# GPT-5.2

> OpenAI's flagship reasoning model for professional work, with configurable reasoning effort and image input.

## Key facts

- Model author: OpenAI
- Input: $1.75 per 1M tokens
- Output: $14.00 per 1M tokens
- Cached input: $0.175 per 1M tokens
- Context window: 400,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2025-12-11
- Knowledge cutoff: Aug 31, 2025
- Model IDs: `openai/gpt-5.2`
- Model page: https://www.realrelay.ai/model/openai/gpt-5.2

## Overview

GPT-5.2 is a flagship reasoning model from OpenAI designed for professional work, with configurable reasoning effort. It accepts text and image input, returns text, and supports tool calling and structured output, so it can analyze documents and screenshots and hand back results that other systems can parse.

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 December 11, 2025.

## Capabilities

GPT-5.2 supports reasoning, tool calling, structured output and image input, and returns text output.

OpenAI documents GPT-5.2 as a flagship model for professional work with configurable reasoning effort.

## Pricing

GPT-5.2 costs $1.75 per 1M input tokens and $14.00 per 1M output tokens. Cached input reads cost $0.175 per 1M tokens. GPT-5.2 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-5.2 for professional document work: reviewing reports, contracts or slide screenshots with image input, and returning structured output for downstream systems.

It also fits multi-step business workflows that call tools to look up data and then summarize the findings, within a 400K-token context window. Image input also extends this to slide decks and scanned pages shared as pictures.

## 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-5.2", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-5.2?

GPT-5.2 is a flagship reasoning model from OpenAI designed for professional work, with configurable reasoning effort.

### How much does GPT-5.2 cost?

GPT-5.2 costs $1.75 per 1M input tokens and $14.00 per 1M output tokens. Cached input reads cost $0.175 per 1M tokens.

### What is the context window of GPT-5.2?

GPT-5.2 has a 400K-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-5.2 support?

GPT-5.2 accepts text and image input and returns text.

### Does GPT-5.2 support tool calling?

Yes. GPT-5.2 supports tool calling, along with reasoning, structured output and image input.

### When was GPT-5.2 released?

GPT-5.2 was released on December 11, 2025. Its knowledge cutoff is August 31, 2025.

### How do I call GPT-5.2 via the API?

Call GPT-5.2 through RealRelay's OpenAI-compatible API by setting the model name to openai/gpt-5.2.