Qwen3.8 2.4T A95B

Open-weights release of the Qwen3.8 flagship (2.4T MoE, ~95B active); thinking always on with reasoning_effort low/medium/xhigh. The hosted Qwen 3.8 Max (vision, non-thinking, 1M default context) is Alibaba-only.

Model overview

Model ID: alibaba/qwen3.8-2.4t-a95b
Provider: alibaba
Type: language
Context window: 262,144 tokens
Max output tokens: 131,072

Tags: reasoning, tool-use, implicit-caching, vision

Model pricing

Metric	Value
`Input tokens (/1M)`	`$2.00`
`Output tokens (/1M)`	`$6.00`
`Image generation`	`n/a`
`Cached input read (/1M)`	`$0.20`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix