# GPT-5.5

> OpenAI's reasoning model for coding and professional work, with computer use, web search and a 1.05M-token window.

## Key facts

- Model author: OpenAI
- Input: $4.6056 per 1M tokens (starting tier)
- Output: $27.6332 per 1M tokens (starting tier)
- Cached input: $0.4606 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: 2026-04-23
- Knowledge cutoff: Dec 01, 2025
- Model IDs: `jd/gpt-5.5`, `openai/gpt-5.5`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.5

## Overview

GPT-5.5 is a reasoning model from OpenAI designed for coding and professional work. It accepts text and image input, returns text, and combines reasoning, tool calling, structured output and computer use within a 1.05M-token context window. Its large context window also makes it suited to long documents and large codebases.

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 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-5.5 for coding and professional work.

## Pricing

GPT-5.5 costs from $4.61 per 1M input tokens and from $27.63 per 1M output tokens. Cached input reads cost from $0.46 per 1M tokens. Pricing is tiered, and the prices shown are the starting tier. GPT-5.5 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.5 for coding agents that work across a large repository, planning changes, calling tools and running tests; the 1.05M-token context window keeps the code and its history in one request.

For professional work it can research with web search, read files and screenshots, operate software through computer use, and return structured output for downstream systems.

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

## FAQ

### What is GPT-5.5?

GPT-5.5 is a reasoning model from OpenAI designed for coding and professional work.

### How much does GPT-5.5 cost?

GPT-5.5 costs from $4.61 per 1M input tokens and from $27.63 per 1M output tokens. Cached input reads cost from $0.46 per 1M tokens. Pricing is tiered, and the prices shown are the starting tier.

### What is the context window of GPT-5.5?

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

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

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

### Does GPT-5.5 support tool calling?

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

### When was GPT-5.5 released?

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

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

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