Chat

GPT-5.4 Mini

OpenAI

GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. With a 400K context window and 128K max output, it supports text and image inputs with reasoning token support. It delivers strong performance in coding, computer use, and sub-agent scenarios while maintaining significantly lower cost and latency than the full GPT-5.4.

Try Now

Capabilities

Thinking

Tool Use

Image Input

Image Generation

PDF Input

Example Use Cases

High-volume coding and agent tasks at lower cost

Fast multimodal processing with reasoning

Sub-agent or classification workloads at scale

Technical Specifications

Context Window

400,000 tokens

Max Output

128,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.75

Non-Reasoning Output

$4.50

Cache Read Input

$0.075

Tool Costs (per 1K calls)

Web Search

$10

Code Execution

$30

Image Generation

$400