Model

GPT-4.1

CLOSED

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

API-only coding-focused flagship with a 1,047,576-token context window and June 2024 knowledge cutoff.

ReasoningCodingVisionFunction callingTool useAgentic

1466.6

Elo · rank #129

Parameters

Undisclosed

Active params

—

Context

1M tokens

Architecture

Dense transformer (size undisclosed; non-reasoning)

License

Proprietary

Languages

—

API price (in/out)

$2 / $8

Modalities

text · vision

Benchmark results

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

Aider PolyglotCoding52.4%#24

best: Claude Opus 4.5 · 89.4%

AIMEMath48.1%#120

best: GPT-5.2 · 100.0%

GAIAAgents49.7%#7

best: MiniMax-M2 · 75.7%

GPQA DiamondReasoning66.3%#136

best: GPT-5.6 · 94.6%

IFEvalReasoning87.4%#41

best: Gemma 4 26B A4B · 98.5%

MathVistaVision72.2%#21

best: Seed 2.1 Pro · 90.7%

MMLUKnowledge90.2%#8

best: OpenAI o3 · 92.9%

MMMLUKnowledge87.3%#14

best: Gemini 3.1 Pro · 92.6%

MMMUVision74.8%#36

best: Claude Fable 5 · 89.3%

SWE-bench VerifiedCoding54.6%#86

best: Claude Fable 5 · 95.0%

Video-MMEVision72.0%#17

best: Seed 2.1 Pro · 89.2%

Run it locally

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

Input / M tok

Output / M tok

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 APIAvailable via OpenAI API

API price $2/$8 · each benchmark row carries its own source badge (see methodology)