# UnoRouter

> 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.

## Facts
- UnoRouter is an OpenAI compatible AI gateway: one API key for 200+ models across OpenAI, Anthropic, Google, DeepSeek, Moonshot, Zhipu, Qwen and more.
- Most models have a genuine free tier (`:free` suffix), about 1 request per minute per model per user; the cap returns HTTP 429 with a Retry-After header.
- Endpoints: /v1/chat/completions, /v1/responses, /v1/embeddings, Anthropic native /v1/messages, Gemini native /v1beta. Base URL https://api.unorouter.com/v1.
- Paid models bill pay as you go per token, credits never expire, top up from $1.
- The entire stack is open source under OSI licenses: https://github.com/unorouter
- MCP server: com.unorouter/mcp in the official MCP registry, npm package unorouter-mcp, hosted endpoint https://mcp.unorouter.com/mcp

## Docs
- [Integrations](https://unorouter.com/en/docs/integrations): Use UnoRouter with your favorite AI tools. Browse 28 setup guides below and pick the one for your client.
- [Chat Guide](https://unorouter.com/en/docs/chat): Everything the built-in roleplay chat can do, from your first message to advanced scripting.
- [Platform Guide](https://unorouter.com/en/docs/platform): Everything about the UnoRouter API itself: getting a key, model pricing, rate limits, error codes and billing.
- [LibreChat Integration Guide](https://unorouter.com/en/docs/integrations/librechat): Connect UnoRouter to LibreChat through a custom OpenAI-compatible endpoint.
- [Open WebUI Integration Guide](https://unorouter.com/en/docs/integrations/open-webui): Connect UnoRouter to Open WebUI as a native OpenAI connection.
- [LobeChat Integration Guide](https://unorouter.com/en/docs/integrations/lobechat): Connect UnoRouter to LobeChat through a custom provider or Docker env vars.
- [AnythingLLM Integration Guide](https://unorouter.com/en/docs/integrations/anythingllm): Connect UnoRouter to AnythingLLM as a Generic OpenAI provider.
- [Cherry Studio Integration Guide](https://unorouter.com/en/docs/integrations/cherry-studio): Connect UnoRouter to Cherry Studio as an OpenAI provider.
- [TypingMind Integration Guide](https://unorouter.com/en/docs/integrations/typingmind): Connect UnoRouter to TypingMind as a custom OpenAI-compatible model.
- [BoltAI Integration Guide](https://unorouter.com/en/docs/integrations/boltai): Connect UnoRouter to BoltAI as a custom OpenAI-compatible server.
- [Page Assist Integration Guide](https://unorouter.com/en/docs/integrations/page-assist): Connect UnoRouter to Page Assist as a custom OpenAI-compatible API.
- [Chatbox Integration Guide](https://unorouter.com/en/docs/integrations/chatbox): Connect UnoRouter to Chatbox using OpenAI API Compatible mode.
- [Big-AGI Integration Guide](https://unorouter.com/en/docs/integrations/big-agi): Connect UnoRouter to Big-AGI as a custom OpenAI source.
- [SillyTavern Integration Guide](https://unorouter.com/en/docs/integrations/sillytavern): Connect UnoRouter to SillyTavern through the Custom OpenAI-compatible chat completion source.
- [Janitor.AI Integration Guide](https://unorouter.com/en/docs/integrations/janitor-ai): Connect UnoRouter to Janitor.AI as a custom proxy with the exact URL format Janitor's API Settings panel expects.
- [RisuAI Integration Guide](https://unorouter.com/en/docs/integrations/risuai): Connect UnoRouter to RisuAI through the Custom Models option in Advanced Settings.
- [Chub / Venus Integration Guide](https://unorouter.com/en/docs/integrations/chub): Connect UnoRouter to Chub.ai (Venus) through the Secrets panel's Reverse proxy option.
- [OpenCode Setup Guide](https://unorouter.com/en/docs/integrations/opencode): Add UnoRouter as a custom provider in OpenCode and pick any model as the active coding agent.
