GPT-4o Mini

Language modelPrevious generationCard summarized

Fast, affordable small model for focused tasks

Active (legacy)● Re-checked 12 Oct 2026 · 34 facts · 1 correction · 1 unconfirmedSource: GPT-4o mini model page (OpenAI API docs); no separate system card published

Use it via API

$94.50 /month

$1.89 per 1K requests

RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change

Code example Compare

Where to call it

OpenAI APIgpt-4o-mini

Supports

Image input
Streaming
Structured outputs
Tool calling
Web search
Prompt caching
Batch API
Fine-tuning

Full feature support

Good for

Fast, low-cost focused tasks
Fine-tuning, including distilling outputs from a larger model such as GPT-4o
Structured Outputs from text and image inputs

Overview

OpenAI · 15mini

GPT-4o mini

Fast, affordable small model for focused tasks

Cost: $0.15 in
Context: 128K

Input / output: $0.15 / $0.60
Max output: 16K
Knows up to: October 2023
Released: 18 Jul 2024

OpenAI published no separate system card for GPT-4o mini. The model page describes a fast, affordable small model for focused tasks that takes text and images and returns text, including Structured Outputs. OpenAI calls it ideal for fine-tuning and for distilling outputs from a larger model such as GPT-4o. The GPT-4o System Card reports its accuracy in several underrepresented languages. model page; GPT-4o System Card p.24–25

gpt-4o-mini

Input / output per 1M: $0.15 / $0.60
Context window: 128K
Max output: 16K
Knows up to: October 2023
Reasoning: None
Weights: Closed

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses OpenAI's GPT-4o mini model page (OpenAI API docs); no separate system card published. Every claim carries its source page.