice":0.29,"description":"This model always redirects to the latest model in the MoonshotAI Kimi family.","thinkingConfig":{"maxBudget":6000}},"~google/gemini-flash-latest":{"name":"Google Gemini Flash Latest","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.375,"outputPrice":1.875,"cacheReadsPrice":0.0375,"description":"This model always redirects to the latest model in the Google Gemini Flash family.","thinkingConfig":{"maxBudget":6000}},"~anthropic/claude-sonnet-latest":{"name":"Anthropic Claude Sonnet Latest","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":10,"cacheReadsPrice":0.19999999999999998,"description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family.","thinkingConfig":{"maxBudget":6000}},"~openai/gpt-latest":{"name":"OpenAI GPT Latest","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":10,"cacheReadsPrice":0.19999999999999998,"description":"This model always redirects to the latest model in the OpenAI GPT family.","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-plus-20260420":{"name":"Qwen: Qwen3.5 Plus 2026-04-20","maxTokens":65536,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.3,"outputPrice":1.7999999999999998,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.6-flash":{"name":"Qwen: Qwen3.6 Flash","maxTokens":65536,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.1875,"outputPrice":1.125,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.6-35b-a3b":{"name":"Qwen: Qwen3.6 35B A3B","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.14,"outputPrice":1,"cacheReadsPrice":0.049999999999999996,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.6-max-preview":{"name":"Qwen: Qwen3.6 Max Preview","maxTokens":65536,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1.0270000000000001,"outputPrice":6.162,"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.6-27b":{"name":"Qwen: Qwen3.6 27B","maxTokens":81920,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.32,"outputPrice":3.1999999999999997,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.5-pro":{"name":"OpenAI: GPT-5.5 Pro","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":30,"outputPrice":180,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.5-pro:batch":{"name":"OpenAI: GPT-5.5 Pro (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":15,"outputPrice":90,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.5":{"name":"OpenAI: GPT-5.5","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":30,"cacheReadsPrice":0.5,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.5:batch":{"name":"OpenAI: GPT-5.5 (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":15,"cacheReadsPrice":0.25,"description":"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...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v4-pro":{"name":"DeepSeek: DeepSeek V4 Pro 0423","maxTokens":384000,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.790308,"outputPrice":1.580616,"cacheReadsPrice":0.065859,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v4-flash":{"name":"DeepSeek: DeepSeek V4 Flash 0423","maxTokens":384000,"contextWindow":1048576,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.088606,"outputPrice":0.177212,"cacheReadsPrice":0.017721200000000003,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","thinkingConfig":{"maxBudget":6000}},"tencent/hy3-preview":{"name":"Tencent: Hy3 preview","maxTokens":0,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.18,"outputPrice":0.6,"cacheReadsPrice":0.06,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","thinkingConfig":{"maxBudget":6000}},"xiaomi/mimo-v2.5-pro":{"name":"Xiaomi: MiMo-V2.5-Pro","maxTokens":131072,"contextWindow":1050000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.435,"outputPrice":0.87,"cacheReadsPrice":0.0036,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","thinkingConfig":{"maxBudget":6000}},"xiaomi/mimo-v2.5":{"name":"Xiaomi: MiMo-V2.5","maxTokens":131072,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.14,"outputPrice":0.28,"cacheReadsPrice":0.0028,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-image-2":{"name":"OpenAI: GPT-5.4 Image 2","maxTokens":128000,"contextWindow":272000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":8,"outputPrice":15,"cacheReadsPrice":2,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","thinkingConfig":{"maxBudget":6000}},"~anthropic/claude-opus-latest":{"name":"Anthropic: Claude Opus Latest","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheReadsPrice":0.5,"description":"This model always redirects to the latest model in the Claude Opus family.","thinkingConfig":{"maxBudget":6000}},"openrouter/pareto-code":{"name":"Pareto Code Router","maxTokens":0,"contextWindow":2000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":-1000000,"outputPrice":-1000000,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how..."},"moonshotai/kimi-k2.6":{"name":"MoonshotAI: Kimi K2.6","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.95,"outputPrice":4,"cacheReadsPrice":0.16,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.7":{"name":"Anthropic: Claude Opus 4.7","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.7:1m":{"name":"Anthropic: Claude Opus 4.7","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5},{"contextWindow":9007199254740991,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5}]},"anthropic/claude-opus-4.7:batch":{"name":"Anthropic: Claude Opus 4.7 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":12.5,"cacheReadsPrice":0.25,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5.1":{"name":"Z.ai: GLM 5.1","maxTokens":202752,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.26,"outputPrice":3.9600000000000004,"cacheReadsPrice":0.234,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","thinkingConfig":{"maxBudget":6000}},"google/gemma-4-26b-a4b-it":{"name":"Google: Gemma 4 26B A4B ","maxTokens":16384,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.07,"outputPrice":0.33999999999999997,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","thinkingConfig":{"maxBudget":6000}},"google/gemma-4-26b-a4b-it:free":{"name":"Google: Gemma 4 26B A4B  (free)","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","thinkingConfig":{"maxBudget":6000}},"google/gemma-4-31b-it":{"name":"Google: Gemma 4 31B","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.33999999999999997,"cacheReadsPrice":0.09999999999999999,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","thinkingConfig":{"maxBudget":6000}},"google/gemma-4-31b-it:free":{"name":"Google: Gemma 4 31B (free)","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.6-plus":{"name":"Qwen: Qwen3.6 Plus","maxTokens":65536,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.325,"outputPrice":1.95,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5v-turbo":{"name":"Z.ai: GLM 5V Turbo","maxTokens":131072,"contextWindow":202752,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.2,"outputPrice":4,"cacheReadsPrice":0.24,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","thinkingConfig":{"maxBudget":6000}},"arcee-ai/trinity-large-thinking":{"name":"Arcee AI: Trinity Large Thinking","maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.22,"outputPrice":0.85,"cacheReadsPrice":0.06,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...","thinkingConfig":{"maxBudget":6000}},"x-ai/grok-4.20-multi-agent":{"name":"SpaceXAI: Grok 4.20 Multi-Agent","maxTokens":0,"contextWindow":2000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":2.5,"cacheReadsPrice":0.19999999999999998,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","thinkingConfig":{"maxBudget":6000}},"x-ai/grok-4.20":{"name":"SpaceXAI: Grok 4.20","maxTokens":0,"contextWindow":2000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":2.5,"cacheReadsPrice":0.19999999999999998,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","thinkingConfig":{"maxBudget":6000}},"google/lyria-3-pro-preview":{"name":"Google: Lyria 3 Pro Preview","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz..."},"google/lyria-3-clip-preview":{"name":"Google: Lyria 3 Clip Preview","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate..."},"kwaipilot/kat-coder-pro-v2":{"name":"Kwaipilot: KAT-Coder-Pro V2","maxTokens":80000,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.06,"description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,..."},"rekaai/reka-edge":{"name":"Reka Edge","maxTokens":16384,"contextWindow":16384,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.09999999999999999,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,..."