Qwen3.5 Plus 2026-02-15
Qwen3.5 Plus is a multimodal AI model developed by Qwen that processes text, images, and video inputs. It utilizes a hybrid architecture combining linear attention with sparse mixture-of-experts to support complex reasoning and tool-calling tasks.
Qwen3.5 Plus 2026-02-15 specs and pricing
- Provider: Qwen
- Released: February 16, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text, images, video
- Output: text
- Price: $0.26 input / $1.56 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Qwen3.5 Plus 2026-02-15 is good at
- Analyzing long-form documents and visual media
- Complex reasoning tasks requiring tool integration
- Processing large-scale data inputs efficiently
To-dos to try with Qwen3.5 Plus 2026-02-15
- Upload a long video file and summarize the key events and timestamps.
- Provide a complex technical diagram and ask the model to explain the underlying logic.
- Use the tool-calling feature to extract structured data from a series of images.
FAQ
- What types of media can Qwen3.5 Plus process? This model is capable of ingesting text, images, and video files as input.
- What is the core architecture of this model? It is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models.
- How much does Qwen3.5 Plus 2026-02-15 cost? Qwen3.5 Plus 2026-02-15 costs $0.26 per million input tokens and $1.56 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.95 credits ($1 = 100 credits).
- What is the context window of Qwen3.5 Plus 2026-02-15? Qwen3.5 Plus 2026-02-15 can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Qwen3.5 Plus 2026-02-15 without coding? Yes. In todo.is you pick Qwen3.5 Plus 2026-02-15 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.