# GPT-5 nano

> OpenAI's smallest GPT-5 variant, tuned for speed and efficiency, with image input and tool calling.

## Key facts

- Model author: OpenAI
- Input: $0.05 per 1M tokens
- Output: $0.40 per 1M tokens
- Cached input: $0.005 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: May 31, 2024
- Model IDs: `openai/gpt-5-nano`
- Model page: https://www.realrelay.ai/model/openai/gpt-5-nano

## Overview

GPT-5 nano is the smallest variant of OpenAI's GPT-5, designed for speed and efficiency. It is a reasoning model that accepts text and image input, returns text, and supports tool calling and structured output, with a context window of 400,000 tokens.

GPT-5 nano has a context window of 400,000 tokens and can generate up to 128,000 output tokens. It accepts text and image input and returns text output. Its knowledge cutoff is May 31, 2024, and it was released on August 7, 2025.

## Capabilities

GPT-5 nano supports reasoning, tool calling, structured output and image input, and it returns text. It can generate up to 128,000 output tokens per request, which covers reasoning and the visible answer.

Its knowledge cutoff is May 31, 2024. Cached input reads have a very low separate price.

## Pricing

GPT-5 nano is billed per token: $0.05 per 1M input tokens and $0.40 per 1M output tokens. Cached input reads cost $0.005 per 1M tokens. GPT-5 nano is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5 nano for rapid interactions and developer tools, such as inline suggestions, quick lookups through tool calls, or short replies in a chat window where response time matters.

It also fits high-volume text steps that return structured output, for example extracting fields from messages or documents before a larger model takes over.

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

## FAQ

### What is GPT-5 nano?

GPT-5 nano is the smallest variant of OpenAI's GPT-5, designed for speed and efficiency. It is a reasoning model that accepts text and image input, returns text, and supports tool calling and structured output, with a context window of 400,000 tokens.

### How much does GPT-5 nano cost?

GPT-5 nano costs $0.05 per 1M input tokens and $0.40 per 1M output tokens, with cached input reads at $0.005 per 1M tokens.

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

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

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

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

### Which features does GPT-5 nano support?

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

### When was GPT-5 nano released?

GPT-5 nano was released on August 7, 2025. Its knowledge cutoff is May 31, 2024.

### How do I call GPT-5 nano through the API?

To call GPT-5 nano, send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-5-nano.