Qwen: Qwen3.5-35B-A3B chat
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.
Capabilities
Context Window 262k tokens
Max Output 65k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.16
Output $1.30
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p