# Routerah

> 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
- Routerah 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.routerah.app/v1.
- Paid models bill pay as you go per token, pay as you go credit never expires, top up from $1. Subscription credit resets weekly and unused credit does not carry over.
- The entire stack is open source under OSI licenses: https://github.com/routerah
- MCP server: com.routerah/mcp in the official MCP registry, npm package routerah-mcp, hosted endpoint https://mcp.routerah.app/mcp

## Docs
- [Integrations](https://routerah.app/en/docs/integrations): Use Routerah with the tools you already have. 29 setup guides — pick your client below.
- [Chat Guide](https://routerah.app/en/docs/chat): Everything the built-in roleplay chat can do.
- [Platform Guide](https://routerah.app/en/docs/platform): Keys, pricing, rate limits, errors and billing for the Routerah API.
- [LibreChat Integration Guide](https://routerah.app/en/docs/integrations/librechat): Connect Routerah to LibreChat through a custom OpenAI-compatible endpoint.
- [Open WebUI Integration Guide](https://routerah.app/en/docs/integrations/open-webui): Connect Routerah to Open WebUI as a native OpenAI connection.
- [LobeChat Integration Guide](https://routerah.app/en/docs/integrations/lobechat): Connect Routerah to LobeChat through a custom provider or Docker env vars.
- [AnythingLLM Integration Guide](https://routerah.app/en/docs/integrations/anythingllm): Connect Routerah to AnythingLLM as a Generic OpenAI provider.
- [Cherry Studio Integration Guide](https://routerah.app/en/docs/integrations/cherry-studio): Connect Routerah to Cherry Studio as an OpenAI provider.
- [TypingMind Integration Guide](https://routerah.app/en/docs/integrations/typingmind): Connect Routerah to TypingMind as a custom OpenAI-compatible model.
- [BoltAI Integration Guide](https://routerah.app/en/docs/integrations/boltai): Connect Routerah to BoltAI as a custom OpenAI-compatible server.
- [Page Assist Integration Guide](https://routerah.app/en/docs/integrations/page-assist): Connect Routerah to Page Assist as a custom OpenAI-compatible API.
- [Chatbox Integration Guide](https://routerah.app/en/docs/integrations/chatbox): Connect Routerah to Chatbox using OpenAI API Compatible mode.
- [Big-AGI Integration Guide](https://routerah.app/en/docs/integrations/big-agi): Connect Routerah to Big-AGI as a custom OpenAI source.
- [SillyTavern Integration Guide](https://routerah.app/en/docs/integrations/sillytavern): Connect Routerah to SillyTavern through the Custom OpenAI-compatible chat completion source.
- [Janitor.AI Integration Guide](https://routerah.app/en/docs/integrations/janitor-ai): Connect Routerah to Janitor.AI as a custom proxy with the URL format its API Settings panel expects.
- [RisuAI Integration Guide](https://routerah.app/en/docs/integrations/risuai): Connect Routerah to RisuAI through the Custom Models option in Advanced Settings.
- [Chub / Venus Integration Guide](https://routerah.app/en/docs/integrations/chub): Connect Routerah to Chub.ai (Venus) through the Secrets panel's Reverse proxy option.
- [Nevika Integration Guide](https://routerah.app/en/docs/integrations/nevika): Connect Routerah to Nevika through its Custom Proxy settings.
- [OpenCode Setup Guide](https://routerah.app/en/docs/integrations/opencode): Add Routerah as a custom provider in OpenCode and pick any model as the active agent.
- [Kilo Code Setup Guide](https://routerah.app/en/docs/integrations/kilo-code): Add a custom Routerah provider in the Kilo Code VSCode sidebar.
- [Zed IDE Setup Guide](https://routerah.app/en/docs/integrations/zed): Add Routerah as a custom OpenAI-compatible provider in Zed.
- [Cline Setup Guide](https://routerah.app/en/docs/integrations/cline): Add Routerah as an OpenAI Compatible provider in Cline and run a full agent loop in VSCode.
- [Roo Code Setup Guide](https://routerah.app/en/docs/integrations/roo-code): Add Routerah as the OpenAI Compatible provider and Roo Code's agent roles share one base URL.
