Qwen3.5-27B
Qwen3.5-27B is a vision-language model developed by Qwen that supports text, image, and video inputs. It features a linear attention mechanism designed to balance inference speed with performance, and it includes native support for reasoning and tool calling.
Qwen3.5-27B specs and pricing
- Provider: Qwen
- Released: February 25, 2026
- Context window: 262K tokens
- Max output: 82K tokens
- Input: text, images, video
- Output: text
- Price: $0.26 input / $2.60 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Qwen3.5-27B is good at
- Analyzing visual content like images and videos
- Complex tasks requiring multi-step reasoning
- Applications that benefit from integrated tool usage
To-dos to try with Qwen3.5-27B
- Upload a video of a meeting and summarize the key decisions made
- Provide an image of a handwritten flowchart and convert it into a structured text description
- Use tool calling to search for external data and synthesize it into a report
FAQ
- What types of media can I provide to Qwen3.5-27B? The model accepts text, images, and video as input.
- Does this model support reasoning and tool calling? Yes, Qwen3.5-27B is built with native capabilities for both reasoning processes and tool calling.
- How much does Qwen3.5-27B cost? Qwen3.5-27B costs $0.26 per million input tokens and $2.60 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.09 credits ($1 = 100 credits).
- What is the context window of Qwen3.5-27B? Qwen3.5-27B can read up to 262K tokens at once and write up to 82K tokens in one reply.
- Can I use Qwen3.5-27B without coding? Yes. In todo.is you pick Qwen3.5-27B 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.