qwen Open weights Reasoning

Qwen3 235B A22B pricing & benchmarks

Released Apr 28, 2025 · served by 1 provider

Input / 1M tokens$0.455
Output / 1M tokens$1.82
Context window131K
Cached input
1M in + 300K out$1.00

What Qwen3 235B A22B is

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Providers and prices for Qwen3 235B A22B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Alibabacheapest $0.455 $1.82 131K 100.0%

Qwen3 235B A22B benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
dataviz models #93 1030 41%
uicomponent models #94 999 39.1%
website models #98 1055 40.5%
codecategories models #99 1033 38.3%
3d models #101 916 24.5%
gamedev models #103 985 33.1%

FAQ

How much does the Qwen3 235B A22B API cost?

$0.455 per 1M input tokens and $1.82 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.00.

Is Qwen3 235B A22B free?

No. It is a paid model starting at $0.455 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 235B A22B?

Alibaba at $0.455 input / $1.82 output per 1M tokens.

Can I self-host Qwen3 235B A22B?

Yes — weights are published as Qwen/Qwen3-235B-A22B on Hugging Face, so you can run it on your own hardware.