anyrouter

What this skill does

# 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):

1. **`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.
2. **Append `.md` to any docs URL** — `https://anyrouter.dev/docs/<path>.md` gives the raw markdown of any rendered page.
3. **`https://anyrouter.dev/llms-full.txt`** — every doc concatenated, useful when you want one bulk read.
4. **`https://anyrouter.dev/llms.txt`** — short LLM index per `llmstxt.org`.
5. **`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.

## The contract

| Setting | Value |
| --- | --- |
| Base URL | `https://anyrouter.dev/api/v1` |
| API key env var | `ANYROUTER_API_KEY` (keys are prefixed `sk-ar-`) |
| Model id format | `provider/model` (e.g. `openai/gpt-5.4-mini`, `anthropic/claude-sonnet-4.6`) |
| Chat endpoint | `POST /chat/completions` (OpenAI-compatible) |
| Anthropic-native endpoint | `POST /messages` (for `anthropic/*` models) |
| Modern agent endpoint | `POST /responses` (typed output items + tools) |
| MCP endpoint | `https://anyrouter.dev/api/v1/mcp` (configured by this plugin) |
| Dashboard | https://anyrouter.dev/dashboard |
| Docs index (markdown) | https://anyrouter.dev/docs.md |

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:

1. Pick the most likely URL from the entry points below. If unsure, fetch `https://anyrouter.dev/docs.md` first and read the section headings.
2. Use WebFetch (or `curl -sSL <url>`) to retrieve the raw markdown.
3. Quote / paraphrase from what you fetched. Include the URL in your response so the user can verify.
4. 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](https://anyrouter.dev/docs/getting-started/quickstart.md) — First request in under five minutes. Point any OpenAI-compatible client at the AnyRouter base URL.
- [Authentication](https://anyrouter.dev/docs/getting-started/authentication.md) — Generate, scope, and rotate API keys. Bearer tokens, BYOK, per-environment isolation.

**Guides** (recipes for agents and migrations)
- [AI Agent Integration](https://anyrouter.dev/docs/guides/ai-agent-integration.md) — Paste-prompt for any coding agent (Claude Code, Cursor, Codex, Aider, Hermes, …) wiring AnyRouter into an existing project.
- [Claude Code](https://anyrouter.dev/docs/guides/claude-code.md) — Two env vars (`ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN`) route Claude Code through AnyRouter. Includes a `claude-ar` wrapper recipe.
- [Streaming](https://anyrouter.dev/docs/guides/streaming.md) — SSE incremental completions, cancellation, event shape.
- [Migrate from OpenAI](https://anyrouter.dev/docs/guides/migrate-from-openai.md) — Swap base URL, key env, model id (`gpt-*` → `openai/gpt-*`).
- [Migrate from Anthropic](https://anyrouter.dev/docs/guides/migrate-from-anthropic.md) — Keep the Anthropic SDK, swap base URL + key. Preserve `anthropic-version` header.
- [Migrate from OpenRouter](https://anyrouter.dev/docs/guides/migrate-from-openrouter.md) — Same `provider/model` ids, same `provider` object. Just change base URL and key env.
- [Hermes Agent](https://anyrouter.dev/docs/guides/hermes-agent.md) — Nous Research's Hermes Agent as a custom OpenAI-compatible provider.
- [OpenClaw](https://anyrouter.dev/docs/guides/openclaw.md) — One key across every model and messaging channel.
- [Errors](https://anyrouter.dev/docs/guides/errors.md) — HTTP status codes, error envelopes, retry guidance.
- [Provider Routing](https://anyrouter.dev/docs/guides/provider-routing.md) — Per-request ordering, sorting, fallbacks, performance thresholds, price caps.
- [Model Fallbacks](https://anyrouter.dev/docs/guides/model-fallbacks.md) — Automatic failover between models when providers are down or rate-limited.
- [Latency Overhead](https://anyrouter.dev/docs/guides/latency-overhead.md) — Real-world latency added by AnyRouter vs direct upstream calls.
- [Using Responses API](https://anyrouter.dev/docs/guides/migrate-to-responses.md) — Migration to the modern `/responses` endpoint with typed output items + tools.
- [Dashboard Tour](https://anyrouter.dev/docs/guides/dashboard-tour.md) — Walkthrough of every dashboard page in the order a new team uses them.

**Features** (product surface — describe what the platform does)
- [Smart Routing](https://anyrouter.dev/docs/features/routing.md) — How AnyRouter picks an upstream. Priority order, failover, model aliases, `X-AnyRouter-Provider` pinning.
- [App Attribution](https://anyrouter.dev/docs/features/app-attribution.md) — `X-AnyRouter-Title / -Source / -Version` headers; public-ranking surface.
- [Prompt Caching](https://anyrouter.dev/docs/features/caching.md) — Cache long system prompts across requests.
- [BYOK (Bring Your Own Key)](https://anyrouter.dev/docs/features/byok.md) — Attach upstream provider keys so requests run at list price through your accounts.
- [Tool Use](https://anyrouter.dev/docs/features/tool-use.md) — Cross-provider function calling + structured outputs.
- [Presets](https://anyrouter.dev/docs/features/presets.md) — Reusable config bundles, callable as `@preset/<name>` from any request.
- [Rate Limits](https://anyrouter.dev/docs/features/rate-limits.md) — Per-IP and per-key tiers; `429` vs `403` semantics; backoff guidance.
- [Privacy & Logging Controls](https://anyrouter.dev/docs/features/privacy-controls.md) — Body capture, PII redaction, training opt-out, blocked providers, residency.
- [Credits & Billing](https://anyrouter.dev/docs/features/credits.