# GPT-6 Luna

## Best for

Everyday GPT-6 work where you want to keep costs down

## When not to use

Audio, video, or realtime work. Not GPT-6 Sol — use Sol for complex coding and long-horizon agentic workflows. Call it as `gpt-6-luna`.

## Overview

GPT-6 Luna is the lower-cost GPT-6 option for repeatable, focused tasks. It handles coding, reasoning, tool use, and image input, with a 1,050,000-token context window.

| | |
| --- | --- |
| API identifier | `gpt-6-luna` |
| Developer | OpenAI |
| Context window | 1,050,000 tokens |
| Supports | text, reasoning, tool-use, image input, vision |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.10 | $0.01 | $0.50 |

## Call it

Put `gpt-6-luna` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).