Qwen3.5 397B A17B
Qwen3.5 397B-A17B is a multimodal model developed by Qwen that processes text, images, and video. It utilizes a hybrid architecture combining linear attention and sparse mixture-of-experts to support reasoning and tool-calling capabilities.
Qwen3.5 397B A17B specs and pricing
- Provider: Qwen
- Released: February 16, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text, images, video
- Output: text
- Price: $0.50 input / $3.60 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Qwen3.5 397B A17B is good at
- Analyzing complex video content
- Reasoning-heavy tasks requiring tool integration
- Processing large documents or visual data sets
To-dos to try with Qwen3.5 397B A17B
- Analyze this 30-minute video file and summarize the key events chronologically.
- Read these five technical diagrams and explain the differences in their architecture.
- Use a search tool to find current data and create a report based on this uploaded document.
FAQ
- What types of media can this model process? The model is capable of ingesting and analyzing text, images, and video files.
- Does this model support complex problem solving? Yes, the model is designed with native reasoning capabilities and supports tool-calling for advanced tasks.
- How much does Qwen3.5 397B A17B cost? Qwen3.5 397B A17B costs $0.50 per million input tokens and $3.60 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.9 credits ($1 = 100 credits).
- What is the context window of Qwen3.5 397B A17B? Qwen3.5 397B A17B can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Qwen3.5 397B A17B without coding? Yes. In todo.is you pick Qwen3.5 397B A17B 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.