Back to all models
qwen

Qwen: Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

qwen/qwen3.5-397b-a17b

Context Size

256K

Input Price

57,750 pts/M

Output Price

367,500 pts/M


Architecture

Text
Image
Video

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Details

TokenizerQwen3
Provider Context131.072K tokens
ModeratedNo
CreatedFeb 16, 2026