GPT-4.1 mini

A small, fast, and capable model for high-volume workloads.

A smaller GPT-4.1 language-model release from OpenAI for API use, positioned for lower latency and cost than GPT-4.1.

Pricing

Official site · Nov 1, 2026, 6:26 AM

Input / 1M

$0.40

Output / 1M

$1.60

Cached input / 1M

$0.10

USD per 1M text tokens. Input $0.40, cached input $0.10, output $1.60.

OpenAI's official model documentation lists per-1M-token text rates; model status is marked deprecated. Recorded standard listed rates.

Context window

1,047,576 tokens

Arena ranking

Benchmarkable

Yes

Model level

release

MMLU Pro

0.78

GPQA

0.66

HLE

0.05

LiveCodeBench

0.48

MATH-500

0.93

AIME

0.43

AIME 2025

0.46

IFBench

0.38

LCR

0.44

TerminalBench Hard

0.08

TAU2

0.53

0 linked stories

No linked stories yet.