Qwen3-Max
Alibaba · Released 24 Sep 2025 · qwen3-max
$1.20
Input price / 1M tokens
#26 of 61, cheapest first
$6.00
Output price / 1M tokens
#32 of 61, cheapest first
262K
Context window
#54 of 71
63
Output tokens / second
#49 of 61
Summary
Qwen3-Max is a proprietary model from Alibaba, released on 24 Sep 2025.
At $1.20 input and $6.00 output per million tokens, it is #26 of 61 on input price, cheapest first.
Its 262K-token context window ranks #54 of 71.
Measured output speed is 63 tokens per second, #49 of 61.
Qwen 3 series Max model with thinking and non-thinking modes, upgraded for agent programming and tool use in the 2026-01-23 snapshot. Being retired on Qwen Cloud on 10 Oct 2026.
Benchmarks · 0 reported
No benchmark score we could source for this model. We show scores only with a source link.
Sources
- price tiers, batch discount: alibabacloud.com/help/en/model-studio/model-pricing, checked 2 Oct 2026
- context, max output, cache prices, retirement date: qwencloud.com/models/qwen3-max, checked 2 Oct 2026
- retirement notice: docs.qwencloud.com/changelog/model-deprecations/mainline-models, checked 2 Oct 2026
- release date: alibabacloud.com/help/en/model-studio/newly-released-models, checked 2 Oct 2026
- output speed: artificialanalysis.ai/models/qwen3-max, checked 2 Oct 2026
Building on Qwen3-Max?
Get the architecture right before the bill arrives.
We size caching, routing and fallbacks for your workload on a free call, and tell you where a cheaper model is good enough.