# GPT-4o-mini

Ultra-affordable small model with vision — best for high-volume, cost-sensitive tasks.

## Overview

- **Provider:** OpenAI
- **Model ID:** `gpt-4o-mini`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gpt-4o-mini
- **Version:** 4o-mini
- **Knowledge cutoff:** 2023-10
- **Best for:** High-volume tasks, cost optimization, fast inference, simple chat and vision

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.15 / 1M tokens |
| Output | $0.6 / 1M tokens |
| Cache read | $0.075 / 1M tokens |
| Cache write (5 minutes) | $0.15 / 1M tokens |

## Specifications

- **Context window:** 128K
- **Maximum output:** 16K
- **Typical latency:** 6 ms
- **Released:** 2024-07

## Capabilities

- chat
- tool_use
- vision
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gpt-4o-mini"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gpt-4o-mini.