- [Continue.dev Setup Guide](https://routerah.app/en/docs/integrations/continue-dev): Add a Routerah model entry to Continue's config.yaml. It hot-reloads across VSCode and JetBrains.
- [Aider Setup Guide](https://routerah.app/en/docs/integrations/aider): Aider is LiteLLM-backed, so Routerah's OpenAI-compatible base URL works with two env vars.
- [CC Switch Integration Guide](https://routerah.app/en/docs/integrations/cc-switch): Manage Claude Code, Codex, and Gemini CLI provider configs in one place.
- [Claude Code Integration](https://routerah.app/en/docs/integrations/claude-code): Point Claude Code, Cursor, VS Code extensions, or any Anthropic-compatible client at Routerah and reach every model.
- [OpenAI Codex CLI Setup Guide](https://routerah.app/en/docs/integrations/codex): Install and configure Codex CLI with Routerah on Windows, macOS, and Linux.
- [Gemini CLI Integration](https://routerah.app/en/docs/integrations/gemini-cli): Use Routerah with the Gemini CLI and any Google GenAI-compatible client.
- [OpenClaw Integration](https://routerah.app/en/docs/integrations/openclaw): Use Routerah as the model provider for your OpenClaw agent.
- [Hermes Agent Integration](https://routerah.app/en/docs/integrations/hermes): Use Routerah as the model provider for Hermes Agent. One OpenAI-compatible endpoint, every model.
- [MCP Server Setup Guide](https://routerah.app/en/docs/integrations/mcp): Give any MCP client live access to Routerah: search the model catalog, check pricing, and chat with any model.
- [Getting Started](https://routerah.app/en/docs/chat/getting-started): Loadouts, greetings, swipes, and branches.
- [Theme customizer](https://routerah.app/en/docs/chat/theme): Colours, fonts and a wallpaper, for the whole app or just for chat.
- [Characters](https://routerah.app/en/docs/chat/characters): Create, import, and export character cards.
- [Personas](https://routerah.app/en/docs/chat/personas): The identity you play as.
- [Lorebooks](https://routerah.app/en/docs/chat/lorebooks): World knowledge injected when it is relevant.
- [Cards](https://routerah.app/en/docs/chat/cards): Bundle persona, characters, and lorebooks into one loadout.
- [Presets](https://routerah.app/en/docs/chat/presets): Sampling, behavior toggles, and core prompts.
- [Prompt Template](https://routerah.app/en/docs/chat/prompt-template): Reorder what the model sees, block by block.
- [Group Chats](https://routerah.app/en/docs/chat/group-chats): Several characters, one scene.
- [Multiplayer Rooms](https://routerah.app/en/docs/chat/multiplayer): One scene, several people at the keyboard.
- [Macros (CBS)](https://routerah.app/en/docs/chat/macros): Curly-brace scripting inside any prompt text.
- [Regex Scripts](https://routerah.app/en/docs/chat/regex-scripts): Automatic find-and-replace at four points in the pipeline.
- [Triggers & Lua](https://routerah.app/en/docs/chat/triggers-and-lua): Automation that runs around every message.
- [Plugins](https://routerah.app/en/docs/chat/plugins): Your own JavaScript, running around every message.
- [Memory & Context](https://routerah.app/en/docs/chat/memory-and-context): Keeping long stories coherent past the context window.
- [Images](https://routerah.app/en/docs/chat/images): Illustrations generated from the scene, in the chat.
- [Custom Providers](https://routerah.app/en/docs/chat/custom-providers): Chat through your own endpoint and key.
- [Your Data](https://routerah.app/en/docs/chat/data): Everything is local. Take it anywhere, inspect anything.
- [Import from JanitorAI](https://routerah.app/en/docs/chat/janitorai-import): Every chat, character, and lorebook in one file. Desktop and Android.
- [Backup & Restore](https://routerah.app/en/docs/chat/backups): One file holds everything, images included.
- [Quickstart](https://routerah.app/en/docs/platform/quickstart): A working API call in five minutes.
