AI model · Qwen
Qwen3.8 2.4T A95B
Model ID: qwen/qwen3.8-2.4t-a95b
- Input
- $2 per 1M tokens
- Output
- $6 per 1M tokens
- Context
- 1M tokens at once
- Max output
- 131K tokens per reply
- Released
- 12 Aug 2026 Qwen
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Sources
- Qwen: Qwen3.8 2.4T A95B on OpenRouter — read 2 Oct 2026