Compare AI models

Specifications
Parameters
—0.8B/2B/4B/9B
Context window
400k256k
API pricing
Input price
$0.20—
Output price
$1.25—
Cached input price
$0.02—
Cheapest input
$0.10OpenAI—
Cheapest output
$0.625OpenAI—
$103OpenAI list price—
Benchmarks
GPQA Diamond
82.8%81.7%
OSWorld-Verified
39%41.8%
MMMU-Pro
66.1%70.1%
Overview
CompanyOpenAIQwen
Release dateMar 17 2026Mar 2 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Small leads GPT-5.4 nano on 2 of the 3 benchmarks they both report (GPQA Diamond, OSWorld-Verified, MMMU-Pro). Only GPT-5.4 nano has a verified first-party price for an available API: $0.20 per million input tokens and $1.25 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Small. Qwen3.5 Small shipped 15 days before GPT-5.4 nano, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.4 nano) vs 256k (Qwen3.5 Small). GPT-5.4 nano is closed, while Qwen3.5 Small is open weight.

On GPQA Diamond, GPT-5.4 nano leads at 82.8% vs Qwen3.5 Small at 81.7%. On OSWorld-Verified, Qwen3.5 Small leads at 41.8% vs GPT-5.4 nano at 39%. On MMMU-Pro, Qwen3.5 Small leads at 70.1% vs GPT-5.4 nano at 66.1%.