qwen

Qwen3 Max pricing & benchmarks

Released Sep 23, 2025 · served by 1 provider

Input / 1M tokens$0.780
Output / 1M tokens$3.90
Context window262K
Cached input$0.156
1M in + 300K out$1.95

What Qwen3 Max is

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...

Providers and prices for Qwen3 Max

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 $0.780 $3.90 262K 100.0%

Qwen3 Max benchmark results

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

CategoryArenaRankEloWin rate
asciiart models #38 1166 47.2%
svg models #64 1061 37.3%
gamedev models #67 1151 43.9%
3d models #73 1131 43.5%
dataviz models #76 1128 41%
uicomponent models #76 1114 40.2%
codecategories models #77 1140 44%
website models #77 1144 44.5%

FAQ

How much does the Qwen3 Max API cost?

$0.780 per 1M input tokens and $3.90 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.95.

Is Qwen3 Max free?

No. It is a paid model starting at $0.780 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 Max?

Alibaba at $0.780 input / $3.90 output per 1M tokens.

Can I self-host Qwen3 Max?

No. Qwen3 Max is closed-weight and only available through hosted APIs.