},"minimax/minimax-m2.7":{"name":"MiniMax: MiniMax M2.7","maxTokens":0,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.06,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m2.7:free":{"name":"MiniMax: MiniMax M2.7 (free)","maxTokens":0,"contextWindow":196608,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-nano":{"name":"OpenAI: GPT-5.4 Nano","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":1.25,"cacheReadsPrice":0.02,"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. It supports text and image inputs and is designed for low-latency...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-nano:batch":{"name":"OpenAI: GPT-5.4 Nano (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.625,"cacheReadsPrice":0.01,"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. It supports text and image inputs and is designed for low-latency...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-mini":{"name":"OpenAI: GPT-5.4 Mini","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.75,"outputPrice":4.5,"cacheReadsPrice":0.075,"description":"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,...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-mini:batch":{"name":"OpenAI: GPT-5.4 Mini (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.375,"outputPrice":2.25,"cacheReadsPrice":0.0375,"description":"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,...","thinkingConfig":{"maxBudget":6000}},"mistralai/mistral-small-2603":{"name":"Mistral: Mistral Small 4","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":0.6,"cacheReadsPrice":0.015,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5-turbo":{"name":"Z.ai: GLM 5 Turbo","maxTokens":131072,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.2,"outputPrice":4,"cacheReadsPrice":0.24,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-super-120b-a12b":{"name":"NVIDIA: Nemotron 3 Super","maxTokens":16384,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.08499999999999999,"outputPrice":0.39999999999999997,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-super-120b-a12b:free":{"name":"NVIDIA: Nemotron 3 Super (free)","maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","thinkingConfig":{"maxBudget":6000}},"bytedance-seed/seed-2.0-lite":{"name":"ByteDance Seed: Seed-2.0-Lite","maxTokens":131072,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":2,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-9b":{"name":"Qwen: Qwen3.5-9B","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.15,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-pro":{"name":"OpenAI: GPT-5.4 Pro","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":30,"outputPrice":180,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4-pro:batch":{"name":"OpenAI: GPT-5.4 Pro (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":15,"outputPrice":90,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4":{"name":"OpenAI: GPT-5.4","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":15,"cacheReadsPrice":0.25,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.4:batch":{"name":"OpenAI: GPT-5.4 (batch)","maxTokens":128000,"contextWindow":1050000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":7.5,"cacheReadsPrice":0.125,"description":"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...","thinkingConfig":{"maxBudget":6000}},"inception/mercury-2":{"name":"Inception: Mercury 2","maxTokens":50000,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":0.75,"cacheReadsPrice":0.024999999999999998,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-flash-lite-preview":{"name":"Google: Gemini 3.1 Flash Lite Preview","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":1.5,"cacheReadsPrice":0.024999999999999998,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","thinkingConfig":{"maxBudget":6000}},"bytedance-seed/seed-2.0-mini":{"name":"ByteDance Seed: Seed-2.0-Mini","maxTokens":131072,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-flash-image-preview":{"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","maxTokens":8192,"contextWindow":65536,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":3,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-35b-a3b":{"name":"Qwen: Qwen3.5-35B-A3B","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":1.25,"cacheReadsPrice":0.25,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-27b":{"name":"Qwen: Qwen3.5-27B","maxTokens":65536,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.195,"outputPrice":1.56,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-122b-a10b":{"name":"Qwen: Qwen3.5-122B-A10B","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.26,"outputPrice":2.08,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-flash-02-23":{"name":"Qwen: Qwen3.5-Flash","maxTokens":65536,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.065,"outputPrice":0.26,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-pro-preview-customtools":{"name":"Google: Gemini 3.1 Pro Preview Custom Tools","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.3-codex":{"name":"OpenAI: GPT-5.3-Codex","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.75,"outputPrice":14,"cacheReadsPrice":0.175,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","thinkingConfig":{"maxBudget":6000}},"aion-labs/aion-2.0":{"name":"AionLabs: Aion-2.0","maxTokens":32768,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.7999999999999999,"outputPrice":1.5999999999999999,"cacheReadsPrice":0.19999999999999998,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-pro-preview":{"name":"Google: Gemini 3.1 Pro Preview","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3.1-pro-preview:batch":{"name":"Google: Gemini 3.1 Pro Preview (batch)","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":1,"outputPrice":6,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-4.6":{"name":"Anthropic: Claude Sonnet 4.6","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-4.6:1m":{"name":"Anthropic: Claude Sonnet 4.6","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3},{"contextWindow":9007199254740991,"inputPrice":6,"outputPrice":22.5,"cacheWritesPrice":7.5,"cacheReadsPrice":0.6}]},"anthropic/claude-sonnet-4.6:batch":{"name":"Anthropic: Claude Sonnet 4.6 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.5,"outputPrice":7.5,"cacheReadsPrice":0.15,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-plus-02-15":{"name":"Qwen: Qwen3.5 Plus 2026-02-15","maxTokens":65536,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.26,"outputPrice":1.56,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3.5-397b-a17b":{"name":"Qwen: Qwen3.5 397B A17B","maxTokens":262144,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.5,"outputPrice":3.5999999999999996,"cacheReadsPrice":0.3,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m2.5":{"name":"MiniMax: MiniMax M2.5","maxTokens":128000,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.27,"outputPrice":1.08,"cacheReadsPrice":0.027,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-5":{"name":"Z.ai: GLM 5","maxTokens":128000,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":1.92,"cacheReadsPrice":0.12,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-max-thinking":{"name":"Qwen: Qwen3 Max Thinking","maxTokens":65536,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.78,"outputPrice":3.9,"description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.6":{"name":"Anthropic: Claude Opus 4.6","maxTokens":128000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.6:1m":{"name":"Anthropic: Claude Opus 4.6","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5},{"contextWindow":9007199254740991,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5}]},"anthropic/claude-opus-4.6:batch":{"name":"Anthropic: Claude Opus 4.6 (batch)","maxTokens":128000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":12.5,"cacheReadsPrice":0.25,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-coder-next":{"name":"Qwen: Qwen3 Coder Next","maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.12,"outputPrice":0.7999999999999999,"cacheReadsPrice":0.07,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per..."},"openrouter/free":{"name":"Free Models Router","maxTokens":0,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0,"outputPrice":0,"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","thinkingConfig":{"maxBudget":6000}},"stepfun/step-3.5-flash":{"name":"StepFun: Step 3.5 Flash","maxTokens":65536,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.3,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","thinkingConfig":{"maxBudget":6000}},"moonshotai/kimi-k2.5":{"name":"MoonshotAI: Kimi K2.5","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":3,"cacheReadsPrice":0.09999999999999999,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","thinkingConfig":{"maxBudget":6000}},"upstage/solar-pro-3":{"name":"Upstage: Solar Pro 3","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":0.6,"cacheReadsPrice":0.015,"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m2-her":{"name":"MiniMax: MiniMax M2-her","maxTokens":2048,"contextWindow":65536,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.03,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message..."