- [Kilo Code Setup Guide](https://unorouter.com/en/docs/integrations/kilo-code): Connect a custom UnoRouter provider directly in the Kilo Code VSCode sidebar without leaving the editor.
- [Zed IDE Setup Guide](https://unorouter.com/en/docs/integrations/zed): Add UnoRouter as a custom OpenAI-compatible provider in Zed and the built-in agent handles the rest.
- [Cline Setup Guide](https://unorouter.com/en/docs/integrations/cline): Add UnoRouter as an OpenAI Compatible provider in Cline and run a full agent loop inside VSCode.
- [Roo Code Setup Guide](https://unorouter.com/en/docs/integrations/roo-code): Add UnoRouter as the OpenAI Compatible provider and Roo Code’s agent roles share the same base URL.
- [Continue.dev Setup Guide](https://unorouter.com/en/docs/integrations/continue-dev): Drop a UnoRouter model entry into Continue’s config.yaml and it hot-reloads across VSCode and JetBrains.
- [Aider Setup Guide](https://unorouter.com/en/docs/integrations/aider): Aider is LiteLLM-backed, so UnoRouter’s OpenAI-compatible base URL works with two env vars.
- [CC Switch Integration Guide](https://unorouter.com/en/docs/integrations/cc-switch): All-in-One AI CLI Management Tool for unified management of Claude Code, Codex, and Gemini CLI provider configurations.
- [Claude Code Integration](https://unorouter.com/en/docs/integrations/claude-code): Use UnoRouter with Claude Code, Cursor, VS Code extensions, and any Anthropic-compatible client. Point your API to UnoRouter and access all models.
- [OpenAI Codex CLI Setup Guide](https://unorouter.com/en/docs/integrations/codex): Step-by-step guide to install and configure Codex CLI with UnoRouter on Windows, macOS, and Linux.
- [Gemini CLI Integration](https://unorouter.com/en/docs/integrations/gemini-cli): Use UnoRouter with the Gemini CLI and any Google GenAI-compatible client. Access Gemini models alongside Claude and GPT.
- [OpenClaw Integration](https://unorouter.com/en/docs/integrations/openclaw): Use UnoRouter as a model provider for your OpenClaw agent. Configure once and access every model through OpenClaw's gateway.
- [Hermes Agent Integration](https://unorouter.com/en/docs/integrations/hermes): Use UnoRouter as the model provider for Hermes Agent. Point one OpenAI-compatible endpoint at UnoRouter and reach every model.
- [MCP Server Setup Guide](https://unorouter.com/en/docs/integrations/mcp): Give any MCP client live access to UnoRouter: search the model catalog, check pricing, and chat with any model through the unorouter-mcp server.
- [Getting Started](https://unorouter.com/en/docs/chat/getting-started): Your first chat: loadouts, greetings, swipes, and branches.
- [Characters](https://unorouter.com/en/docs/chat/characters): Create, import, and export character cards.
- [Personas](https://unorouter.com/en/docs/chat/personas): The identity you play as in every chat.
- [Lorebooks](https://unorouter.com/en/docs/chat/lorebooks): World knowledge that appears in the prompt exactly when it is relevant.
- [Cards](https://unorouter.com/en/docs/chat/cards): Bundle persona, characters, and lorebooks into one loadout.
- [Presets](https://unorouter.com/en/docs/chat/presets): The request recipe: sampling, behavior toggles, and core prompts.
- [Prompt Template](https://unorouter.com/en/docs/chat/prompt-template): Reorder what the model sees, block by block.
- [Group Chats](https://unorouter.com/en/docs/chat/group-chats): Several characters, one scene.
- [Macros (CBS)](https://unorouter.com/en/docs/chat/macros): Curly-brace scripting inside any prompt text.
- [Regex Scripts](https://unorouter.com/en/docs/chat/regex-scripts): Automatic find-and-replace at four points in the pipeline.
- [Triggers & Lua](https://unorouter.com/en/docs/chat/triggers-and-lua): Automation that runs around every message.
