qwentext + image + video → text
Qwen: Qwen3.5 Plus 2026-02-15
Canonical ID: qwen/qwen3.5-plus-02-15
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.26
Completion Output (1M Tokens)
Output$1.56
Prompt KV-Cache Read (1M Tokens)
Cached$0.00
Context Window Capacity
Context976.563k tokens
Supported Parameters & Features
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p