},"writer/palmyra-x5":{"name":"Writer: Palmyra X5","maxTokens":8192,"contextWindow":1040000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.6,"outputPrice":6,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million..."},"openai/gpt-audio":{"name":"OpenAI: GPT Audio","maxTokens":16384,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":2.5,"outputPrice":10,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced..."},"openai/gpt-audio-mini":{"name":"OpenAI: GPT Audio Mini","maxTokens":16384,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.6,"outputPrice":2.4,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million..."},"z-ai/glm-4.7-flash":{"name":"Z.ai: GLM 4.7 Flash","maxTokens":16384,"contextWindow":202752,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.06,"outputPrice":0.39999999999999997,"cacheReadsPrice":0.01,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.2-codex":{"name":"OpenAI: GPT-5.2-Codex","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.75,"outputPrice":14,"cacheReadsPrice":0.175,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","thinkingConfig":{"maxBudget":6000}},"bytedance-seed/seed-1.6-flash":{"name":"ByteDance Seed: Seed 1.6 Flash","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.075,"outputPrice":0.3,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","thinkingConfig":{"maxBudget":6000}},"bytedance-seed/seed-1.6":{"name":"ByteDance Seed: Seed 1.6","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":2,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m2.1":{"name":"MiniMax: MiniMax M2.1","maxTokens":131072,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1.2,"cacheReadsPrice":0.03,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-4.7":{"name":"Z.ai: GLM 4.7","maxTokens":131072,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.39999999999999997,"outputPrice":1.75,"cacheReadsPrice":0.08,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3-flash-preview":{"name":"Google: Gemini 3 Flash Preview","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.5,"outputPrice":3,"cacheReadsPrice":0.049999999999999996,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3-flash-preview:batch":{"name":"Google: Gemini 3 Flash Preview (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":1.5,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","thinkingConfig":{"maxBudget":6000}},"nvidia/nemotron-3-nano-30b-a3b":{"name":"NVIDIA: Nemotron 3 Nano 30B A3B","maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.03,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.2-chat":{"name":"OpenAI: GPT-5.2 Chat","maxTokens":32000,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.75,"outputPrice":14,"cacheReadsPrice":0.175,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on..."},"openai/gpt-5.2-pro":{"name":"OpenAI: GPT-5.2 Pro","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":21,"outputPrice":168,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.2-pro:batch":{"name":"OpenAI: GPT-5.2 Pro (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":10.5,"outputPrice":84,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.2":{"name":"OpenAI: GPT-5.2","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.75,"outputPrice":14,"cacheReadsPrice":0.175,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.2:batch":{"name":"OpenAI: GPT-5.2 (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.875,"outputPrice":7,"cacheReadsPrice":0.0875,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","thinkingConfig":{"maxBudget":6000}},"mistralai/devstral-2512":{"name":"Mistral: Devstral 2 2512","maxTokens":0,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.44,"outputPrice":2.2,"cacheReadsPrice":0.044,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring..."},"relace/relace-search":{"name":"Relace: Relace Search","maxTokens":128000,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1,"outputPrice":3,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic..."},"z-ai/glm-4.6v":{"name":"Z.ai: GLM 4.6V","maxTokens":32768,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":0.8999999999999999,"cacheReadsPrice":0.055,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","thinkingConfig":{"maxBudget":6000}},"openrouter/bodybuilder":{"name":"Body Builder (beta)","maxTokens":0,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":-1000000,"outputPrice":-1000000,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:..."},"openai/gpt-5.1-codex-max":{"name":"OpenAI: GPT-5.1-Codex-Max","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","thinkingConfig":{"maxBudget":6000}},"amazon/nova-2-lite-v1":{"name":"Amazon: Nova 2 Lite","maxTokens":65535,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.3,"outputPrice":2.5,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","thinkingConfig":{"maxBudget":6000}},"mistralai/ministral-14b-2512":{"name":"Mistral: Ministral 3 14B 2512","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.02,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language..."},"mistralai/ministral-8b-2512":{"name":"Mistral: Ministral 3 8B 2512","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":0.15,"cacheReadsPrice":0.015,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities."},"mistralai/ministral-3b-2512":{"name":"Mistral: Ministral 3 3B 2512","maxTokens":0,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.09999999999999999,"cacheReadsPrice":0.01,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities."},"mistralai/mistral-large-2512":{"name":"Mistral: Mistral Large 3 2512","maxTokens":0,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.5,"outputPrice":1.5,"cacheReadsPrice":0.049999999999999996,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license."},"deepseek/deepseek-v3.2":{"name":"DeepSeek: DeepSeek V3.2","maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.26,"outputPrice":0.38,"cacheReadsPrice":0.13,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.5":{"name":"Anthropic: Claude Opus 4.5","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":5,"outputPrice":25,"cacheWritesPrice":6.25,"cacheReadsPrice":0.5,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.5:batch":{"name":"Anthropic: Claude Opus 4.5 (batch)","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":12.5,"cacheReadsPrice":0.25,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","thinkingConfig":{"maxBudget":6000}},"allenai/olmo-3-32b-think":{"name":"AllenAI: Olmo 3 32B Think","maxTokens":65536,"contextWindow":65536,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.15,"outputPrice":0.5,"description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...","thinkingConfig":{"maxBudget":6000}},"google/gemini-3-pro-image-preview":{"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","maxTokens":32768,"contextWindow":65536,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":12,"cacheReadsPrice":0.19999999999999998,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.1":{"name":"OpenAI: GPT-5.1","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.1:batch":{"name":"OpenAI: GPT-5.1 (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.625,"outputPrice":5,"cacheReadsPrice":0.0625,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.1-codex":{"name":"OpenAI: GPT-5.1-Codex","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.13,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5.1-codex-mini":{"name":"OpenAI: GPT-5.1-Codex-Mini","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":2,"cacheReadsPrice":0.03,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","thinkingConfig":{"maxBudget":6000}},"moonshotai/kimi-k2-thinking":{"name":"MoonshotAI: Kimi K2 Thinking","maxTokens":100352,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":2.5,"cacheReadsPrice":0.15,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","thinkingConfig":{"maxBudget":6000}},"amazon/nova-premier-v1":{"name":"Amazon: Nova Premier 1.0","maxTokens":32000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":12.5,"cacheReadsPrice":0.625,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models."