Hub/Models/qwen/qwen3.8-2.4t-a95b
qwentext → text

Qwen: Qwen3.8 2.4T A95B

Canonical ID: qwen/qwen3.8-2.4t-a95b

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
Strategy & Ops44.4 / 100
Finance & Accounting41.3 / 100
Legal Index37 / 100
Healthcare & Medical39 / 100

Token Pricing & Economics

Prompt Input (1M Tokens)
$2.00
Input
Completion Output (1M Tokens)
$6.00
Output
Prompt KV-Cache Read (1M Tokens)
$0.25
Cached
Context Window Capacity
1,024k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p