Compare AI models

Specifications
Parameters
—>1T
Context window
400k256k
API pricing
Input price
$0.75—
Output price
$4.50—
Cached input price
$0.075—
Cheapest input
$0.375OpenAI—
Cheapest output
$2.25OpenAI—
$375OpenAI list price—
Benchmarks
Humanity's Last Exam · with tools
41.5%49.8%
GPQA Diamond
88%87.4%
Overview
CompanyOpenAIQwen
Release dateMar 17 2026Jan 26 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-5.4 mini and Qwen3-Max-Thinking are evenly matched across the 2 benchmarks they both report (Humanity's Last Exam, GPQA Diamond). Only GPT-5.4 mini has a verified first-party price for an available API: $0.75 per million input tokens and $4.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3-Max-Thinking. Qwen3-Max-Thinking shipped 50 days before GPT-5.4 mini, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.4 mini) vs 256k (Qwen3-Max-Thinking).

On Humanity's Last Exam · with tools, Qwen3-Max-Thinking leads at 49.8% vs GPT-5.4 mini at 41.5%. On GPQA Diamond, GPT-5.4 mini leads at 88% vs Qwen3-Max-Thinking at 87.4%.