},"perplexity/sonar-pro-search":{"name":"Perplexity: Sonar Pro Search","maxTokens":8000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":3,"outputPrice":15,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","thinkingConfig":{"maxBudget":6000}},"mistralai/voxtral-small-24b-2507":{"name":"Mistral: Voxtral Small 24B 2507","maxTokens":0,"contextWindow":32000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.3,"cacheReadsPrice":0.01,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio..."},"openai/gpt-oss-safeguard-20b":{"name":"OpenAI: gpt-oss-safeguard-20b","maxTokens":65536,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.075,"outputPrice":0.3,"cacheReadsPrice":0.0375,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-m2":{"name":"MiniMax: MiniMax M2","maxTokens":131072,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.255,"outputPrice":1.02,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-vl-32b-instruct":{"name":"Qwen: Qwen3 VL 32B Instruct","maxTokens":32768,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.10400000000000001,"outputPrice":0.41600000000000004,"description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text..."},"ibm-granite/granite-4.0-h-micro":{"name":"IBM: Granite 4.0 Micro","maxTokens":131000,"contextWindow":131000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.017,"outputPrice":0.112,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long..."},"openai/gpt-5-image-mini":{"name":"OpenAI: GPT-5 Image Mini","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":2,"cacheReadsPrice":0.25,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-haiku-4.5":{"name":"Anthropic: Claude Haiku 4.5","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":5,"cacheWritesPrice":1.25,"cacheReadsPrice":0.1,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-haiku-4.5:batch":{"name":"Anthropic: Claude Haiku 4.5 (batch)","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.5,"outputPrice":2.5,"cacheReadsPrice":0.049999999999999996,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-vl-8b-thinking":{"name":"Qwen: Qwen3 VL 8B Thinking","maxTokens":32768,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.18,"outputPrice":2.0999999999999996,"description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-vl-8b-instruct":{"name":"Qwen: Qwen3 VL 8B Instruct","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.117,"outputPrice":0.45499999999999996,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon..."},"openai/gpt-5-image":{"name":"OpenAI: GPT-5 Image","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":10,"outputPrice":10,"cacheReadsPrice":1.25,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-flash-image":{"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","maxTokens":8192,"contextWindow":32768,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":2.5,"cacheReadsPrice":0.03,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,..."},"qwen/qwen3-vl-30b-a3b-thinking":{"name":"Qwen: Qwen3 VL 30B A3B Thinking","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.19999999999999998,"outputPrice":2.4,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-vl-30b-a3b-instruct":{"name":"Qwen: Qwen3 VL 30B A3B Instruct","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.13,"outputPrice":0.52,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception..."},"openai/gpt-5-pro":{"name":"OpenAI: GPT-5 Pro","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":15,"outputPrice":120,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5-pro:batch":{"name":"OpenAI: GPT-5 Pro (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":7.5,"outputPrice":60,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-4.6":{"name":"Z.ai: GLM 4.6","maxTokens":131072,"contextWindow":204800,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.5,"outputPrice":2,"cacheReadsPrice":0.09999999999999999,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-4.5":{"name":"Anthropic: Claude Sonnet 4.5","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-4.5:1m":{"name":"Anthropic: Claude Sonnet 4.5","maxTokens":64000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3},{"contextWindow":9007199254740991,"inputPrice":6,"outputPrice":22.5,"cacheWritesPrice":7.5,"cacheReadsPrice":0.6}]},"anthropic/claude-sonnet-4.5:batch":{"name":"Anthropic: Claude Sonnet 4.5 (batch)","maxTokens":64000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.5,"outputPrice":7.5,"cacheReadsPrice":0.15,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v3.2-exp":{"name":"DeepSeek: DeepSeek V3.2 Exp","maxTokens":65536,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.27,"outputPrice":0.41,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","thinkingConfig":{"maxBudget":6000}},"thedrummer/cydonia-24b-v4.1":{"name":"TheDrummer: Cydonia 24B V4.1","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":0.5,"cacheReadsPrice":0.15,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence."},"relace/relace-apply-3":{"name":"Relace: Relace Apply 3","maxTokens":128000,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.85,"outputPrice":1.25,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at..."},"qwen/qwen3-vl-235b-a22b-thinking":{"name":"Qwen: Qwen3 VL 235B A22B Thinking","maxTokens":32768,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.39999999999999997,"outputPrice":4,"description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-vl-235b-a22b-instruct":{"name":"Qwen: Qwen3 VL 235B A22B Instruct","maxTokens":32768,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.21,"outputPrice":1.9,"cacheReadsPrice":0.09999999999999999,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table..."},"qwen/qwen3-max":{"name":"Qwen: Qwen3 Max","maxTokens":65536,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.78,"outputPrice":3.9,"cacheReadsPrice":0.156,"description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It..."},"qwen/qwen3-coder-plus":{"name":"Qwen: Qwen3 Coder Plus","maxTokens":65536,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.65,"outputPrice":3.25,"cacheReadsPrice":0.13,"description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and..."},"openai/gpt-5-codex:batch":{"name":"OpenAI: GPT-5 Codex (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.625,"outputPrice":5,"cacheReadsPrice":0.0625,"description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-v3.1-terminus":{"name":"DeepSeek: DeepSeek V3.1 Terminus","maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.27,"outputPrice":1,"cacheReadsPrice":0.135,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-coder-flash":{"name":"Qwen: Qwen3 Coder Flash","maxTokens":65536,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.195,"outputPrice":0.975,"cacheReadsPrice":0.039,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling..."},"qwen/qwen3-next-80b-a3b-thinking":{"name":"Qwen: Qwen3 Next 80B A3B Thinking","maxTokens":32768,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.15,"outputPrice":1.2,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-next-80b-a3b-instruct":{"name":"Qwen: Qwen3 Next 80B A3B Instruct","maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":1.1,"cacheReadsPrice":0.07,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual..."},"qwen/qwen-plus-2025-07-28":{"name":"Qwen: Qwen Plus 0728","maxTokens":32768,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.26,"outputPrice":0.78,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination."},"qwen/qwen-plus-2025-07-28:thinking":{"name":"Qwen: Qwen Plus 0728 (thinking)","maxTokens":32768,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.26,"outputPrice":0.78,"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","thinkingConfig":{"maxBudget":6000}},"moonshotai/kimi-k2-0905":{"name":"MoonshotAI: Kimi K2 0905","maxTokens":100352,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.6,"outputPrice":2.5,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32..."},"qwen/qwen3-30b-a3b-thinking-2507":{"name":"Qwen: Qwen3 30B A3B Thinking 2507","maxTokens":32768,"contextWindow":81920,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.19999999999999998,"outputPrice":2.4,"description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...","thinkingConfig":{"maxBudget":6000}},"nousresearch/hermes-4-70b":{"name":"Nous: Hermes 4 70B","maxTokens":0,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.13,"outputPrice":0.39999999999999997,"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...","thinkingConfig":{"maxBudget":6000}},"nousresearch/hermes-4-405b":{"name":"Nous: Hermes 4 405B","maxTokens":0,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1,"outputPrice":3,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-chat-v3.1":{"name":"DeepSeek: DeepSeek V3.1","maxTokens":161000,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.55,"outputPrice":1.6500000000000001,"cacheReadsPrice":0.55,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","thinkingConfig":{"maxBudget":6000}},"mistralai/mistral-medium-3.1":{"name":"Mistral: Mistral Medium 3.1","maxTokens":0,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.39999999999999997,"outputPrice":2,"cacheReadsPrice":0.04,"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..."