Back to all models
qwen
qwenQwen: 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...
qwen/qwen3.8-2.4t-a95b
Context Size
1,048.576K
Input Price
300,000 pts/M
Output Price
900,000 pts/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerQwen
Max Completion262,144 tokens
Provider Context1,000K tokens
ModeratedNo
CreatedAug 12, 2026