- [Memory & Context](https://unorouter.com/en/docs/chat/memory-and-context): Keeping long stories coherent past the context window.
- [Images](https://unorouter.com/en/docs/chat/images): Illustrations generated from the scene, right in the chat.
- [Custom Providers](https://unorouter.com/en/docs/chat/custom-providers): Chat through your own endpoint and key.
- [Your Data](https://unorouter.com/en/docs/chat/data): Everything is local; take it anywhere, inspect anything.
- [Quickstart](https://unorouter.com/en/docs/platform/quickstart): From zero to a working API call in about five minutes.
- [Models & Pricing](https://unorouter.com/en/docs/platform/models-and-pricing): What the :free suffix means, how usage is priced and why a model sometimes disappears.
- [Notifications](https://unorouter.com/en/docs/platform/notifications): Get alerted when model prices move, providers go down or come back, and new free models appear.
- [Group Pinning](https://unorouter.com/en/docs/platform/group-pinning): Lock a model to specific provider groups and their rates instead of automatic cheapest routing.
- [Errors & Rate Limits](https://unorouter.com/en/docs/platform/errors-and-rate-limits): What each status code means and what to do about it.
- [Account & Billing](https://unorouter.com/en/docs/platform/account-and-billing): Where your money goes, where free credit comes from, and how to audit every request.
- [Discord Rewards](https://unorouter.com/en/docs/platform/discord-rewards): Every way to earn free balance in the Discord server, how payouts work, and the rules that keep them fair.

## Blog
- [The best AI gateway for SillyTavern in 2026](https://unorouter.com/en/blog/best-ai-gateway-for-sillytavern): SillyTavern needs an OpenAI-compatible endpoint and a key. Here is what actually matters when you pick a gateway, and how to connect one in under a minute.
- [The best OpenRouter alternatives in 2026](https://unorouter.com/en/blog/best-openrouter-alternatives-2026): OpenRouter is not the only way to reach many models from one key. Here are the alternatives worth knowing in 2026, what each is good for, and how to pick.
- [UnoRouter: the open source OpenRouter alternative](https://unorouter.com/en/blog/open-source-openrouter-alternative): OpenRouter is closed source. UnoRouter does the same one key, 200+ model job with the entire stack public under OSI licenses, self hostable, and with a hosted free tier to test on.
- [What is an LLM gateway?](https://unorouter.com/en/blog/what-is-an-llm-gateway): An LLM gateway is one endpoint and key that routes requests to many model providers. Here is what it does, why it helps, and who actually needs one.
- [How to connect any LLM to SillyTavern](https://unorouter.com/en/blog/how-to-connect-any-llm-to-sillytavern): SillyTavern can talk to almost any model through one OpenAI-compatible endpoint. Here is the exact setup, how to switch models, and how to fix common errors.
- [One API key for Claude Code and character chat](https://unorouter.com/en/blog/one-api-key-for-claude-code-and-roleplay): Coding agents and character chat clients both speak OpenAI-compatible APIs. Here is how one key powers Claude Code and your character chats from a single balance.
- [UnoRouter vs nano-gpt: chat marketplace or one key for both](https://unorouter.com/en/blog/unorouter-vs-nano-gpt): nano-gpt offers a huge model catalog behind a chat UI. UnoRouter gives you the same pay-as-you-go access plus a real developer API and a built-in character client, under one clean key.
- [UnoRouter vs Portkey: AI gateway or full LLMOps platform](https://unorouter.com/en/blog/unorouter-vs-portkey): Portkey is an enterprise LLMOps platform with observability, guardrails, and governance. UnoRouter is a simpler hosted gateway with a built-in chat client. The choice is how much platform you actually need.
- [UnoRouter vs MegaLLM: same coder gateway, plus a chat client](https://unorouter.com/en/blog/unorouter-vs-megallm): MegaLLM is a popular frontier-model gateway for coding agents. UnoRouter does the same job and adds a built-in chat and character client. The difference is whether you only ship code or also want a place to chat.