},"z-ai/glm-4.5v":{"name":"Z.ai: GLM 4.5V","maxTokens":16384,"contextWindow":65536,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":1.7999999999999998,"cacheReadsPrice":0.11,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5":{"name":"OpenAI: GPT-5","maxTokens":8192,"contextWindow":272000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5:batch":{"name":"OpenAI: GPT-5 (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.625,"outputPrice":5,"cacheReadsPrice":0.0625,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5-mini":{"name":"OpenAI: GPT-5 Mini","maxTokens":8192,"contextWindow":272000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":2,"cacheReadsPrice":0.024999999999999998,"description":"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....","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5-mini:batch":{"name":"OpenAI: GPT-5 Mini (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.125,"outputPrice":1,"cacheReadsPrice":0.012499999999999999,"description":"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....","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5-nano":{"name":"OpenAI: GPT-5 Nano","maxTokens":8192,"contextWindow":272000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.049999999999999996,"outputPrice":0.39999999999999997,"cacheReadsPrice":0.005,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-5-nano:batch":{"name":"OpenAI: GPT-5 Nano (batch)","maxTokens":128000,"contextWindow":400000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.024999999999999998,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.0025,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-oss-120b":{"name":"OpenAI: gpt-oss-120b","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.037,"outputPrice":0.16999999999999998,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-oss-20b":{"name":"OpenAI: gpt-oss-20b","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.03,"outputPrice":0.13,"cacheReadsPrice":0.03,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.1":{"name":"Anthropic: Claude Opus 4.1","maxTokens":32000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":15,"outputPrice":75,"cacheWritesPrice":18.75,"cacheReadsPrice":1.5,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4.1:batch":{"name":"Anthropic: Claude Opus 4.1 (batch)","maxTokens":32000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":7.5,"outputPrice":37.5,"cacheReadsPrice":0.75,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","thinkingConfig":{"maxBudget":6000}},"mistralai/codestral-2508":{"name":"Mistral: Codestral 2508","maxTokens":0,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":0.8999999999999999,"cacheReadsPrice":0.03,"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.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)"},"qwen/qwen3-coder-30b-a3b-instruct":{"name":"Qwen: Qwen3 Coder 30B A3B Instruct","maxTokens":262144,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.07,"outputPrice":0.28,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the..."},"qwen/qwen3-30b-a3b-instruct-2507":{"name":"Qwen: Qwen3 30B A3B Instruct 2507","maxTokens":32000,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.04815,"outputPrice":0.19305,"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. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and..."},"z-ai/glm-4.5":{"name":"Z.ai: GLM 4.5","maxTokens":98304,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.6,"outputPrice":2.2,"cacheReadsPrice":0.11,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","thinkingConfig":{"maxBudget":6000}},"z-ai/glm-4.5-air":{"name":"Z.ai: GLM 4.5 Air","maxTokens":98304,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.13,"outputPrice":0.85,"cacheReadsPrice":0.024999999999999998,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-235b-a22b-thinking-2507":{"name":"Qwen: Qwen3 235B A22B Thinking 2507","maxTokens":0,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.22999999999999998,"outputPrice":2.3,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-coder":{"name":"Qwen: Qwen3 Coder 480B A35B","maxTokens":65536,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":1,"cacheReadsPrice":0.09999999999999999,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over..."},"bytedance/ui-tars-1.5-7b":{"name":"ByteDance: UI-TARS 7B ","maxTokens":2048,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.09999999999999999,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement..."},"google/gemini-2.5-flash-lite":{"name":"Google: Gemini 2.5 Flash Lite","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cacheReadsPrice":0.01,"description":"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...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-flash-lite:batch":{"name":"Google: Gemini 2.5 Flash Lite (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.01,"description":"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...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-235b-a22b-2507":{"name":"Qwen: Qwen3 235B A22B Instruct 2507","maxTokens":16384,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.09,"outputPrice":0.55,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,..."},"moonshotai/kimi-k2":{"name":"MoonshotAI: Kimi K2 0711","maxTokens":100352,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.5700000000000001,"outputPrice":2.3,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for..."},"cognitivecomputations/dolphin-mistral-24b-venice-edition":{"name":"Venice: Uncensored","maxTokens":8192,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.19999999999999998,"outputPrice":0.8999999999999999,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving..."},"tencent/hunyuan-a13b-instruct":{"name":"Tencent: Hunyuan A13B Instruct","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.14,"outputPrice":0.5700000000000001,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","thinkingConfig":{"maxBudget":6000}},"morph/morph-v3-large":{"name":"Morph: Morph V3 Large","maxTokens":131072,"contextWindow":262144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.8999999999999999,"outputPrice":1.9,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>..."},"morph/morph-v3-fast":{"name":"Morph: Morph V3 Fast","maxTokens":38000,"contextWindow":81920,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.7999999999999999,"outputPrice":1.2,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>..."},"baidu/ernie-4.5-vl-424b-a47b":{"name":"Baidu: ERNIE 4.5 VL 424B A47B ","maxTokens":16000,"contextWindow":123000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.42,"outputPrice":1.25,"description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...","thinkingConfig":{"maxBudget":6000}},"mistralai/mistral-small-3.2-24b-instruct":{"name":"Mistral: Mistral Small 3.2 24B","maxTokens":16384,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.075,"outputPrice":0.19999999999999998,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on..."},"minimax/minimax-m1":{"name":"MiniMax: MiniMax M1","maxTokens":40000,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.55,"outputPrice":2.2,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-flash":{"name":"Google: Gemini 2.5 Flash","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.3,"outputPrice":2.5,"cacheReadsPrice":0.03,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-flash:batch":{"name":"Google: Gemini 2.5 Flash (batch)","maxTokens":8192,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":1.25,"cacheReadsPrice":0.03,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-pro":{"name":"Google: Gemini 2.5 Pro","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-pro:batch":{"name":"Google: Gemini 2.5 Pro (batch)","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.625,"outputPrice":5,"cacheReadsPrice":0.125,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","thinkingConfig":{"maxBudget":6000}},"openai/o3-pro":{"name":"OpenAI: o3 Pro","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":20,"outputPrice":80,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","thinkingConfig":{"maxBudget":6000}},"openai/o3-pro:batch":{"name":"OpenAI: o3 Pro (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":10,"outputPrice":40,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","thinkingConfig":{"maxBudget":6000}},"google/gemini-2.5-pro-preview":{"name":"Google: