| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | Identical contract to 1 other entry | api_5e05efff |
| Context and output | 262,144 context · 65,536 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | None recorded yet | – |
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...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":0.6,"top_p":0.95,"top_k":20,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Qwen: Qwen3.5 397B A17B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