- [UnoRouter vs RisuAI: we ported the character chat engine into a hosted 2-in-1](https://unorouter.com/en/blog/unorouter-vs-risuai): RisuAI is the power-user character chat frontend. UnoRouter ported its engine (lorebooks, CBS macros, triggers, regex, card import) into a hosted product where the same key also drives coding agents. Not a rival, a 2-in-1.
- [UnoRouter vs LiteLLM: hosted gateway or self-hosted proxy](https://unorouter.com/en/blog/unorouter-vs-litellm): LiteLLM is the most popular self-hosted LLM proxy. UnoRouter is a hosted gateway with a built-in chat client. The real choice is whether you want to run the infrastructure yourself.
- [Where to find UnoRouter: our directory listings](https://unorouter.com/en/blog/featured-on): UnoRouter is listed across the AI tool and startup directories. Here is where you can find us, verify the listings, and read independent takes.
- [UnoRouter vs OpenRouter: an honest comparison](https://unorouter.com/en/blog/unorouter-vs-openrouter): UnoRouter and OpenRouter both put many models behind one OpenAI-compatible key. The difference is what sits on top: a headless API, or an API plus a built-in chat and character client. Here is the honest version.
- [We aggregated 190+ free AI models into one endpoint](https://unorouter.com/en/blog/free-models-aggregated): We wired 18 free providers into UnoRouter: 190+ free model rows, 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.
- [We pointed Cloudflare's agent scanner at our site. It came back 100/100.](https://unorouter.com/en/blog/agent-ready): Cloudflare just shipped a scanner that grades how ready your site is for AI agents. We hit a perfect 100/100 and the top Level 5 rating. Here is exactly what it checks and why most sites fail.
- [Your cheap Claude is probably a fake. We caught 183 of them.](https://unorouter.com/en/blog/claude-authenticity): We probed 8 popular Claude resellers for 17 days. 183 of their channels were not Claude at all. Most were Kiro Cascade or Codeium wearing a Claude name tag. Names, numbers, and the script we used so you can test your own provider.
- [Which image models actually take 6 reference inputs? We ran the benchmark.](https://unorouter.com/en/blog/six-input-image-models): Many image models advertise multi-reference editing, but availability across resellers varies wildly. We sent a fixed 6-image scene-composition prompt to every image channel in our catalog. 332 channel runs, 136 unique models, 54 with at least one verified passing provider.
- [Join the UnoRouter Discord, get free balance](https://unorouter.com/en/blog/discord-community): Link your account for $1, boost the server for $1 every month, hunt bugs for up to $50. We just opened the UnoRouter Discord.
- [UnoRouter vs Janitor.AI: the backend, plus a chat of your own](https://unorouter.com/en/blog/unorouter-vs-janitorai): Janitor.AI is a character chat front-end that needs a backend. UnoRouter is that backend on one key, and it has its own character chat too, so you can stay in one place.
- [UnoRouter vs Character.AI: open models and a real key](https://unorouter.com/en/blog/unorouter-vs-character-ai): Character.AI is a closed, filtered chat with no API and no model choice. UnoRouter is open: 200+ models, a real OpenAI-compatible key, your data local, and the same key codes too.
- [UnoRouter vs SillyTavern: same depth, hosted, on one key](https://unorouter.com/en/blog/unorouter-vs-sillytavern): SillyTavern is the power-user character front-end you self-host and feed your own keys. UnoRouter has the same depth hosted, where the key is the account and also runs coding agents.
- [UnoRouter vs Chub / Venus: the card depth, plus code on one key](https://unorouter.com/en/blog/unorouter-vs-chub): Chub (Venus) is a card library and chat with tiered models or BYOK. UnoRouter has the cards and lorebook depth plus 200+ models on one key that also runs coding agents.
- [UnoRouter vs Marinara: we ported the preset engine into a 2-in-1](https://unorouter.com/en/blog/unorouter-vs-marinara): Marinara Engine is a standalone, self-hosted role-play, visual-novel, and game app built around 22 built-in agents. UnoRouter carries the same agent-pipeline idea in a hosted product where one key also runs coding agents.
