Wire AnyRouter into a project, migrate from Anthropic / OpenAI / OpenRouter, and call its MCP server. Use when the user mentions AnyRouter, asks to add a unified LLM gateway, wants to swap providers without code churn, migrates an existing OpenAI/Anthropic/OpenRouter integration, sets up Claude Code / Codex / Cursor against a custom base URL, or needs help with model ids like `provider/model`, app attribution headers (`X-AnyRouter-*`), provider preferences, streaming, BYOK, or the AnyRouter MCP server at `https://anyrouter.dev/api/v1/mcp`.
Instrucciones de origen · Vista previa de solo lectura
name
anyrouter
description
Wire AnyRouter into a project, migrate from Anthropic / OpenAI / OpenRouter, and call its MCP server. Use when the user mentions AnyRouter, asks to add a unified LLM gateway, wants to swap providers without code churn, migrates an existing OpenAI/Anthropic/OpenRouter integration, sets up Claude Code / Codex / Cursor against a custom base URL, or needs help with model ids like `provider/model`, app attribution headers (`X-AnyRouter-*`), provider preferences, streaming, BYOK, or the AnyRouter MCP server at `https://anyrouter.dev/api/v1/mcp`.
AnyRouter
AnyRouter is a universal, OpenAI-compatible LLM gateway. One base URL, one API key, 150+ models across 28+ providers, deterministic failover, and a remote MCP server for key + credit management. Use this skill whenever you need to wire AnyRouter into a project or migrate an existing integration.
Always fetch the live docs — do not rely on memory
This skill is intentionally thin. It tells you where to look, not what every page says. AnyRouter ships its full documentation as raw markdown, regenerated on every deploy. Before answering any non-trivial AnyRouter question, fetch the relevant .md URL with your web-fetch tool (WebFetch, curl via Bash, or your platform's equivalent) and read the current content. Do not rely on the model id, scope name, or header values memorised in this skill — they can change.
Discovery sources (in priority order):
https://anyrouter.dev/docs.md — auto-generated index. Every section, every page, every link points at the .md mirror. Start here when you don't know which page you need.
Append .md to any docs URL — https://anyrouter.dev/docs/<path>.md gives the raw markdown of any rendered page.
https://anyrouter.dev/llms-full.txt — every doc concatenated, useful when you want one bulk read.
— short LLM index per .
https://anyrouter.dev/llms.txt
llmstxt.org
https://anyrouter.dev/docs/index.json — machine-readable manifest if you need to filter programmatically.
Operating rule: when the user asks about AnyRouter, do not paraphrase from this skill alone. Fetch the live .md, ground your answer in it, and cite the URL you used.
Default model when unspecified: openai/gpt-5.4-mini. Cheap+fast: openai/gpt-5.4-nano, anthropic/claude-haiku-4.5. High-quality: anthropic/claude-sonnet-4.6, openai/gpt-5.4.
When to use this skill
The user mentions AnyRouter by name.
They want to add a unified LLM gateway so they can swap providers without rewriting client code.
They have an existing OpenAI, Anthropic, or OpenRouter integration and want to migrate to AnyRouter.
They want to point Claude Code, Codex, Cursor, Aider, Hermes, or another agent at AnyRouter.
They need app attribution, provider preferences, price caps, failover, or routing controls.
They want to use the AnyRouter MCP server from a client.
Before integrating, check if the project already has an LLM client. If so, change the base URL, key, and model id rather than introducing a new client.
How to look things up
When the user asks something specific (recipes, headers, scopes, model lists, BYOK setup, billing details, rate limits), fetch the matching .md URL before answering. Do not summarise from this skill alone.
Recipe:
Pick the most likely URL from the entry points below. If unsure, fetch https://anyrouter.dev/docs.md first and read the section headings.
Use WebFetch (or curl -sSL <url>) to retrieve the raw markdown.
Quote / paraphrase from what you fetched. Include the URL in your response so the user can verify.
If the URL 404s, the page was renamed or removed — re-fetch the index and pick the current link.
Top categories with a one-line summary of every important child page. These hints let you pick the right URL without an index round-trip — the authoritative, current list with every page is always at https://anyrouter.dev/docs.md.
Getting Started
Quickstart — First request in under five minutes. Point any OpenAI-compatible client at the AnyRouter base URL.
Authentication — Generate, scope, and rotate API keys. Bearer tokens, BYOK, per-environment isolation.
Guides (recipes for agents and migrations)
AI Agent Integration — Paste-prompt for any coding agent (Claude Code, Cursor, Codex, Aider, Hermes, …) wiring AnyRouter into an existing project.
Claude Code — Two env vars (ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN) route Claude Code through AnyRouter. Includes a claude-ar wrapper recipe.
From Anthropic → either keep the Anthropic SDK and set ANTHROPIC_BASE_URL=https://anyrouter.dev/api (Anthropic-native /messages), or unify on /chat/completions with model: "anthropic/claude-sonnet-4.6". Details: https://anyrouter.dev/docs/guides/migrate-from-anthropic.md.
From OpenRouter → identical request shape. Change base URL to https://anyrouter.dev/api/v1, key env to ANYROUTER_API_KEY. provider.only / .ignore / .order / .sort / .max_price / .allow_fallbacks all map across. Details: https://anyrouter.dev/docs/guides/migrate-from-openrouter.md.
Pin a single upstream with X-AnyRouter-Provider: <provider_id> — useful for reproducibility, BYOK testing, and outage debugging. Full routing model: https://anyrouter.dev/docs/features/routing.md.
This plugin registers a remote MCP server at https://anyrouter.dev/api/v1/mcp. Tools exposed:
Tool
Purpose
list_models
Search the catalog by provider, capability, or context window
get_credits
Workspace balance and lifetime usage
list_keys
List API keys
create_key
Mint a new API key
revoke_key
Disable a key by id
list_presets
List saved request presets
list_conversations
Search workspace conversations
OAuth runs on first tool call — the user picks Read-only / Standard / Full on the consent screen. There is no chat tool; use the regular chat endpoint for inference.
