Qwen
Qwen: Qwen3.8 2.4T A95B
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 suited for coding, research, complex reasoning, and agentic workflows.
Input
$2
/ 1M tokens
Output
$6
/ 1M tokens
Context window
1.05M
tokens
Limits
Context
1,048,576
tokens
Max output
131,072
13% of the context window
Parameters
2,446,182,725,504
Model facts
Author
Qwen
Tokenizer
Qwen
Modality
Text -> Text
License
Other
Created
Aug 12, 2026
Hugging Face
Qwen/Qwen3.8-2.4T-A95B
Default generation parameters
temperature
1
top_k
20
top_p
0.95
Reasoning
RequiredDefault XhighXhighMediumLow
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin pPresence penaltyReasoningReasoning effortRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p
Capability scores
50.1
Agentic index
Better than 85% of models compared
71.9
Coding index
Better than 81% of models compared
39.9
Intelligence index
Better than 84% of models compared