Hub/Models/qwen/qwen3.5-397b-a17b
qwentext + image + video → text

Qwen: Qwen3.5 397B A17B

Canonical ID: qwen/qwen3.5-397b-a17b

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

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

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.45
Input
Completion Output (1M Tokens)
$3.00
Output
Prompt KV-Cache Read (1M Tokens)
$0.22
Cached
Context Window Capacity
256k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p