# Gemini 3.1 Pro Preview (thinking) API

> Gemini 3.1 Pro Preview (thinking) by Google, through an OpenAI-compatible chat completions API. By Google, on Revana at $2.00 in / $12.00 out per 1M tokens.

- Model id: `gemini-3.1-pro-preview-thinking`
- Kind: text (chat completions)
- Maker: Google
- Endpoint: `POST https://api.revana.si/v1/chat/completions` (OpenAI-compatible, streaming supported)
- Routes: 1
- Page: https://revana.si/llm/gemini-3.1-pro-preview-thinking

## Price (USD per million tokens)

| Tokens | Price |
|---|---|
| Input | $2.00 |
| Cached input | $2.00 |
| Cache write (5 min) | $2.00 |
| Cache write (1 hour) | $2.00 |
| Output | $12.00 |

Reasoning tokens are billed as output. Each answer's `usage.cost_usd` is the amount taken from your balance; a request with no answer costs nothing.

## Request

```bash
curl https://api.revana.si/v1/chat/completions \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.1-pro-preview-thinking","messages":[{"role":"user","content":"Write a haiku about routing."}]}'
```

Or any OpenAI SDK with `base_url="https://api.revana.si/v1"`. Docs: https://revana.si/chat