# GPT-5

> OpenAI's reasoning model for coding and agentic tasks, with text and image input and structured output.

## Key facts

- Model author: OpenAI
- Input: $1.25 per 1M tokens
- Output: $10.00 per 1M tokens
- Cached input: $0.125 per 1M tokens
- Context window: 400,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2025-08-07
- Knowledge cutoff: Sep 30, 2024
- Model IDs: `openai/gpt-5`
- Model page: https://www.realrelay.ai/model/openai/gpt-5

## Overview

GPT-5 is a reasoning model from OpenAI designed for coding and agentic tasks. It accepts text and image input and returns text. Tool calling and structured output let it drive multi-step workflows whose results other software can parse reliably. It is documented for tasks that combine reasoning with tool use.

It has a 400K-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 September 30, 2024, and it was released on August 7, 2025.

## Capabilities

GPT-5 supports reasoning, tool calling, structured output and image input, and returns text output.

OpenAI documents GPT-5 as a reasoning model for coding and agentic tasks.

## Pricing

GPT-5 costs $1.25 per 1M input tokens and $10.00 per 1M output tokens. Cached input reads cost $0.125 per 1M tokens. GPT-5 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5 for coding agents that read a repository, plan a change and call tools to edit and test it; the 400K-token context window holds a large codebase in one request.

It also suits agentic workflows that pair tool calls with screenshots or diagrams as image input, and that need structured output for downstream systems.

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

## FAQ

### What is GPT-5?

GPT-5 is a reasoning model from OpenAI designed for coding and agentic tasks.

### How much does GPT-5 cost?

GPT-5 costs $1.25 per 1M input tokens and $10.00 per 1M output tokens. Cached input reads cost $0.125 per 1M tokens.

### What is the context window of GPT-5?

GPT-5 has a 400K-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-5 support?

GPT-5 accepts text and image input and returns text.

### Does GPT-5 support tool calling?

Yes. GPT-5 supports tool calling, along with reasoning, structured output and image input.

### When was GPT-5 released?

GPT-5 was released on August 7, 2025. Its knowledge cutoff is September 30, 2024.

### How do I call GPT-5 via the API?

Call GPT-5 through RealRelay's OpenAI-compatible API by setting the model name to openai/gpt-5.