llms.txt
+48 −36
https://unorouter.com/llms.txt
− > One key for every AI model. Use it in your code, in Claude Code, or in your favorite AI clients. Smart routing across every major provider.− - UnoRouter is an OpenAI compatible AI gateway: one API key for 200+ models across OpenAI, Anthropic, Google, DeepSeek, Moonshot, Zhipu, Qwen and more.− - [Integrations](https://unorouter.com/en/docs/integrations): Use UnoRouter with your favorite AI tools. Browse 29 setup guides below and pick the one for your client.− - [Janitor.AI Integration Guide](https://unorouter.com/en/docs/integrations/janitor-ai): Connect UnoRouter to Janitor.AI as a custom proxy with the URL format its API Settings panel expects.− - [We aggregated 130+ free AI models from about 50 providers into one endpoint](https://unorouter.com/en/blog/free-models-aggregated): We wired about 50 free providers into UnoRouter: 130+ free models, one OpenAI-compatible endpoint, $0 per token. They carry upstream limits we cannot raise, plus a light 1-per-minute cap we add to keep the shared pools fair. Here is the honest version.− - [We got tired of fake Claude. So we built UnoRouter.](https://unorouter.com/en/blog/launch): Outages every other week. Premium models silently swapped for cheap clones. We snapped, shipped our own router, and made it paranoid about both. Here is the launch story.− - [How we tell real Claude from a fake](https://unorouter.com/en/blog/claude-authenticity): Cheap Claude is often another model wearing Claude's name. Why asking the model proves nothing, why the knowledge cutoff is a guess, and the checks that actually catch a fake.− - [Pricing](https://unorouter.com/en/pricing): Simple pricing for every AI model. Subscribe for better value or pay as you go. Works with your code, with Claude Code, and with SillyTavern, RisuAI, and any OpenAI-compatible AI chat client.− - [Models](https://unorouter.com/en/models): Every AI model in one place. GPT, Claude, Gemini, DeepSeek and more. Use them in your code or in any OpenAI-compatible AI chat client. Same pricing for both.− - [kimi-k3.1-pro](https://unorouter.com/en/models/moonshot/kimi-k3.1-pro): 0.576 in / 2.88 out per 1M tokens− - [or-kimi-k3.1-pro](https://unorouter.com/en/models/moonshot/or-kimi-k3.1-pro): 5.3334 in / 26.667 out per 1M tokens− - [deepseek-v4.1-flash-1017](https://unorouter.com/en/models/deepseek/deepseek-v4.1-flash-1017): 0.08634 in / 0.34536 out per 1M tokens− - [gemini-4-argon](https://unorouter.com/en/models/google/gemini-4-argon): 0.54 in / 2.7 out per 1M tokens− - [step-5-preview](https://unorouter.com/en/models/stepfun/step-5-preview): 2 in / 5.4 out per 1M tokens− - [claude-haiku-5-5](https://unorouter.com/en/models/anthropic/claude-haiku-5-5): 0.036 in / 0.18 out per 1M tokens− - [claude-sonnet-5-5](https://unorouter.com/en/models/anthropic/claude-sonnet-5-5): 0.447 in / 2.235 out per 1M tokens− - [gpt-6-luna](https://unorouter.com/en/models/openai/gpt-6-luna): 0.021 in / 0.10500000000000001 out per 1M tokens− - [claude-opus-5.5](https://unorouter.com/en/models/anthropic/claude-opus-5.5): 0.894 in / 4.47 out per 1M tokens− - [mimo-v2.6-flash](https://unorouter.com/en/models/xiaomi/mimo-v2.6-flash): 0.048006 in / 0.096012 out per 1M tokens− - [mimo-v2.6-pro](https://unorouter.com/en/models/xiaomi/mimo-v2.6-pro): 0.335994 in / 0.671988 out per 1M tokens− - [grok-4.7](https://unorouter.com/en/models/xai/grok-4.7): 0.024 in / 0.07200000000000001 out per 1M tokens− - [intern-s2:free](https://unorouter.com/en/models/internlm/intern-s2:free): free− - [agnes-3.0-flash:free](https://unorouter.com/en/models/agnes-ai/agnes-3.0-flash:free): free− - [deepseek-v4.1-flash](https://unorouter.com/en/models/deepseek/deepseek-v4.1-flash): 0.035994 in / 0.1827163422 out per 1M tokens− - [qwen3.8-max](https://unorouter.com/en/models/alibaba/qwen3.8-max): 0.42 in / 1.26 out per 1M tokens− - [gemini-3.8-flash](https://unorouter.com/en/models/google/gemini-3.8-flash): 