Gemini 2.5 Pro Preview 06-05","maxTokens":65536,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-r1-0528":{"name":"DeepSeek: R1 0528","maxTokens":32768,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.5,"outputPrice":2.1500000000000004,"cacheReadsPrice":0.35,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-opus-4":{"name":"Anthropic: Claude Opus 4","maxTokens":32000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":15,"outputPrice":75,"cacheWritesPrice":18.75,"cacheReadsPrice":1.5,"description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-4":{"name":"Anthropic: Claude Sonnet 4","maxTokens":64000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...","thinkingConfig":{"maxBudget":6000}},"anthropic/claude-sonnet-4:1m":{"name":"Anthropic: Claude Sonnet 4","maxTokens":64000,"contextWindow":1000000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3,"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...","thinkingConfig":{"maxBudget":6000},"tiers":[{"contextWindow":200000,"inputPrice":3,"outputPrice":15,"cacheWritesPrice":3.75,"cacheReadsPrice":0.3},{"contextWindow":9007199254740991,"inputPrice":6,"outputPrice":22.5,"cacheWritesPrice":7.5,"cacheReadsPrice":0.6}]},"google/gemma-3n-e4b-it":{"name":"Google: Gemma 3n 4B","maxTokens":0,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.06,"outputPrice":0.12,"description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks..."},"mistralai/mistral-medium-3":{"name":"Mistral: Mistral Medium 3","maxTokens":0,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.39999999999999997,"outputPrice":2,"cacheReadsPrice":0.04,"description":"Mistral Medium 3 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..."},"google/gemini-2.5-pro-preview-05-06":{"name":"Google: Gemini 2.5 Pro Preview 05-06","maxTokens":65535,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":10,"cacheReadsPrice":0.125,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","thinkingConfig":{"maxBudget":6000}},"arcee-ai/virtuoso-large":{"name":"Arcee AI: Virtuoso Large","maxTokens":64000,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.75,"outputPrice":1.2,"description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k..."},"meta-llama/llama-guard-4-12b":{"name":"Meta: Llama Guard 4 12B","maxTokens":16384,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.18,"outputPrice":0.18,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM..."},"qwen/qwen3-30b-a3b":{"name":"Qwen: Qwen3 30B A3B","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.12,"outputPrice":0.5,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-8b":{"name":"Qwen: Qwen3 8B","maxTokens":8192,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.117,"outputPrice":0.45499999999999996,"description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-14b":{"name":"Qwen: Qwen3 14B","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.12,"outputPrice":0.24,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-32b":{"name":"Qwen: Qwen3 32B","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.08,"outputPrice":0.28,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","thinkingConfig":{"maxBudget":6000}},"qwen/qwen3-235b-a22b":{"name":"Qwen: Qwen3 235B A22B","maxTokens":8192,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.45499999999999996,"outputPrice":1.8199999999999998,"description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...","thinkingConfig":{"maxBudget":6000}},"openai/o4-mini-high":{"name":"OpenAI: o4 Mini High","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.1,"outputPrice":4.4,"cacheReadsPrice":0.275,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...","thinkingConfig":{"maxBudget":6000}},"openai/o4-mini-high:batch":{"name":"OpenAI: o4 Mini High (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.55,"outputPrice":2.2,"cacheReadsPrice":0.1375,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...","thinkingConfig":{"maxBudget":6000}},"openai/o3":{"name":"OpenAI: o3","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":8,"cacheReadsPrice":0.5,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","thinkingConfig":{"maxBudget":6000}},"openai/o3:batch":{"name":"OpenAI: o3 (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":4,"cacheReadsPrice":0.25,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","thinkingConfig":{"maxBudget":6000}},"openai/o4-mini":{"name":"OpenAI: o4 Mini","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.1,"outputPrice":4.4,"cacheReadsPrice":0.275,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","thinkingConfig":{"maxBudget":6000}},"openai/o4-mini:batch":{"name":"OpenAI: o4 Mini (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.55,"outputPrice":2.2,"cacheReadsPrice":0.1375,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-4.1":{"name":"OpenAI: GPT-4.1","maxTokens":32768,"contextWindow":1047576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2,"outputPrice":8,"cacheReadsPrice":0.5,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and..."},"openai/gpt-4.1:batch":{"name":"OpenAI: GPT-4.1 (batch)","maxTokens":32768,"contextWindow":1047576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1,"outputPrice":4,"cacheReadsPrice":0.25,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and..."},"openai/gpt-4.1-mini":{"name":"OpenAI: GPT-4.1 Mini","maxTokens":32768,"contextWindow":1047576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.39999999999999997,"outputPrice":1.5999999999999999,"cacheReadsPrice":0.09999999999999999,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard..."},"openai/gpt-4.1-mini:batch":{"name":"OpenAI: GPT-4.1 Mini (batch)","maxTokens":32768,"contextWindow":1047576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":0.7999999999999999,"cacheReadsPrice":0.049999999999999996,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard..."},"openai/gpt-4.1-nano":{"name":"OpenAI: GPT-4.1 Nano","maxTokens":32768,"contextWindow":1047576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.09999999999999999,"outputPrice":0.39999999999999997,"cacheReadsPrice":0.024999999999999998,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million..."},"openai/gpt-4.1-nano:batch":{"name":"OpenAI: GPT-4.1 Nano (batch)","maxTokens":32768,"contextWindow":1047576,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.049999999999999996,"outputPrice":0.19999999999999998,"cacheReadsPrice":0.012499999999999999,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million..."},"meta-llama/llama-4-maverick":{"name":"Meta: Llama 4 Maverick","maxTokens":16384,"contextWindow":1048576,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.19999999999999998,"outputPrice":0.7999999999999999,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward..."},"meta-llama/llama-4-scout":{"name":"Meta: Llama 4 Scout","maxTokens":16384,"contextWindow":1310720,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.3,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input..."},"deepseek/deepseek-chat-v3-0324":{"name":"DeepSeek: DeepSeek V3 0324","maxTokens":163840,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":1,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well..."},"openai/o1-pro":{"name":"OpenAI: o1-pro","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":150,"outputPrice":600,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/o1-pro:batch":{"name":"OpenAI: o1-pro (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":75,"outputPrice":300,"description":"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...","thinkingConfig":{"maxBudget":6000}},"mistralai/mistral-small-3.1-24b-instruct":{"name":"Mistral: Mistral Small 3.1 24B","maxTokens":128000,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.351,"outputPrice":0.5549999999999999,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and..."},"google/gemma-3-4b-it":{"name":"Google: Gemma 3 4B","maxTokens":16384,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.049999999999999996,"outputPrice":0.09999999999999999,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,..."},"google/gemma-3-12b-it":{"name":"Google: Gemma 3 12B","maxTokens":16384,"contextWindow":131072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.049999999999999996,"outputPrice":0.15,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,..."},"cohere/command-a":{"name":"Cohere: Command A","maxTokens":8192,"contextWindow":256000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":2.5,"outputPrice":10,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary..."