# GPT-5.5 Pro

> OpenAI's pro-tier reasoning model, with a code interpreter and structured output 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: code_interpreter, file_search, hosted_shell, image_generation, reasoning, structured_output, tools, vision, web_search
- Released: 2026-04-23
- Knowledge cutoff: Dec 01, 2025
- Model IDs: `openai/gpt-5.5-pro`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.5-pro

## Overview

GPT-5.5 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 structured output, tool calling, web search and a code interpreter, 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 December 1, 2025, and it was released on April 23, 2026.

## Capabilities

GPT-5.5 Pro 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 and a hosted shell.

OpenAI documents GPT-5.5 Pro as producing smarter and more precise responses.

## Pricing

GPT-5.5 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-5.5 Pro is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.5 Pro for analysis that needs both precision and computation, such as reading long reports and running code through the code interpreter to check figures before answering.

Structured output and file search also suit research pipelines that must return machine-readable findings from large document sets. Web search and tool calling extend this to questions that need information from outside 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-5.5-pro", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-5.5 Pro?

GPT-5.5 Pro is a pro-tier reasoning model from OpenAI, designed to produce smarter and more precise responses.

### How much does GPT-5.5 Pro cost?

GPT-5.5 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-5.5 Pro?

GPT-5.5 Pro has a 1.05M-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-5.5 Pro support?

GPT-5.5 Pro accepts text and image input and returns text.

### Does GPT-5.5 Pro support tool calling?

Yes. GPT-5.5 Pro supports tool calling, along with reasoning, structured output and image input.

### When was GPT-5.5 Pro released?

GPT-5.5 Pro was released on April 23, 2026. Its knowledge cutoff is December 1, 2025.

### How do I call GPT-5.5 Pro via the API?

Call GPT-5.5 Pro through RealRelay's OpenAI-compatible API by setting the model name to openai/gpt-5.5-pro.