| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | No other entry shares this exact contract | api_b840156f |
| Context and output | 1,000,000 context · 65,536 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | Alibaba | measured 21 August 2026 |
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 10 prompt tokens.
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
Supported parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Qwen: Qwen3.6 Plus: 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.
