All use cases
Decisions API
Triage with typed decisions instead of chat
Send state and typed questions to /api/v1/decisions and get probabilities back, not generated text. anyrouter/decision is free on every plan.
What this is for
Routing a ticket or flagging urgency with a chat model means prompting for JSON and parsing it. A decision model returns the typed answer directly.
Steps, then copy
- 1.Send state (text or an object) and a questions map. Each question is noul (yes/no), choice, or score.
- 2.Use model anyrouter/decision. It picks a healthy decision model and falls back if one fails.
- 3.Read answers in the response. The model field names the model that answered.
curl · decisions
bash
curl https://anyrouter.dev/api/v1/decisions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"state": "Help! My payouts have been failing for 3 days.",
"model": "anyrouter/decision",
"questions": {
"is_urgent": { "type": "noul", "instructions": "Does this convey urgency?" }
}
}'Limits
- Do not send decision requests to /chat/completions. They are rejected there.
- A fair-use burst cap of 60 requests a minute per key applies. There is no daily or monthly cap.
Ready to try it
The guide has the full walkthrough. Sign up if you still need a key.
Next playbooks
- One API in front of every provider dialectOpenAI /chat/completions, Anthropic /messages, and a Responses API — same key, same catalog.
- Keep an agent up when a provider goes downList backup models in one request. If the primary model's providers are down or rate-limited, AnyRouter tries the next model.
- A real free LLM API for side projectsOne key, 271+ models, and a documented free tier — not a mystery coupon that disappears.