/ Models

Language models

Qwen: Qwen3.8 2.4T A95B

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...

Maker
Qwen
Context window
1M
Max output
52K
Input / 1M
$2
Output / 1M
$6
1M in + 1M out
$8

Everything else

Max output52K
Input / 1M$2
Output / 1M$6
Cache read / 1M$0.2
Cache write / 1M
1M in + 1M out$8
Takestext
Returnstext
Toolsyes
Reasoningalways on · xhigh, medium, low
Open weightsyes
Released2026-08-12
Knowledge cutoff
Retires
Catalog idqwen/qwen3.8-2.4t-a95b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models