Hub/Models/qwen/qwen3.5-35b-a3b
qwentext + image + video → text

Qwen: Qwen3.5-35B-A3B

Canonical ID: qwen/qwen3.5-35b-a3b

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.14
Input
Completion Output (1M Tokens)
$1.00
Output
Prompt KV-Cache Read (1M Tokens)
$0.05
Cached
Context Window Capacity
256k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p