# GPT-6 Luna

> OpenAI's efficient reasoning model for focused, high-volume tasks with text and image input.

## Key facts

- Model author: OpenAI
- Input: $0.10 per 1M tokens (starting tier)
- Output: $0.50 per 1M tokens (starting tier)
- Cached input: $0.01 per 1M tokens
- Context window: 1,050,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-09-22
- Knowledge cutoff: May 18, 2026
- Model IDs: `jd/gpt-6-luna`, `openai/gpt-6-luna`
- Model page: https://www.realrelay.ai/model/openai/gpt-6-luna

## Overview

GPT-6 Luna is a reasoning model from OpenAI designed for focused, high-volume tasks. OpenAI positions it as an efficient model: it reads text and image input, returns text, and supports tool calling and structured output, so it fits steps that an application runs again and again with a clear input and a predictable result.

It has a 1.05M-token context window and can generate up to 128,000 output tokens. It accepts text and image input and returns text. Its knowledge cutoff is May 18, 2026, and it was released on September 22, 2026.

## Capabilities

GPT-6 Luna supports reasoning, tool calling, structured output and image understanding, and it accepts text and image input.

OpenAI's description centers on focused tasks at high volume. That points to well-defined steps in a larger system, where each call has a narrow job and returns a result that other code can parse.

## Pricing

GPT-6 Luna is priced from $0.10 per 1M input tokens and from $0.50 per 1M output tokens. Cached input reads are priced from $0.01 per 1M tokens.

GPT-6 Luna is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-6 Luna for focused, high-volume work such as classifying support tickets, extracting fields from documents or screenshots, and routing requests. Structured output keeps each result easy for downstream code to read.

Its tool calling lets it act as a quick first step in an agent pipeline, and the 1.05M-token context window leaves room for long inputs when a task needs them.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-6-luna", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-6 Luna?

GPT-6 Luna is an efficient OpenAI reasoning model for focused, high-volume tasks, with text and image input and a 1.05M-token context window.

### How much does GPT-6 Luna cost?

GPT-6 Luna is priced from $0.10 per 1M input tokens and from $0.50 per 1M output tokens. Cached input reads are priced from $0.01 per 1M tokens.

### What is the context window and maximum output of GPT-6 Luna?

GPT-6 Luna has a 1.05M-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-6 Luna support?

GPT-6 Luna accepts text and image input and returns text.

### What capabilities does GPT-6 Luna support?

GPT-6 Luna supports reasoning, tool calling, structured output and image understanding.

### When was GPT-6 Luna released?

GPT-6 Luna was released on September 22, 2026.

### How do I call GPT-6 Luna via the API?

Call GPT-6 Luna through RealRelay's OpenAI-compatible API using the model ID openai/gpt-6-luna.