Qwen3.6 35B A3B
Qwen3.6 35B A3B is a multimodal model developed by Alibaba Cloud that utilizes a sparse mixture-of-experts architecture. It supports text, image, and video inputs and features a large context window of 262,144 tokens. The model is designed for complex tasks requiring reasoning and tool-calling capabilities.
Qwen3.6 35B A3B specs and pricing
- Provider: Qwen
- Released: April 27, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text, images, video
- Output: text
- Price: $0.10 input / $0.90 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Qwen3.6 35B A3B is good at
- Analyzing long documents or video content
- Complex reasoning tasks requiring tool usage
- Multimodal data processing involving images and video
To-dos to try with Qwen3.6 35B A3B
- Upload a long video file and summarize the key events that occur in the first ten minutes.
- Provide a set of images and ask the model to extract and organize the text data found within them.
- Use the tool-calling feature to process a complex query that requires searching through a large text document.
FAQ
- What types of media can this model process? Qwen3.6 35B A3B is a multimodal model capable of processing text, images, and video inputs.
- Who developed this model? This model is an open-weight release provided by Alibaba Cloud.
- How much does Qwen3.6 35B A3B cost? Qwen3.6 35B A3B costs $0.10 per million input tokens and $0.90 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.41 credits ($1 = 100 credits).
- What is the context window of Qwen3.6 35B A3B? Qwen3.6 35B A3B can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Qwen3.6 35B A3B without coding? Yes. In todo.is you pick Qwen3.6 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.