# GPT-5.4 nano

> OpenAI's small model for simple, high-volume tasks, with tool calling and image input, listed as deprecated.

## Key facts

- Model author: OpenAI
- Input: $0.20 per 1M tokens
- Output: $1.25 per 1M tokens
- Cached input: $0.02 per 1M tokens
- Context window: 400,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: apply_patch, code_interpreter, file_search, hosted_shell, image_generation, reasoning, structured_output, tools, vision, web_search
- Released: 2026-03-17
- Knowledge cutoff: Aug 31, 2025
- Model IDs: `openai/gpt-5.4-nano`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.4-nano

## Overview

GPT-5.4 nano is a small model from OpenAI designed for simple, high-volume tasks. It accepts text and image input, returns text, and supports reasoning, tool calling and structured output. OpenAI lists it as deprecated, so plan a migration path for any long-lived workload.

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 August 31, 2025, and it was released on March 17, 2026.

## Capabilities

GPT-5.4 nano 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, image generation, patch-based code editing and a hosted shell.

OpenAI documents GPT-5.4 nano for simple, high-volume tasks.

## Pricing

GPT-5.4 nano costs $0.20 per 1M input tokens and $1.25 per 1M output tokens. Cached input reads cost $0.02 per 1M tokens. GPT-5.4 nano is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.4 nano for high-volume, simple jobs such as classifying support tickets, extracting fields into structured output or routing requests to the right tool.

Image input also lets it handle simple visual tasks at scale, such as labelling screenshots or reading short text from images. Structured output keeps results machine-readable, so they can be fed straight into databases or queues.

## 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-5.4-nano", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-5.4 nano?

GPT-5.4 nano is a small model from OpenAI designed for simple, high-volume tasks.

### How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per 1M input tokens and $1.25 per 1M output tokens. Cached input reads cost $0.02 per 1M tokens.

### What is the context window of GPT-5.4 nano?

GPT-5.4 nano has a 400K-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-5.4 nano support?

GPT-5.4 nano accepts text and image input and returns text.

### Does GPT-5.4 nano support tool calling?

Yes. GPT-5.4 nano supports tool calling, along with reasoning, structured output and image input.

### When was GPT-5.4 nano released?

GPT-5.4 nano was released on March 17, 2026. Its knowledge cutoff is August 31, 2025.

### How do I call GPT-5.4 nano via the API?

Call GPT-5.4 nano through RealRelay's OpenAI-compatible API by setting the model name to openai/gpt-5.4-nano.