- [Models & Pricing](https://routerah.app/en/docs/platform/models-and-pricing): The :free suffix, pricing, and why models disappear.
- [Group Pinning](https://routerah.app/en/docs/platform/group-pinning): Lock a model to specific provider groups instead of cheapest routing.
- [Platform API](https://routerah.app/en/docs/platform/platform-api): Read the catalog, prices, your balance and your usage from code.
- [Consents for model providers](https://routerah.app/en/docs/platform/consents): Why some providers need your consent, how to give or withdraw it, and how API clients handle the consent error.
- [Rate Limits & Errors](https://routerah.app/en/docs/platform/errors-and-rate-limits): The limits, and what each status code means.
- [Account & Billing](https://routerah.app/en/docs/platform/account-and-billing): Balance, free credit, and auditing requests.
- [Discord Rewards](https://routerah.app/en/docs/platform/discord-rewards): Every way to earn free balance in the Discord server.

## Blog

## Product
- [Pricing](https://routerah.app/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://routerah.app/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://routerah.app/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
- [kimi-k3.1-pro](https://routerah.app/en/models/moonshot/kimi-k3.1-pro): 0.068 in / 0.34 out per 1M tokens
- [or-kimi-k3.1-pro](https://routerah.app/en/models/moonshot/or-kimi-k3.1-pro): 2 in / 10 out per 1M tokens
- [minimax-m3.1-flash:free](https://routerah.app/en/models/minimax/minimax-m3.1-flash:free): free
- [deepseek-v4.1-flash-1017](https://routerah.app/en/models/deepseek/deepseek-v4.1-flash-1017): 0.02073 in / 0.08292 out per 1M tokens
- [xing4.0-29b-a4b:free](https://routerah.app/en/models/teleai/xing4.0-29b-a4b:free): free
- [sage-a1.5:free](https://routerah.app/en/models/internlm/sage-a1.5:free): free
- [jev-1.14](https://routerah.app/en/models/typesafe/jev-1.14): 0.0887 in / 0 out per 1M tokens
- [gemini-4-argon](https://routerah.app/en/models/google/gemini-4-argon): 0.816 in / 4.08 out per 1M tokens
- [muse-wonder](https://routerah.app/en/models/meta/muse-wonder): 4 in / 20 out per 1M tokens
- [step-5-preview](https://routerah.app/en/models/stepfun/step-5-preview): 1 in / 2.7 out per 1M tokens
- [claude-haiku-5-5](https://routerah.app/en/models/anthropic/claude-haiku-5-5): 0.04284 in / 0.2142 out per 1M tokens
- [or-claude-haiku-5-5](https://routerah.app/en/models/anthropic/or-claude-haiku-5-5): 0.1 in / 0.5 out per 1M tokens
- [gemini-nano-banana-2.1](https://routerah.app/en/models/google/gemini-nano-banana-2.1): 0 in / 0 out per 1M tokens
- [mistral-large-4](https://routerah.app/en/models/mistral/mistral-large-4): 2 in / 6 out per 1M tokens
- [nemotron-3.5-bolt-e4b:free](https://routerah.app/en/models/nvidia/nemotron-3.5-bolt-e4b:free): free
- [ling-3.1-flash:free](https://routerah.app/en/models/inclusionai/ling-3.1-flash:free): free
- [mercury-decide:free](https://routerah.app/en/models/inception/mercury-decide:free): free
- [gpt-6.1-sol](https://routerah.app/en/models/openai/gpt-6.1-sol): 0.3 in / 1.5 out per 1M tokens
- [claude-sonnet-5-5](https://routerah.app/en/models/anthropic/claude-sonnet-5-5): 0.447 in / 2.235 out per 1M tokens
- [gpt-6-luna](https://routerah.app/en/models/openai/gpt-6-luna): 0.021 in / 0.10500000000000001 out per 1M tokens
