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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Alibaba | $0.260 | $1.56 | 1M | 100% |
Qwen3.5 Plus 2026-02-15 costs $0.260 per million input tokens and $1.56 per million output tokens via OpenRouter, making it 118th cheapest of 298 paid models.
Qwen3.5 Plus 2026-02-15 generates around 36 tokens per second with 1.8s time-to-first-token (p50), the 211th fastest tracked model.
Qwen3.5 Plus 2026-02-15 supports a 1M-token context window and can output up to 66K tokens. It accepts text, image, video input.