> ## Documentation Index
> Fetch the complete documentation index at: https://docs.snapgen.org/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-5.6 Luna

> Use the lowest-priced GPT-5.6 route on SnapGen.

`gpt-5.6-luna` is the lowest-priced GPT-5.6 route in the current SnapGen catalog. Treat it as a distinct model ID when setting limits, monitoring usage, and comparing output quality.

| Property     | Value                         |
| ------------ | ----------------------------- |
| Model ID     | `gpt-5.6-luna`                |
| Input price  | \$0.25 per 1M tokens          |
| Output price | \$2.00 per 1M tokens          |
| Streaming    | Supported with `stream: true` |

<ParamField body="model" type="string" required>
  Set to `gpt-5.6-luna`.
</ParamField>

<ParamField body="messages" type="array" required>
  Ordered system, user, and assistant messages.
</ParamField>

## Request

```bash theme={null}
curl https://api.snapgen.org/v1/chat/completions \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [{"role": "user", "content": "Convert this support note into structured JSON."}]
  }'
```

Read generated text from `choices[0].message.content`. See [Chat Completions protocol](/api-reference/chat-completions) for streaming and response fields.

## Compatible protocol paths

| Format             | Path                                          |
| ------------------ | --------------------------------------------- |
| Chat Completions   | `/v1/chat/completions`                        |
| Responses          | `/v1/responses`                               |
| Anthropic Messages | `/v1/messages`                                |
| Gemini native      | `/v1beta/models/gpt-5.6-luna:generateContent` |

<Tip>
  Benchmark Luna against your real prompts before selecting it only by price.
  SnapGen does not alias it to another GPT-5.6 route.
</Tip>