- [gpt-6-sol](https://routerah.app/en/models/openai/gpt-6-sol): 0.3 in / 1.5 out per 1M tokens
- [claude-opus-5.5](https://routerah.app/en/models/anthropic/claude-opus-5.5): 0.894 in / 4.47 out per 1M tokens
- [mimo-v2.6-flash](https://routerah.app/en/models/xiaomi/mimo-v2.6-flash): 0.14 in / 0.28 out per 1M tokens
- [mimo-v2.6-pro](https://routerah.app/en/models/xiaomi/mimo-v2.6-pro): 0.435 in / 0.87 out per 1M tokens
- [grok-4.7](https://routerah.app/en/models/xai/grok-4.7): 0.024 in / 0.07200000000000001 out per 1M tokens
- [qwen3.8-omni-flash](https://routerah.app/en/models/alibaba/qwen3.8-omni-flash): 0.15 in / 0.469995 out per 1M tokens
- [jev-1.13](https://routerah.app/en/models/typesafe/jev-1.13): 0.0887 in / 0 out per 1M tokens
- [atria-dawn-preview:free](https://routerah.app/en/models/internlm/atria-dawn-preview:free): free
- [atria-dawn:free](https://routerah.app/en/models/internlm/atria-dawn:free): free
- [intern-s2:free](https://routerah.app/en/models/internlm/intern-s2:free): free
- [deepseek-v4.1-flash](https://routerah.app/en/models/deepseek/deepseek-v4.1-flash): 0.0208065 in / 0.083226 out per 1M tokens
- [gpt-image-2.5-flare](https://routerah.app/en/models/openai/gpt-image-2.5-flare): 1.75 in / 1.75 out per 1M tokens
- [gpt-image-2.5-flare:flat](https://routerah.app/en/models/openai/gpt-image-2.5-flare:flat): 0 in / 0 out per 1M tokens
- [gpt-image-2.5-sunburst](https://routerah.app/en/models/openai/gpt-image-2.5-sunburst): 2.625 in / 2.625 out per 1M tokens
- [gpt-image-2.5-sunburst:flat](https://routerah.app/en/models/openai/gpt-image-2.5-sunburst:flat): 0 in / 0 out per 1M tokens
- [nemotron-sea-lion-v4.8-120b-a12b:free](https://routerah.app/en/models/nvidia/nemotron-sea-lion-v4.8-120b-a12b:free): free
- [gpt-6-astra](https://routerah.app/en/models/openai/gpt-6-astra): 1.5 in / 7.5 out per 1M tokens
- [qwen3.8-max](https://routerah.app/en/models/alibaba/qwen3.8-max): 0.42 in / 1.26 out per 1M tokens
- [k2-horizon:free](https://routerah.app/en/models/ifm/k2-horizon:free): free
- [muse-spark-1.3-contributor](https://routerah.app/en/models/meta/muse-spark-1.3-contributor): 0.1 in / 0.2 out per 1M tokens
- [gemini-3.8-flash](https://routerah.app/en/models/google/gemini-3.8-flash): 0.063 in / 0.315 out per 1M tokens
- [claude-fable-5.1](https://routerah.app/en/models/anthropic/claude-fable-5.1): 2.235 in / 11.174999999999999 out per 1M tokens
- [qwen3.8-flash](https://routerah.app/en/models/alibaba/qwen3.8-flash): 0.0288 in / 0.09023904 out per 1M tokens
- [glm-5.3-flash](https://routerah.app/en/models/zhipu/glm-5.3-flash): 0.081 in / 0.2699973 out per 1M tokens
- [glm-5.3-flash-search:free](https://routerah.app/en/models/zhipu/glm-5.3-flash-search:free): free
- [glm-5.3-flash:free](https://routerah.app/en/models/zhipu/glm-5.3-flash:free): free
- [muse-spark-1.2-contributor](https://routerah.app/en/models/meta/muse-spark-1.2-contributor): 0.1 in / 0.2 out per 1M tokens
- [glm-5.3](https://routerah.app/en/models/zhipu/glm-5.3): 0.098 in / 0.3080042 out per 1M tokens
- [or-glm-5.3](https://routerah.app/en/models/zhipu/or-glm-5.3): 1.27274 in / 4.000094546 out per 1M tokens
- [qwen3.8-27b:free](https://routerah.app/en/models/alibaba/qwen3.8-27b:free): free

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

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