- [UnoRouter vs Lumiverse: the memory ideas, hosted, plus code](https://unorouter.com/en/blog/unorouter-vs-lumiverse): Lumiverse is a source-available role-play suite whose Memory Cortex (entity graph, tiered consolidations, cross-chat vaults) is the deepest RP memory around. UnoRouter carries the same ideas in a hosted 2-in-1 where one key also runs coding agents, and is free to use commercially.
- [UnoRouter vs LibreChat: multi-model chat, hosted, plus character chat](https://unorouter.com/en/blog/unorouter-vs-librechat): LibreChat is a self-hosted, MIT, BYOK ChatGPT clone. UnoRouter is hosted multi-model chat where the key is the account, plus a real character client, on one key that also codes.
- [UnoRouter vs Open WebUI: 200+ hosted models, no Ollama, plus character chat](https://unorouter.com/en/blog/unorouter-vs-open-webui): Open WebUI is a self-hosted, Ollama-first chat UI you run and key up. UnoRouter is 200+ hosted models on one key, no infra, plus a real character client, and the key codes too.
- [UnoRouter vs Agnai: the same RP depth, hosted, on one key](https://unorouter.com/en/blog/unorouter-vs-agnai): Agnai is an open-source RP frontend whose standout is true multiplayer: several humans and several bots in one chat. UnoRouter has single-user RP depth hosted, where the key is the account and also runs coding agents.
- [UnoRouter vs SpicyChat: the easy path, plus depth, models, and code](https://unorouter.com/en/blog/unorouter-vs-spicychat): SpicyChat is a zero-setup RP site whose memory and context are gated behind paid tiers. UnoRouter keeps the easy start but adds 200+ models you choose, deep lorebooks, and a key that also runs coding agents.

## Product
- [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.
- [Chat](https://unorouter.com/en/chat): Chat with any AI model: GPT, Claude, Gemini, DeepSeek and more in one interface, or bring your own OpenAI-compatible endpoint and key.

## Models
- [absolutereality:free](https://unorouter.com/en/models/ai-horde/absolutereality:free): free
- [agnes-1.5-flash:free](https://unorouter.com/en/models/agnes-ai/agnes-1.5-flash:free): free
- [agnes-image-2.0-flash:free](https://unorouter.com/en/models/agnes-ai/agnes-image-2.0-flash:free): free
- [agnes-image-2.1-flash:free](https://unorouter.com/en/models/agnes-ai/agnes-image-2.1-flash:free): free
- [aion-2.0:free](https://unorouter.com/en/models/aion-labs/aion-2.0:free): free
- [aion-3.0:free](https://unorouter.com/en/models/aion-labs/aion-3.0:free): free
- [albedobase-xl-31:free](https://unorouter.com/en/models/ai-horde/albedobase-xl-31:free): free
- [albedobase-xl-sdxl:free](https://unorouter.com/en/models/ai-horde/albedobase-xl-sdxl:free): free
- [allam-2-7b:free](https://unorouter.com/en/models/sdaia/allam-2-7b:free): free
- [amponyxl:free](https://unorouter.com/en/models/ai-horde/amponyxl:free): free
- [anything-v5:free](https://unorouter.com/en/models/ai-horde/anything-v5:free): free
- [bge-base-en-v1.5:free](https://unorouter.com/en/models/baai/bge-base-en-v1.5:free): free
- [bge-large-en-v1.5:free](https://unorouter.com/en/models/baai/bge-large-en-v1.5:free): free
- [bge-multilingual-gemma2:free](https://unorouter.com/en/models/baai/bge-multilingual-gemma2:free): free
- [bge-small-en-v1.5:free](https://unorouter.com/en/models/baai/bge-small-en-v1.5:free): free
- [bielik-11b-v3.0-instruct:free](https://unorouter.com/en/models/speakleash/bielik-11b-v3.0-instruct:free): free
