# o4-mini

> A deprecated, fast and cost-efficient OpenAI reasoning model for math, science, coding and visual tasks.

## Key facts

- Model author: OpenAI
- Input: $1.10 per 1M tokens
- Output: $4.40 per 1M tokens
- Cached input: $0.275 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 100,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: fine_tuning, reasoning, structured_output, tools, vision
- Released: 2025-04-16
- Knowledge cutoff: Jun 01, 2024
- Model IDs: `openai/o4-mini`
- Model page: https://www.realrelay.ai/model/openai/o4-mini

## Overview

o4-mini is a fast, cost-efficient reasoning model from OpenAI. OpenAI documents it for math, science, coding and visual reasoning tasks. It accepts text and image input, returns text, supports tool calling and structured output, and has a 200,000-token context window. 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 and image input and returns text. Its knowledge cutoff is June 1, 2024, and it was released on April 16, 2025.

## Capabilities

o4-mini supports reasoning, tool calling, structured output and image understanding. It reads text and image input together and returns text.

OpenAI describes it as fast and cost-efficient, so it fits reasoning work that runs often and where each call should stay light, while still handling visual input.

## Pricing

o4-mini is priced at $1.10 per 1M input tokens and at $4.40 per 1M output tokens. Cached input reads are priced at $0.275 per 1M tokens.

o4-mini is available through RealRelay's OpenAI-compatible API.

## Use cases

Use o4-mini for frequent reasoning tasks in math, science and coding, such as grading step-by-step solutions, explaining code or answering data questions from a chart.

Image input and tool calling let it read a screenshot or graph and then call a function to fetch the numbers it needs, returning structured output for the next step.

## 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/o4-mini", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is o4-mini?

o4-mini is a deprecated, fast and cost-efficient OpenAI reasoning model with tool calling, image input and a 200,000-token context window.

### How much does o4-mini cost?

o4-mini is priced at $1.10 per 1M input tokens and at $4.40 per 1M output tokens. Cached input reads are priced at $0.275 per 1M tokens.

### What is the context window and maximum output of o4-mini?

o4-mini has a 200,000-token context window and can generate up to 100,000 output tokens.

### What inputs and outputs does o4-mini support?

o4-mini accepts text and image input and returns text.

### What capabilities does o4-mini support?

o4-mini supports reasoning, tool calling, structured output and image understanding.

### When was o4-mini released?

o4-mini was released on April 16, 2025.

### How do I call o4-mini via the API?

Call o4-mini through RealRelay's OpenAI-compatible API using the model ID openai/o4-mini.