# GPT-5.6 Luna

Cost-optimized tier of the GPT-5.6 family for high-volume workloads, positioned above GPT-5.4 nano.

## Overview

- **Provider:** OpenAI
- **Model ID:** `gpt-5.6-luna`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gpt-5.6-luna
- **Version:** 5.6-luna
- **Knowledge cutoff:** 2026-02
- **Best for:** High-volume workloads, fast responses, cost-sensitive tasks with extended context

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.2 / 1M tokens |
| Output | $1.2 / 1M tokens |
| Cache read | $0.02 / 1M tokens |
| Cache write (5 minutes) | $0.25 / 1M tokens |

## Specifications

- **Context window:** 1.05M
- **Maximum output:** 128K
- **Typical latency:** 10 ms
- **Released:** 2026-06

## Capabilities

- chat
- tool_use
- vision
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gpt-5.6-luna"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gpt-5.6-luna.