# GPT-5.6 Luna

> OpenAI's low-price model for price-sensitive, high-volume workloads, with tool calling and image input.

## Key facts

- Model author: OpenAI
- Input: $0.1842 per 1M tokens (starting tier)
- Output: $1.1053 per 1M tokens (starting tier)
- Cached input: $0.0184 per 1M tokens
- Context window: 1,050,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: apply_patch, code_interpreter, computer_use, file_search, hosted_shell, image_generation, reasoning, structured_output, tools, vision, web_search
- Released: 2026-07-09
- Knowledge cutoff: Feb 16, 2026
- Model IDs: `jd/gpt-5.6-luna`, `openai/gpt-5.6-luna`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.6-luna

## Overview

GPT-5.6 Luna is a model from OpenAI optimized for price-sensitive workloads. It accepts text and image input, returns text, and supports reasoning, tool calling and structured output, with a 1.05M-token context window, so applications that make many calls can keep reasoning and long context at a small per-token price.

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 February 16, 2026, and it was released on July 9, 2026.

## Capabilities

GPT-5.6 Luna supports reasoning, tool calling, structured output and image input, and returns text output. Its listed tools also include web search, file search, a code interpreter, computer use, image generation, patch-based code editing and a hosted shell.

OpenAI documents GPT-5.6 Luna as a model optimized for price-sensitive workloads.

## Pricing

GPT-5.6 Luna costs from $0.184 per 1M input tokens and from $1.105 per 1M output tokens. Cached input reads cost from $0.0184 per 1M tokens. Pricing is tiered, and the prices shown are the starting tier. GPT-5.6 Luna is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.6 Luna for high-volume pipelines such as classifying tickets, extracting fields into structured output and summarizing long documents that fit the 1.05M-token window.

Tool calling and image input also suit lightweight agents that route requests or read screenshots at scale. Because the context window is large, a single request can also carry a long conversation history or a batch of documents.

## 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-5.6-luna", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-5.6 Luna?

GPT-5.6 Luna is a model from OpenAI optimized for price-sensitive workloads.

### How much does GPT-5.6 Luna cost?

GPT-5.6 Luna costs from $0.184 per 1M input tokens and from $1.105 per 1M output tokens. Cached input reads cost from $0.0184 per 1M tokens. Pricing is tiered, and the prices shown are the starting tier.

### What is the context window of GPT-5.6 Luna?

GPT-5.6 Luna has a 1.05M-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-5.6 Luna support?

GPT-5.6 Luna accepts text and image input and returns text.

### Does GPT-5.6 Luna support tool calling?

Yes. GPT-5.6 Luna supports tool calling, along with reasoning, structured output and image input.

### When was GPT-5.6 Luna released?

GPT-5.6 Luna was released on July 9, 2026. Its knowledge cutoff is February 16, 2026.

### How do I call GPT-5.6 Luna via the API?

Call GPT-5.6 Luna through RealRelay's OpenAI-compatible API by setting the model name to openai/gpt-5.6-luna.