# Start on anyrouter/free or anyrouter/auto

> Two built-in virtual models: free failover on Go and up (anyrouter/free) and stable paid failover (anyrouter/auto). Do not pick a flaky SKU for your first request.

Two built-in models that fail over

**Slug**: `virtual-presets`  
**URL**: https://anyrouter.dev/use-cases/virtual-presets  
**Markdown**: https://anyrouter.dev/use-cases/virtual-presets.md  
**Short link**: https://anyrouter.dev/u/virtual-presets  

## Why use this

A first request that pins a single free SKU often 404s or 429s. You want something that is answering right now, with automatic fallback.

## Set it up

1. Create a key. anyrouter/free works on Go and up, deducts no credits, and has no daily cap.
2. Call anyrouter/free for the free chain, or anyrouter/auto for paid models that are healthy right now. Paid models need credits.
3. The response model field names the model that answered.

## Code

### curl · anyrouter/free

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anyrouter/free",
    "messages": [{ "role": "user", "content": "Say hello in one sentence." }]
  }'
```

### curl · anyrouter/auto

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anyrouter/auto",
    "messages": [{ "role": "user", "content": "Say hello in one sentence." }]
  }'
```

## Related

- [go-plan](https://anyrouter.dev/use-cases/go-plan)
- [nvidia-free-key](https://anyrouter.dev/use-cases/nvidia-free-key)
- [free-llm-api](https://anyrouter.dev/use-cases/free-llm-api)
