# GPT-6 Astra

> OpenAI's model for demanding reasoning, coding, computer use, research and document creation work.

## Key facts

- Model author: OpenAI
- Input: $10.00 per 1M tokens (starting tier)
- Output: $50.00 per 1M tokens (starting tier)
- Cached input: $1.00 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: 2026-09-03
- Knowledge cutoff: Apr 30, 2026
- Model IDs: `jd/gpt-6-astra`, `openai/gpt-6-astra`
- Model page: https://www.realrelay.ai/model/openai/gpt-6-astra

## Overview

GPT-6 Astra is a reasoning model from OpenAI built for demanding, end-to-end work. OpenAI recommends it for complex reasoning, coding, computer use, research and document creation, where it combines these abilities to carry a task from the first request to a finished result, using the context and tools you provide.

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 April 30, 2026, and it was released on September 3, 2026.

## Capabilities

GPT-6 Astra supports reasoning, tool calling, structured output and image understanding. It reads text and image input together and returns text.

OpenAI describes it as a model that joins several skills in one task: it can reason through a problem, write code, operate software through computer use, research a topic and draft the final document.

## Pricing

GPT-6 Astra is priced from $10.00 per 1M input tokens and from $50.00 per 1M output tokens. Cached input reads are priced from $1.00 per 1M tokens.

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

## Use cases

Use GPT-6 Astra for coding and research tasks that take many steps, such as working through a large codebase or pulling findings together from long source material. The 1.05M-token context window holds the material and the tool results in one request.

It also fits computer use and document creation, where it reads screenshots or page images, calls tools, and returns a finished document as text.

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

## FAQ

### What is GPT-6 Astra?

GPT-6 Astra is an OpenAI reasoning model for complex reasoning, coding, computer use, research and document creation, with a 1.05M-token context window.

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

GPT-6 Astra is priced from $10.00 per 1M input tokens and from $50.00 per 1M output tokens. Cached input reads are priced from $1.00 per 1M tokens.

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

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

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

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

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

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

### When was GPT-6 Astra released?

GPT-6 Astra was released on September 3, 2026.

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

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