Compare AI models

Specifications
Context window
1M—
API pricing
Input price
$2.00—
Output price
$8.00—
Cached input price
$0.50—
Cheapest input
$2.00Azure—
Cheapest output
$8.00Azure—
$800OpenAI list price—
Benchmarks
HumanEval
94.5%85.7%
MMLU
90.2%86.2%
MathVista
72.2%68.1%
MMMU
74.8%63.2%
Overview
CompanyOpenAISpaceXSI
Release dateApr 14 2025Aug 13 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.1 leads Grok‑2 mini on 4 of the 4 benchmarks they both report (HumanEval, MMLU, MathVista, MMMU). Only GPT-4.1 has a verified first-party price for an available API: $2.00 per million input tokens and $8.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Grok‑2 mini. Grok‑2 mini shipped 244 days before GPT-4.1, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, GPT-4.1 leads at 94.5% vs Grok‑2 mini at 85.7%. On MMLU, GPT-4.1 leads at 90.2% vs Grok‑2 mini at 86.2%. On MathVista, GPT-4.1 leads at 72.2% vs Grok‑2 mini at 68.1%. On MMMU, GPT-4.1 leads at 74.8% vs Grok‑2 mini at 63.2%.