# GPT-5.4

> OpenAI's reasoning model for coding and professional work, with a 1.05M-token context window and tool calling.

## Key facts

- Model author: OpenAI
- Input: $2.50 per 1M tokens (starting tier)
- Output: $15.00 per 1M tokens (starting tier)
- Cached input: $0.25 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: 2026-03-05
- Knowledge cutoff: Aug 31, 2025
- Model IDs: `openai/gpt-5.4`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.4

## Overview

GPT-5.4 is a reasoning model from OpenAI designed for coding and professional work, which OpenAI positions as a more affordable option. It accepts text and image input, returns text, and combines reasoning, tool calling and structured output with a 1.05M-token context window.

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 August 31, 2025, and it was released on March 5, 2026.

## Capabilities

GPT-5.4 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-5.4 as a more affordable model for coding and professional work.

## Pricing

GPT-5.4 costs from $2.50 per 1M input tokens and from $15.00 per 1M output tokens. Cached input reads cost from $0.25 per 1M tokens. Pricing is tiered, and the prices shown are the starting tier. GPT-5.4 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.4 for coding work on large repositories: the 1.05M-token context window holds many files at once, and tool calling lets it edit and test code.

For professional work it can review long documents with screenshots or charts as image input and return structured output that downstream systems can parse.

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

## FAQ

### What is GPT-5.4?

GPT-5.4 is a reasoning model from OpenAI designed for coding and professional work, which OpenAI positions as a more affordable option.

### How much does GPT-5.4 cost?

GPT-5.4 costs from $2.50 per 1M input tokens and from $15.00 per 1M output tokens. Cached input reads cost from $0.25 per 1M tokens. Pricing is tiered, and the prices shown are the starting tier.

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

GPT-5.4 has a 1.05M-token context window and can generate up to 128,000 output tokens.

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

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

### Does GPT-5.4 support tool calling?

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

### When was GPT-5.4 released?

GPT-5.4 was released on March 5, 2026. Its knowledge cutoff is August 31, 2025.

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

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