- [codestral-latest:free](https://unorouter.com/en/models/mistral/codestral-latest:free): free
- [codestral:free](https://unorouter.com/en/models/mistral/codestral:free): free
- [cohere-command-a:free](https://unorouter.com/en/models/cohere/cohere-command-a:free): free
- [command-r-plus:free](https://unorouter.com/en/models/cohere/command-r-plus:free): free
- [compound-mini:free](https://unorouter.com/en/models/groq/compound-mini:free): free
- [compound:free](https://unorouter.com/en/models/groq/compound:free): free
- [cyberrealistic-pony:free](https://unorouter.com/en/models/ai-horde/cyberrealistic-pony:free): free
- [deepseek-r1-distill-llama-70b:free](https://unorouter.com/en/models/deepseek/deepseek-r1-distill-llama-70b:free): free
- [deliberate:free](https://unorouter.com/en/models/ai-horde/deliberate:free): free
- [devious-uncensored:free](https://unorouter.com/en/models/navyai/devious-uncensored:free): free
- [diffusiongemma-26b-a4b-it:free](https://unorouter.com/en/models/google/diffusiongemma-26b-a4b-it:free): free
- [dracarys-llama-3.1-70b-instruct:free](https://unorouter.com/en/models/meta/dracarys-llama-3.1-70b-instruct:free): free
- [dreamshaper:free](https://unorouter.com/en/models/lykon/dreamshaper:free): free
- [embeddinggemma-300m:free](https://unorouter.com/en/models/google/embeddinggemma-300m:free): free
- [flat-2d-animerge:free](https://unorouter.com/en/models/ai-horde/flat-2d-animerge:free): free
- [fustercluck:free](https://unorouter.com/en/models/ai-horde/fustercluck:free): free
- [gemini-embedding-001:free](https://unorouter.com/en/models/google/gemini-embedding-001:free): free
- [gemini-embedding-2:free](https://unorouter.com/en/models/google/gemini-embedding-2:free): free
- [gemini-robotics-er-1.6-preview:free](https://unorouter.com/en/models/google/gemini-robotics-er-1.6-preview:free): free
- [gemma-2-2b-it:free](https://unorouter.com/en/models/google/gemma-2-2b-it:free): free
- [gemma-4-31b-it:free](https://unorouter.com/en/models/google/gemma-4-31b-it:free): free
- [gpt-4.1-mini:free](https://unorouter.com/en/models/openai/gpt-4.1-mini:free): free
- [gpt-4.1-nano:free](https://unorouter.com/en/models/openai/gpt-4.1-nano:free): free
- [gpt-4.1:free](https://unorouter.com/en/models/openai/gpt-4.1:free): free
- [gpt-4o-mini:free](https://unorouter.com/en/models/openai/gpt-4o-mini:free): free
- [gpt-4o:free](https://unorouter.com/en/models/openai/gpt-4o:free): free
- [gpt-5-chat-latest:free](https://unorouter.com/en/models/openai/gpt-5-chat-latest:free): free
- [gpt-5.1-codex:free](https://unorouter.com/en/models/openai/gpt-5.1-codex:free): free
- [gpt-5.1:free](https://unorouter.com/en/models/openai/gpt-5.1:free): free
- [gpt-5.2-codex:free](https://unorouter.com/en/models/openai/gpt-5.2-codex:free): free
- [gpt-laborratse:free](https://unorouter.com/en/models/openai/gpt-laborratse:free): free
- [gpt-oss-120b:free](https://unorouter.com/en/models/openai/gpt-oss-120b:free): free
- [gpt-oss-20b:free](https://unorouter.com/en/models/openai/gpt-oss-20b:free): free
- [gpt-oss-safeguard-20b:free](https://unorouter.com/en/models/openai/gpt-oss-safeguard-20b:free): free

## Legal
- [Privacy Policy](https://unorouter.com/en/privacy)
- [Terms of Service](https://unorouter.com/en/terms)

## Optional
- [RSS](https://unorouter.com/en/blog/feed.xml)
- [Sitemap](https://unorouter.com/sitemap.xml)