Model

GPT-4.1 mini

CLOSED

OpenAI · GPT-4.1 family · released Apr 14, 2025

Balanced mid-tier of the 4.1 family with a 1M-token context window, vision, and strong instruction-following.

ReasoningCodingVisionFunction callingTool useAgentic

1285.7

Elo · rank #160

Parameters

Undisclosed

Active params

—

Context

1M tokens

Architecture

Dense transformer (size undisclosed; non-reasoning)

License

Proprietary

Languages

—

API price (in/out)

$0.4 / $1.6

Modalities

text · vision

Benchmark results

Bar shows position within the tracked field; marker = field best

AIMEMath49.6%#118

best: GPT-5.2 · 100.0%

DROPReasoning81#22

best: Hunyuan-T1 · 93.1

GPQA DiamondReasoning65.0%#148

best: GPT-5.6 · 94.6%

HumanEvalCoding93.8%#8

best: Claude Opus 4.5 · 99.4%

IFEvalReasoning84.1%#69

best: Gemma 4 26B A4B · 98.5%

MATH-500Math81.4%#66

best: GPT-5 · 99.4%

MathVistaVision73.1%#19

best: Seed 2.1 Pro · 90.7%

MGSMMath88.2%#17

best: OpenAI o4-mini · 93.7%

MMLUKnowledge87.5%#29

best: OpenAI o3 · 92.9%

MMMLUKnowledge78.5%#29

best: Gemini 3.1 Pro · 92.6%

MMMUVision72.7%#46

best: Claude Fable 5 · 89.3%

SimpleQAKnowledge16.8%#26

best: GPT-4.5 · 62.5%

SWE-bench VerifiedCoding23.6%#112

best: Claude Fable 5 · 95.0%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

$0.4

Output / M tok

$1.6

GPT-4.1 family

Elo progression across releases

GPT-4.1Apr 20251466.6 GPT-4.1 miniApr 20251285.7 GPT-4.1 nanoApr 2025887.9

Resources

DOCSdevelopers.openai.com/api/docs/models/gpt-4.1-mini APIAvailable via OpenAI API

API price $0.4/$1.6 · each benchmark row carries its own source badge (see methodology)