0.052500000000000005 in / 0.2625 out per 1M tokens− - [claude-fable-5.1](https://unorouter.com/en/models/anthropic/claude-fable-5.1): 2.235 in / 11.174999999999999 out per 1M tokens− - [qwen3.8-flash](https://unorouter.com/en/models/alibaba/qwen3.8-flash): 0.036 in / 0.1127988 out per 1M tokens− - [glm-5.3-flash](https://unorouter.com/en/models/zhipu/glm-5.3-flash): 0.081 in / 0.2699973 out per 1M tokens− - [glm-5.3-flash-search:free](https://unorouter.com/en/models/zhipu/glm-5.3-flash-search:free): free− - [glm-5.3-flash-think-search:free](https://unorouter.com/en/models/zhipu/glm-5.3-flash-think-search:free): free− - [glm-5.3-flash-thinking:free](https://unorouter.com/en/models/zhipu/glm-5.3-flash-thinking:free): free− - [glm-5.3-flash:free](https://unorouter.com/en/models/zhipu/glm-5.3-flash:free): free− - [muse-spark-1.2-contributor](https://unorouter.com/en/models/meta/muse-spark-1.2-contributor): 0.2 in / 0.4 out per 1M tokens− - [glm-5.3](https://unorouter.com/en/models/zhipu/glm-5.3): 0.052079999999999994 in / 0.16368223199999998 out per 1M tokens− - [or-glm-5.3](https://unorouter.com/en/models/zhipu/or-glm-5.3): 0.8909599999999999 in / 2.8001981839999996 out per 1M tokens+ > One OpenAI compatible key for GPT, Claude, Gemini, DeepSeek and GLM, plus a free proxy for Janitor AI and SillyTavern. Free models, no credit card.+ - UnoRouter is an OpenAI compatible AI gateway: one API key for the models of OpenAI, Anthropic, Google, DeepSeek, Moonshot, Zhipu, Qwen and more, with the live list at https://unorouter.com/models.+ - Janitor AI, SillyTavern, RisuAI and Chub proxy URL: https://api.unorouter.com/v1/chat/completions (paste the full URL, pick a `:free` model, then hard refresh Janitor).+ - [Integrations](https://unorouter.com/en/docs/integrations): Use UnoRouter with your favorite AI tools. Browse 37 setup guides below and pick the one for your client.+ - [Jan Setup Guide](https://unorouter.com/en/docs/integrations/jan): Add UnoRouter to Jan as a custom provider next to your local models.+ - [Msty Studio Setup Guide](https://unorouter.com/en/docs/integrations/msty): Add UnoRouter to Msty Studio as an OpenAI-compatible online provider.+ - [Obsidian Copilot Setup Guide](https://unorouter.com/en/docs/integrations/obsidian-copilot): Add UnoRouter as a custom provider in Copilot for Obsidian and chat with your notes.+ - [n8n Setup Guide](https://unorouter.com/en/docs/integrations/n8n): Point the n8n OpenAI credential at UnoRouter and run any model in AI Agent workflows.+ - [Dify Setup Guide](https://unorouter.com/en/docs/integrations/dify): Add UnoRouter to Dify with the marketplace plugin or as an OpenAI-API-compatible model.+ - [Janitor AI Proxy Guide: Free Proxy Setup](https://unorouter.com/en/docs/integrations/janitor-ai): Connect UnoRouter to Janitor.AI as a free custom proxy, with free models and the exact URL format its API Settings panel expects.+ - [Agnai Setup Guide](https://unorouter.com/en/docs/integrations/agnai): Add UnoRouter to Agnai as an OpenAI Compat provider for character chat.+ - [Cursor Setup Guide](https://unorouter.com/en/docs/integrations/cursor): Point the OpenAI key slot in Cursor at UnoRouter and use its models in Chat and Agent.+ - [GitHub Copilot Setup Guide](https://unorouter.com/en/docs/integrations/github-copilot): Use UnoRouter models in VS Code Copilot Chat and agent mode through a Custom Endpoint.+ - [Free LLM API in 2026: over 150 AI models on one key](https://unorouter.com/en/blog/free-ai-api): Chat, image, embedding and speech models you can call for free through one OpenAI compatible API, what the limits are, and how to start in two minutes.+ - [Best Janitor AI proxy in 2026: free and paid options compared](https://unorouter.com/en/blog/best-janitor-ai-proxy): What a proxy does in Janitor AI, what makes one good for roleplay, and how the free and paid options compare, including where UnoRouter fits and where it does not.