---
title: "Auto Free API guide"
description: "No-deposit requests, account quotas, supported protocols, and the chat trial distinction."
canonical_url: "https://minirouter.sh/docs/free-inference"
markdown_url: "https://minirouter.sh/docs/free-inference.md"
last_updated: "2026-09-13"
---

# Auto Free API guide

Use model minirouter/auto:free for free requests without a deposit or money hold,
subject to availability and account limits. Free never falls back to paid models, even
if your account has credits. Bare minirouter/auto still selects paid Smart routing.

## Get started

1. Check https://minirouter.sh/models/auto/free for availability.
2. Create a key at https://minirouter.sh/key and save the key and recovery link.
3. Set MINIROUTER_KEY locally, then run:

```sh
curl https://api.minirouter.sh/v1/chat/completions \
  -H "Authorization: Bearer $MINIROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minirouter/auto:free","messages":[{"role":"user","content":"Explain an API gateway in one sentence."}],"max_tokens":256}'
```

The response reports the answering model in x-minirouter-model and a zero customer
charge in x-minirouter-cost-usd and usage.cost.
Use https://minirouter.sh/dashboard/chat/free for the signed-in playground.

## Supported requests

Chat Completions (/v1/chat/completions), Responses (/v1/responses), and Messages
(/v1/messages) support JSON and SSE for text requests.
Unsupported features return an error. Set max_output_tokens for
Responses, or max_tokens for Chat Completions and Messages. Add stream:true for SSE.
Do not send routing overrides: models, provider, providerOptions, route, or fallbacks.

Auto Free selects poolside/laguna-s-2.1-free. Naming that exact model uses the
same free path and shares the same quotas. Use one of these two IDs for no-deposit API requests.

## Account limits

| Limit | Allowance |
| --- | --- |
| Concurrent requests | 1 per account |
| Requests per minute | 5 per account |
| Requests per UTC day | 50 per account |
| Input + output tokens per UTC day | 100,000 per account |
| Estimated input per request | 16,000 tokens |
| Output per request | 2,048 tokens maximum; 1,024 by default |

Limits apply across all keys on an account. Existing account/key limits also apply.
In-progress requests temporarily count their estimated input and maximum output
toward your token allowance. Once complete, the allowance adjusts to actual usage.
Requests sent to a provider count toward your request quota even if they fail. Daily allowances reset
at 00:00 UTC. Creating another key does not increase them. /me.freeInference
returns eligibility, remaining requests/tokens, resetsAt, and request caps.

## Errors and usage

- 429 free_quota_exceeded: wait for Retry-After; daily exhaustion lasts until reset.
  Raising a key limit or adding credits does not raise the free allowance.
- 503 auto_unresolvable: Auto Free is temporarily unavailable. Retry later;
  the router will not switch to a paid model.
- 400 invalid_request: simplify unsupported features or remove routing overrides.
- View your requests in Activity. Auto Free requests always cost you $0.

## Auto Free, chat trial, and paid Auto

- Auto Free: the minirouter/auto:free API alias and signed-in playground, with daily quotas.
- Chat trial: the separate three-message offer at https://minirouter.sh/chat subject to
  availability. Its allowance covers browser chat, not integration API requests.
- Paid Auto: minirouter/auto and smart/cheap/code/roleplay intents use account credits
  and normal monetary holds. Choose paid models explicitly to use them.

Playground conversations clear on reload; only model/reasoning preferences persist.
The separate /chat flow offers account-scoped history and explicit saving.

A listed model may still be unavailable for your request. Each request must fit
your account limits, key permissions, supported features, and available capacity.