},"rekaai/reka-flash-3":{"name":"Reka Flash 3","maxTokens":65536,"contextWindow":65536,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","thinkingConfig":{"maxBudget":6000}},"google/gemma-3-27b-it":{"name":"Google: Gemma 3 27B","maxTokens":131072,"contextWindow":262144,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.08,"outputPrice":0.44999999999999996,"cacheReadsPrice":0.04,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,..."},"thedrummer/skyfall-36b-v2":{"name":"TheDrummer: Skyfall 36B V2","maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.55,"outputPrice":0.7999999999999999,"cacheReadsPrice":0.25,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling."},"perplexity/sonar-reasoning-pro":{"name":"Perplexity: Sonar Reasoning Pro","maxTokens":0,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":2,"outputPrice":8,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","thinkingConfig":{"maxBudget":6000}},"perplexity/sonar-pro":{"name":"Perplexity: Sonar Pro","maxTokens":8000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":3,"outputPrice":15,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like..."},"perplexity/sonar-deep-research":{"name":"Perplexity: Sonar Deep Research","maxTokens":0,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":2,"outputPrice":8,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","thinkingConfig":{"maxBudget":6000}},"mistralai/mistral-saba":{"name":"Mistral: Saba","maxTokens":0,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.19999999999999998,"outputPrice":0.6,"cacheReadsPrice":0.02,"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..."},"openai/o3-mini-high":{"name":"OpenAI: o3 Mini High","maxTokens":100000,"contextWindow":200000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.1,"outputPrice":4.4,"cacheReadsPrice":0.55,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...","thinkingConfig":{"maxBudget":6000}},"openai/o3-mini-high:batch":{"name":"OpenAI: o3 Mini High (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.55,"outputPrice":2.2,"cacheReadsPrice":0.275,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...","thinkingConfig":{"maxBudget":6000}},"aion-labs/aion-rp-llama-3.1-8b":{"name":"AionLabs: Aion-RP 1.0 (8B)","maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.7999999999999999,"outputPrice":1.5999999999999999,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model..."},"qwen/qwen2.5-vl-72b-instruct":{"name":"Qwen: Qwen2.5 VL 72B Instruct","maxTokens":128000,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.7999999999999999,"outputPrice":1,"cacheReadsPrice":0.39999999999999997,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images."},"qwen/qwen-plus":{"name":"Qwen: Qwen-Plus","maxTokens":32768,"contextWindow":1000000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.26,"outputPrice":0.78,"cacheReadsPrice":0.052000000000000005,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination."},"openai/o3-mini":{"name":"OpenAI: o3 Mini","maxTokens":100000,"contextWindow":200000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":1.1,"outputPrice":4.4,"cacheReadsPrice":0.55,"description":"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...","thinkingConfig":{"maxBudget":6000}},"openai/o3-mini:batch":{"name":"OpenAI: o3 Mini (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.55,"outputPrice":2.2,"cacheReadsPrice":0.275,"description":"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...","thinkingConfig":{"maxBudget":6000}},"mistralai/mistral-small-24b-instruct-2501":{"name":"Mistral: Mistral Small 3","maxTokens":16384,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.049999999999999996,"outputPrice":0.08,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed..."},"perplexity/sonar":{"name":"Perplexity: Sonar","maxTokens":0,"contextWindow":127072,"supportsImages":true,"supportsPromptCache":false,"inputPrice":1,"outputPrice":1,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features..."},"deepseek/deepseek-r1-distill-llama-70b":{"name":"DeepSeek: R1 Distill Llama 70B","maxTokens":8192,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.7999999999999999,"outputPrice":0.7999999999999999,"description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...","thinkingConfig":{"maxBudget":6000}},"deepseek/deepseek-r1":{"name":"DeepSeek: R1","maxTokens":16000,"contextWindow":64000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.7,"outputPrice":2.5,"description":"DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....","thinkingConfig":{"maxBudget":6000}},"minimax/minimax-01":{"name":"MiniMax: MiniMax-01","maxTokens":1000192,"contextWindow":1000192,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.19999999999999998,"outputPrice":1.1,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context..."},"microsoft/phi-4":{"name":"Microsoft: Phi 4","maxTokens":16384,"contextWindow":16384,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.07,"outputPrice":0.14,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion..."},"deepseek/deepseek-chat":{"name":"DeepSeek: DeepSeek V3","maxTokens":16000,"contextWindow":163840,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0,"outputPrice":1.0287,"cacheWritesPrice":0.14,"cacheReadsPrice":0.014,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations..."},"sao10k/l3.3-euryale-70b":{"name":"Sao10K: Llama 3.3 Euryale 70B","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.65,"outputPrice":0.75,"description":"Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b)."},"openai/o1":{"name":"OpenAI: o1","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":15,"outputPrice":60,"cacheReadsPrice":7.5,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...","thinkingConfig":{"maxBudget":6000}},"openai/o1:batch":{"name":"OpenAI: o1 (batch)","maxTokens":100000,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":7.5,"outputPrice":30,"cacheReadsPrice":3.75,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...","thinkingConfig":{"maxBudget":6000}},"cohere/command-r7b-12-2024":{"name":"Cohere: Command R7B (12-2024)","maxTokens":4000,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.0375,"outputPrice":0.15,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning..."},"meta-llama/llama-3.3-70b-instruct":{"name":"Meta: Llama 3.3 70B Instruct","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.32,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model..."},"amazon/nova-lite-v1":{"name":"Amazon: Nova Lite 1.0","maxTokens":5120,"contextWindow":300000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.06,"outputPrice":0.24,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite..."},"amazon/nova-micro-v1":{"name":"Amazon: Nova Micro 1.0","maxTokens":5120,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.035,"outputPrice":0.14,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length..."},"amazon/nova-pro-v1":{"name":"Amazon: Nova Pro 1.0","maxTokens":5120,"contextWindow":300000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":0.7999999999999999,"outputPrice":3.1999999999999997,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December..."},"openai/gpt-4o-2024-11-20":{"name":"OpenAI: GPT-4o (2024-11-20)","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":10,"cacheReadsPrice":1.25,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded..."},"mistralai/mistral-large-2407":{"name":"Mistral Large 2407","maxTokens":0,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.19999999999999998,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)...."},"qwen/qwen-2.5-coder-32b-instruct":{"name":"Qwen2.5 Coder 32B Instruct","maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.66,"outputPrice":1,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**..."},"thedrummer/unslopnemo-12b":{"name":"TheDrummer: UnslopNemo 12B","maxTokens":32768,"contextWindow":1024000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.39999999999999997,"outputPrice":0.39999999999999997,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios."},"anthracite-org/magnum-v4-72b":{"name":"Magnum v4 72B","maxTokens":4096,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":3,"outputPrice":5,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct)."},"mistralai/ministral-8b":{"name":"Mistral: Ministral 8B","maxTokens":0,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.11,"outputPrice":0.11,"description":"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length..."},"qwen/qwen-2.5-7b-instruct":{"name":"Qwen: Qwen2.5 7B Instruct","maxTokens":32768,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.09999999999999999,"outputPrice":0.19999999999999998,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and..."},"thedrummer/rocinante-12b":{"name":"TheDrummer: Rocinante 12B","maxTokens":65536,"contextWindow":65536,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":0.5,"description":"Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -..."