Qwen: Qwen3.5 Plus 2026-02-15

qwen/qwen3.5-plus-02-15

Created Feb 16, 20261,000,000 context

$0.40/M input tokens$2.40/M output tokens

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 task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.

Qwen: Qwen3.5 Plus 2026-02-15

qwen/qwen3.5-plus-02-15

Created Feb 16, 20261,000,000 context

$0.40/M input tokens$2.40/M output tokens

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 task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.

Recent activity on Qwen3.5 Plus 2026-02-15

Total usage per day on OpenRouter

Prompt

76.4M

Completion

4.67M

Reasoning

3.25M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.