# o3-mini

> A deprecated, small OpenAI reasoning model for science, math and coding tasks with text input.

## Key facts

- Model author: OpenAI
- Input: $1.10 per 1M tokens
- Output: $4.40 per 1M tokens
- Cached input: $0.55 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 100,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2025-01-31
- Knowledge cutoff: Oct 01, 2023
- Model IDs: `openai/o3-mini`
- Model page: https://www.realrelay.ai/model/openai/o3-mini

## Overview

o3-mini is a small reasoning model from OpenAI optimized for science, math and coding tasks. It takes text input and returns text, supports tool calling and structured output, and has a 200,000-token context window. Its small size makes it a lighter option for text-only reasoning work. OpenAI lists it as deprecated.

It has a 200,000-token context window and can generate up to 100,000 output tokens. It accepts text input and returns text. Its knowledge cutoff is October 1, 2023, and it was released on January 31, 2025.

## Capabilities

o3-mini supports reasoning, tool calling and structured output. It works with text input and returns text, so it does not read images.

OpenAI presents it as a small model for science, math and coding, which makes it a lighter option for text-only reasoning work.

## Pricing

o3-mini is priced at $1.10 per 1M input tokens and at $4.40 per 1M output tokens. Cached input reads are priced at $0.55 per 1M tokens.

o3-mini is available through RealRelay's OpenAI-compatible API.

## Use cases

Use o3-mini for text-only reasoning in science, math and coding, such as checking a derivation, writing and debugging a function or solving a structured quantitative problem.

Tool calling and structured output let it sit inside an automated pipeline, calling a function to look up data and returning an answer that other code can parse.

## 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/o3-mini", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is o3-mini?

o3-mini is a deprecated, small OpenAI reasoning model optimized for science, math and coding tasks, with text input and a 200,000-token context window.

### How much does o3-mini cost?

o3-mini is priced at $1.10 per 1M input tokens and at $4.40 per 1M output tokens. Cached input reads are priced at $0.55 per 1M tokens.

### What is the context window and maximum output of o3-mini?

o3-mini has a 200,000-token context window and can generate up to 100,000 output tokens.

### What inputs and outputs does o3-mini support?

o3-mini accepts text input and returns text.

### What capabilities does o3-mini support?

o3-mini supports reasoning, tool calling and structured output.

### When was o3-mini released?

o3-mini was released on January 31, 2025.

### How do I call o3-mini via the API?

Call o3-mini through RealRelay's OpenAI-compatible API using the model ID openai/o3-mini.