# o1-pro

> OpenAI's higher-compute reasoning model for hard problems, with image input, tools and structured output.

## Key facts

- Model author: OpenAI
- Input: $150.00 per 1M tokens
- Output: $600.00 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 100,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2025-03-19
- Knowledge cutoff: Oct 01, 2023
- Model IDs: `openai/o1-pro`
- Model page: https://www.realrelay.ai/model/openai/o1-pro

## Overview

o1-pro is a reasoning model from OpenAI that uses more compute to answer hard problems with better reasoning and consistency. It accepts text and image input, returns text, and supports tool calling and structured output. The extra compute is its documented difference.

It has a 200,000-token context window and can generate up to 100,000 output tokens. It accepts text and image input and returns text. Its knowledge cutoff is October 1, 2023, and it was released on March 19, 2025.

OpenAI lists o1-pro as deprecated in its model documentation.

## Capabilities

o1-pro supports reasoning, tool calling, structured output and image understanding. It takes text and image input and returns text.

OpenAI describes it as spending more compute on each answer, aimed at hard problems where consistent results over repeated runs matter.

## Pricing

o1-pro is priced at $150.00 per 1M input tokens and at $600.00 per 1M output tokens.

o1-pro is available through RealRelay's OpenAI-compatible API.

## Use cases

Use o1-pro for hard problems where one wrong answer is costly, such as a difficult proof, a subtle bug in a large codebase or a technical analysis that must be repeatable.

Image input allows diagrams and screenshots to be part of the question, and the 200,000-token context window holds long source material.

## 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/o1-pro", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is o1-pro?

o1-pro is an OpenAI reasoning model that uses more compute to answer hard problems with better reasoning and consistency, with a 200,000-token context window. OpenAI lists it as deprecated.

### How much does o1-pro cost?

o1-pro is priced at $150.00 per 1M input tokens and at $600.00 per 1M output tokens.

### What is the context window and maximum output of o1-pro?

o1-pro has a 200,000-token context window and can generate up to 100,000 output tokens.

### What inputs and outputs does o1-pro support?

o1-pro accepts text and image input and returns text.

### What capabilities does o1-pro support?

o1-pro supports reasoning, tool calling, structured output and image understanding.

### When was o1-pro released?

o1-pro was released on March 19, 2025.

### How do I call o1-pro via the API?

Call o1-pro through RealRelay's OpenAI-compatible API using the model ID openai/o1-pro.