},"meta-llama/llama-3.2-1b-instruct":{"name":"Meta: Llama 3.2 1B Instruct","maxTokens":60000,"contextWindow":60000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.027,"outputPrice":0.201,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate..."},"meta-llama/llama-3.2-3b-instruct":{"name":"Meta: Llama 3.2 3B Instruct","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.049999999999999996,"outputPrice":0.33,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it..."},"qwen/qwen-2.5-72b-instruct":{"name":"Qwen2.5 72B Instruct","maxTokens":16384,"contextWindow":32768,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.36,"outputPrice":0.39999999999999997,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and..."},"cohere/command-r-08-2024":{"name":"Cohere: Command R (08-2024)","maxTokens":4000,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.15,"outputPrice":0.6,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and..."},"cohere/command-r-plus-08-2024":{"name":"Cohere: Command R+ (08-2024)","maxTokens":4000,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":2.5,"outputPrice":10,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint..."},"sao10k/l3.1-euryale-70b":{"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.85,"outputPrice":0.85,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b)."},"nousresearch/hermes-3-llama-3.1-70b":{"name":"Nous: Hermes 3 70B Instruct","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.7,"outputPrice":0.7,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the..."},"nousresearch/hermes-3-llama-3.1-405b":{"name":"Nous: Hermes 3 405B Instruct","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1,"outputPrice":1,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the..."},"sao10k/l3-lunaris-8b":{"name":"Sao10K: Llama 3 8B Lunaris","maxTokens":16384,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.04,"outputPrice":0.049999999999999996,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge...."},"openai/gpt-4o-2024-08-06":{"name":"OpenAI: GPT-4o (2024-08-06)","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":10,"cacheReadsPrice":1.25,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is..."},"meta-llama/llama-3.1-70b-instruct":{"name":"Meta: Llama 3.1 70B Instruct","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.39999999999999997,"outputPrice":0.39999999999999997,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong..."},"meta-llama/llama-3.1-8b-instruct":{"name":"Meta: Llama 3.1 8B Instruct","maxTokens":131072,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":true,"inputPrice":0.049999999999999996,"outputPrice":0.08,"cacheReadsPrice":0.024999999999999998,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to..."},"mistralai/mistral-nemo":{"name":"Mistral: Mistral Nemo","maxTokens":16384,"contextWindow":131072,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.019000000000000003,"outputPrice":0.03,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,..."},"openai/gpt-4o-mini":{"name":"OpenAI: GPT-4o-mini","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":0.6,"cacheReadsPrice":0.075,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable..."},"openai/gpt-4o-mini-2024-07-18":{"name":"OpenAI: GPT-4o-mini (2024-07-18)","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.15,"outputPrice":0.6,"cacheReadsPrice":0.075,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable..."},"openai/gpt-4o-mini:batch":{"name":"OpenAI: GPT-4o-mini (batch)","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.075,"outputPrice":0.3,"cacheReadsPrice":0.0375,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable..."},"google/gemma-2-27b-it":{"name":"Google: Gemma 2 27B","maxTokens":2048,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.65,"outputPrice":0.65,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of..."},"openai/gpt-4o":{"name":"OpenAI: GPT-4o","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":2.5,"outputPrice":10,"cacheReadsPrice":1.25,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as..."},"openai/gpt-4o-2024-05-13":{"name":"OpenAI: GPT-4o (2024-05-13)","maxTokens":4096,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":5,"outputPrice":15,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as..."},"openai/gpt-4o:batch":{"name":"OpenAI: GPT-4o (batch)","maxTokens":16384,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":1.25,"outputPrice":5,"cacheReadsPrice":0.625,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as..."},"mistralai/mixtral-8x22b-instruct":{"name":"Mistral: Mixtral 8x22B Instruct","maxTokens":0,"contextWindow":65536,"supportsImages":false,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.19999999999999998,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,..."},"microsoft/wizardlm-2-8x22b":{"name":"WizardLM-2 8x22B","maxTokens":8000,"contextWindow":65535,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.62,"outputPrice":0.62,"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is..."},"openai/gpt-4-turbo":{"name":"OpenAI: GPT-4 Turbo","maxTokens":4096,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":10,"outputPrice":30,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023."},"openai/gpt-4-turbo:batch":{"name":"OpenAI: GPT-4 Turbo (batch)","maxTokens":4096,"contextWindow":128000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":5,"outputPrice":15,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023."},"anthropic/claude-3-haiku":{"name":"Anthropic: Claude 3 Haiku","maxTokens":4096,"contextWindow":200000,"supportsImages":true,"supportsPromptCache":true,"inputPrice":0.25,"outputPrice":1.25,"cacheReadsPrice":0.03,"description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal"},"mistralai/mistral-large":{"name":"Mistral Large","maxTokens":0,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":true,"inputPrice":2,"outputPrice":6,"cacheReadsPrice":0.19999999999999998,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)...."},"openai/gpt-3.5-turbo-0613":{"name":"OpenAI: GPT-3.5 Turbo (older v0613)","maxTokens":4096,"contextWindow":4095,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1,"outputPrice":2,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021."},"openai/gpt-4-turbo-preview":{"name":"OpenAI: GPT-4 Turbo Preview","maxTokens":4096,"contextWindow":128000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":10,"outputPrice":30,"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while..."},"openrouter/auto":{"name":"Auto Router","maxTokens":0,"contextWindow":2000000,"supportsImages":true,"supportsPromptCache":false,"inputPrice":-1000000,"outputPrice":-1000000,"description":"Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...","thinkingConfig":{"maxBudget":6000}},"openai/gpt-3.5-turbo-instruct":{"name":"OpenAI: GPT-3.5 Turbo Instruct","maxTokens":4096,"contextWindow":4095,"supportsImages":false,"supportsPromptCache":false,"inputPrice":1.5,"outputPrice":2,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021."},"openai/gpt-3.5-turbo-16k":{"name":"OpenAI: GPT-3.5 Turbo 16k","maxTokens":4096,"contextWindow":16385,"supportsImages":false,"supportsPromptCache":false,"inputPrice":3,"outputPrice":4,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up..."},"mancer/weaver":{"name":"Mancer: Weaver (alpha)","maxTokens":6000,"contextWindow":8000,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":0.75,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations."},"undi95/remm-slerp-l2-13b":{"name":"ReMM SLERP 13B","maxTokens":4096,"contextWindow":6144,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.44999999999999996,"outputPrice":0.65,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge"},"gryphe/mythomax-l2-13b":{"name":"MythoMax 13B","maxTokens":4096,"contextWindow":8192,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.06,"outputPrice":0.06,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge"},"openai/gpt-3.5-turbo":{"name":"OpenAI: GPT-3.5 Turbo","maxTokens":4096,"contextWindow":16385,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.5,"outputPrice":1.5,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021."},"openai/gpt-3.5-turbo:batch":{"name":"OpenAI: GPT-3.5 Turbo (batch)","maxTokens":4096,"contextWindow":16385,"supportsImages":false,"supportsPromptCache":false,"inputPrice":0.25,"outputPrice":0.75,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021."},"openai/gpt-4":{"name":"OpenAI: GPT-4","maxTokens":4096,"contextWindow":8191,"supportsImages":false,"supportsPromptCache":false,"inputPrice":30,"outputPrice":60,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning..."}}