Qwen3.5-35B-A3B
Qwen3.5-35B-A3B is a native vision-language model developed by Qwen that utilizes a hybrid architecture combining linear attention and a sparse mixture-of-experts model. It is designed for efficient processing of text, image, and video inputs with a large context window and built-in reasoning and tool-calling capabilities.
Qwen3.5-35B-A3B specs and pricing
- Provider: Qwen
- Released: February 25, 2026
- Context window: 262K tokens
- Max output: 82K tokens
- Input: text, images, video
- Output: text
- Price: $0.14 input / $1.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Qwen3.5-35B-A3B is good at
- Analyzing complex video content
- Reasoning tasks involving multi-modal data
- Automated workflows requiring tool integration
To-dos to try with Qwen3.5-35B-A3B
- Analyze this 30-minute video file and summarize the key events chronologically.
- Examine these ten product images and draft a comparison table based on their visual features.
- Use the provided tool to search for current market data and incorporate it into a written report.
FAQ
- What types of media can this model process? Qwen3.5-35B-A3B is capable of processing text, images, and video inputs.
- Does this model support advanced problem-solving features? Yes, the model includes native reasoning capabilities and supports tool calling for complex tasks.
- How much does Qwen3.5-35B-A3B cost? Qwen3.5-35B-A3B costs $0.14 per million input tokens and $1.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.53 credits ($1 = 100 credits).
- What is the context window of Qwen3.5-35B-A3B? Qwen3.5-35B-A3B can read up to 262K tokens at once and write up to 82K tokens in one reply.
- Can I use Qwen3.5-35B-A3B without coding? Yes. In todo.is you pick Qwen3.5-35B-A3B 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.