# GPT-5.4 Mini

Compact reasoning model with extended 400K context. Balanced cost-performance for reasoning tasks.

## Overview

- **Provider:** OpenAI
- **Model ID:** `gpt-5.4-mini`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/gpt-5.4-mini
- **Version:** 5.4-mini
- **Best for:** Cost-effective reasoning, extended context processing, balanced intelligence-cost ratio

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.75 / 1M tokens |
| Output | $4.5 / 1M tokens |
| Cache read | $0.075 / 1M tokens |
| Cache write (5 minutes) | $0.75 / 1M tokens |

## Specifications

- **Context window:** 400K
- **Maximum output:** 128K
- **Typical latency:** 10 ms
- **Released:** 2026-06

## Capabilities

- chat
- tool_use
- vision
- coding

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "gpt-5.4-mini"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/gpt-5.4-mini.