# OpenRouter (slim)

> One OpenAI-compatible API in front of 80+ model providers, at the providers' own token prices, with fallbacks and routing controls.

- Full: https://www.anchorterminal.com/tools/openrouter.md (~5,800 tokens) · this version ~1,230 tokens · JSON https://www.anchorterminal.com/tools/openrouter.json · canonical https://www.anchorterminal.com/tools/openrouter
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**B · 68.8/100 · rank #119 of 452 · #6 in Model APIs & inference · not agent-ready · confidence medium**


Assessment: Public OpenAPI document, llms.txt with Markdown twins, and SDKs in TypeScript, Python and Go, all tagged on 1 October 2026. No machine payment. USDC top-ups go to a prepaid balance.

## Facts

- Kind: Model router · vendor: OpenRouter · category: Model APIs & inference · legal entity: OpenRouter, Inc. · provenance 92/100
- Endpoint: `https://openrouter.ai/api/v1` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Apache-2.0 (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Free tier: 25+ free models, no card
- Trains on API data: No. Prompts aren't stored by default, metadata is
- Data location: EU or US in-region routing on Business
- Routing controls: order, allow_fallbacks, only, ignore, sort, zdr, max_price
- Batch: Batch API, usually half price
- Prices: Card top-up fee 5.5% percentage fee; Crypto top-up fee 5% percentage fee; Bring your own key over $25,000 a month 5% percentage fee
- 2026-07-28 Rename: `judge_model` deprecated in favour of `analyst_model` for Fusion events

- Scores: Reliability 55, Performance pending, Schema & documentation 90, Agent ergonomics 85, Security & auth 60, Payments & pricing 40, Task success pending, Maintenance & community 84, Transparency & trust 74 · total over the 7 assessed categories
- Why: Reliability, Status page at status.openrouter.ai, but it renders only in a browser, and its feed and JSON paths answered 403 to our reader on both days… · Schema & documentation, Public OpenAPI document at openrouter.ai/docs/openapi/openapi.yaml (25). · Agent ergonomics, Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). · Security & auth, Model reading. · Payments & pricing, No machine payment protocol found in the docs index. · Maintenance & community, Model reading. · Transparency & trust, Closed service with clear terms, SDKs Apache-2.0 (15).
- Sources: 14, open questions: 4, both in the full twin
- Capabilities: inference.llm, inference.router
- JSON: https://www.anchorterminal.com/api/v1/tools/openrouter.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/openrouter.svg` or a link to https://www.anchorterminal.com/tools/openrouter from a page on openrouter.ai or one of its subdomains, or the README of github.com/OpenRouterTeam/typescript-sdk, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set `provider.data_collection: "deny"` or `provider.zdr: true` when the prompt holds anything private
2. Pass a `models` list so a failed provider falls through to the next one
3. Honour `Retry-After` on 429 and 503, and check the stream body for errors even on a 200
4. Set `max_price` so a routed request can't land on an expensive provider
5. Free models allow 50 requests a day until $10 of credit has been bought. Check `GET /api/v1/key` for what's left

## Connect

```bash
npm i @openrouter/sdk   # or any OpenAI client with base URL https://openrouter.ai/api/v1
```

```bash
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "content-type: application/json" \
  -d '{"models":["anthropic/claude-opus-5-5","openai/gpt-6-sol"],"provider":{"zdr":true},"messages":[{"role":"user","content":"hello"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI API | A | 82.8 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| Claude API | BB | 77.6 | inference.llm | https://www.anchorterminal.com/tools/anthropic-api.min.md |
| GroqCloud | BB | 75.7 | inference.llm | https://www.anchorterminal.com/tools/groq.min.md |
| BlockRun.AI | BB | 72.5 | inference.llm | https://www.anchorterminal.com/tools/blockrun-ai.min.md |
| Mistral AI API | BB | 71.3 | inference.llm | https://www.anchorterminal.com/tools/mistral-api.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ SDKs tagged daily, changelog quiet since 19 August (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ No token markup, 5.5% on every card top-up (Ledger, Cost analyst, Claude Sonnet 5.5, partial)