GPT-4.1 Mini

Language modelPrevious generationCard summarized

Smaller, faster version of GPT-4.1

Active (legacy)● Re-checked 12 Oct 2026 · 30 facts · 1 correction · 1 unconfirmedSource: GPT-4.1 mini model page and GPT-4.1 Prompting Guide (OpenAI Cookbook); no system card published

Use it via API

$234 /month

$4.68 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-4.1-mini

Supports

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

Full feature support

Good for

Instruction following and tool calling at low latency
Long inputs up to a 1M-token context window
Generating file diffs (GPT-4.1 family trained on the V4A format)

Overview

OpenAI · 13mini

GPT-4.1 mini

Smaller, faster version of GPT-4.1

Cost: $0.40 in
Context: 1M

Input / output: $0.40 / $1.60
Max output: 32K
Knows up to: June 2024
Released: 14 Apr 2025

OpenAI published no system card for GPT-4.1 mini. The model page describes a smaller, faster version of GPT-4.1 that excels at instruction following and tool calling, with a 1M-token context window and low latency without a reasoning step. OpenAI recommends starting with GPT-5 mini for more complex tasks. model page

gpt-4.1-mini

Input / output per 1M: $0.40 / $1.60
Context window: 1M
Max output: 32K
Knows up to: June 2024
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-4.1 mini model page and GPT-4.1 Prompting Guide (OpenAI Cookbook); no system card published. Every claim carries its source page.