# GPT-5.4 Pro

> OpenAI's pro-tier reasoning model, designed for smarter and more precise responses over a 1.05M-token context.

## Key facts

- Model author: OpenAI
- Input: $30.00 per 1M tokens (starting tier)
- Output: $180.00 per 1M tokens (starting tier)
- Context window: 1,050,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: apply_patch, computer_use, file_search, image_generation, reasoning, tools, vision, web_search
- Released: 2026-03-05
- Knowledge cutoff: Aug 31, 2025
- Model IDs: `openai/gpt-5.4-pro`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.4-pro

## Overview

GPT-5.4 Pro is a pro-tier reasoning model from OpenAI, designed to produce smarter and more precise responses. It accepts text and image input, returns text, and supports tool calling, web search and computer use, with a 1.05M-token context window for long inputs.

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 Pro supports reasoning, tool calling and image input, and returns text output. Its listed tools also include web search, file search, computer use, image generation and patch-based code editing.

OpenAI documents GPT-5.4 Pro as producing smarter and more precise responses.

## Pricing

GPT-5.4 Pro costs from $30.00 per 1M input tokens and from $180.00 per 1M output tokens. Pricing is tiered, and the prices shown are the starting tier. GPT-5.4 Pro is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.4 Pro for demanding analysis over very long inputs, such as reading a whole set of contracts or research files in one request and answering with careful reasoning.

With computer use, web search and file search it can also run multi-step research and operations tasks that gather information from several sources.

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

## FAQ

### What is GPT-5.4 Pro?

GPT-5.4 Pro is a pro-tier reasoning model from OpenAI, designed to produce smarter and more precise responses.

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

GPT-5.4 Pro costs from $30.00 per 1M input tokens and from $180.00 per 1M output tokens. Pricing is tiered, and the prices shown are the starting tier.

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

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

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

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

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

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

### When was GPT-5.4 Pro released?

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

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

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