+ - [How to get a free DeepSeek API key in 2026](https://unorouter.com/en/blog/free-deepseek-api-key): DeepSeek's own API is paid. Here is how to call DeepSeek models for free through an OpenAI compatible key, what the limits are, and how to use it in your code, Janitor AI or SillyTavern.+ - [UnoRouter free models: free tier and limits explained](https://unorouter.com/en/blog/free-models-aggregated): We wired about 50 free providers into UnoRouter: 130+ free models, one OpenAI-compatible endpoint, $0 per token. They carry upstream limits we cannot raise, plus a light 1-per-minute cap we add to keep the shared pools fair. Here is the honest version.+ - [What is UnoRouter, and why we built it](https://unorouter.com/en/blog/launch): Outages every other week. Premium models silently swapped for cheap clones. We snapped, shipped our own router, and made it paranoid about both. Here is the launch story.+ - [Fake Claude: how to tell if a model is really Claude](https://unorouter.com/en/blog/claude-authenticity): Cheap Claude is often another model wearing Claude's name. Why asking the model proves nothing, why the knowledge cutoff is a guess, and the checks that actually catch a fake.+ - [Pricing](https://unorouter.com/en/pricing): Simple pricing for every AI model: free models, pay as you go or a subscription for better value. Works in your code, Claude Code, SillyTavern and RisuAI.+ - [Models](https://unorouter.com/en/models): Every AI model in one place: GPT, Claude, Gemini, DeepSeek and more. Use them in your code or any OpenAI-compatible chat client, same pricing for both.+ - [ling-3.2-flash:free](https://unorouter.com/en/models/inclusionai/ling-3.2-flash:free): free+ - [gemini-4-hydrogen](https://unorouter.com/en/models/google/gemini-4-hydrogen): 0.6000000000000001 in / 3.0000000000000004 out per 1M tokens+ - [gemini-4-carbon](https://unorouter.com/en/models/google/gemini-4-carbon): 0.6214 in / 3.1069999999999998 out per 1M tokens+ - [claude-fable-5.2](https://unorouter.com/en/models/anthropic/claude-fable-5.2): 2.88 in / 14.399999999999999 out per 1M tokens+ - [hy4](https://unorouter.com/en/models/tencent/hy4): 0.1208049 in / 0.36226973412 out per 1M tokens+ - [kimi-k3.1-pro](https://unorouter.com/en/models/moonshot/kimi-k3.1-pro): 0.216 in / 1.08 out per 1M tokens+ - [or-kimi-k3.1-pro](https://unorouter.com/en/models/moonshot/or-kimi-k3.1-pro): 3.6 in / 18 out per 1M tokens+ - [flint-v1.0:free](https://unorouter.com/en/models/recursive/flint-v1.0:free): free+ - [minimax-m3.1-flash:free](https://unorouter.com/en/models/minimax/minimax-m3.1-flash:free): free+ - [deepseek-v4.1-flash-1017](https://unorouter.com/en/models/deepseek/deepseek-v4.1-flash-1017): 0.04463999999999999 in / 0.17855999999999997 out per 1M tokens, free tier as deepseek-v4.1-flash-1017:free+ - [nemotron-3-5-super-vl:free](https://unorouter.com/en/models/nvidia/nemotron-3-5-super-vl:free): free+ - [gemini-4-argon](https://unorouter.com/en/models/google/gemini-4-argon): 0.4726 in / 2.363 out per 1M tokens+ - [step-5-preview](https://unorouter.com/en/models/stepfun/step-5-preview): 2 in / 5.4 out per 1M tokens, free tier as step-5-preview:free+ - [claude-haiku-5-5](https://unorouter.com/en/models/anthropic/claude-haiku-5-5): 0.0432 in / 0.21600000000000003 out per 1M tokens+ - [claude-sonnet-5-5](https://unorouter.com/en/models/anthropic/claude-sonnet-5-5): 0.5 in / 2.5 out per 1M tokens+ - [solar-mini4:free](https://unorouter.com/en/models/upstage/solar-mini4:free): free+ - [gpt-6-luna](https://unorouter.com/en/models/openai/gpt-6-luna): 0.021 in / 0.10500000000000001 out per 1M tokens, free tier as gpt-6-luna:free+ - [claude-opus-5.5](https://unorouter.com/en/models/anthropic/claude-opus-5.5): 1.5272 in / 7.635999999999999 out per 1M tokens+ - [mimo-v2.6-flash](https://unorouter.com/en/models/xiaomi/mimo-v2.6-flash): 0.033600000000000005 in / 0.06720000000000001 out per 1M tokens, free tier as mimo-v2.6-flash:free
Showing the first 40 of each.