Qwen3.6 35B A3B
Qwen3.6 35B A3B is a large language model made by Qwen, added to the catalog on 27 Apr 2026. It has a context window of 262,144 tokens and costs $0.10 per 1M input tokens and $0.90 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: summarizing video content in text, analyzing documents with visual references and extracting structured information from mixed inputs.
Price checked ยท source: OpenRouter
What Qwen3.6 35B A3B is
Qwen3.6 35B A3B is an open-weight multimodal model from Alibaba Cloud. It accepts text, images, and video as input and produces text. Its listed context length is 262,144 tokens, and its maximum output is 235,929 tokens. This gives it room to work with lengthy prompts and substantial source material in a single context, while the output limit allows for long responses when the task calls for them.
Alongside text responses, the model supports reasoning, tool use, structured outputs, and response-format controls. These options suit workflows that need a response in a defined structure or involve tools. Image and video inputs let users include visual material in text-based prompts; the output remains text, rather than generated images or video. The catalog does not specify particular image or video limits, so those details should not be assumed.
With its long context, multimodal input, and text output, Qwen3.6 35B A3B may suit tasks such as analyzing documents alongside visual references, summarizing video content in text, and extracting organized information from mixed inputs. It can also support text-focused reasoning and drafting, with structured output options for results that need a predictable format. The model is described as having 35 billion total parameters and 3 billion active parameters per token; the catalog does not specify a performance level or guarantee a particular result.
Key features
- Accepts text, image, and video inputs and produces text
- Has a context length of 262,144 tokens
- Supports tool use and reasoning
- Supports structured outputs and response-format controls
- Has a maximum output length of 235,929 tokens
Typical uses
- Summarizing video content in text
- Analyzing documents with visual references
- Extracting structured information from mixed inputs
- Reasoning over long text prompts
- Drafting text in a defined output format
Qwen3.6 35B A3B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.10 |
| Output, per 1M tokens | $0.90 |
| Cached input read, per 1M tokens | $0.025 |
No price change since it was added on 27 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0003 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0032 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0048 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.016 |
Qwen3.6 35B A3B specifications
| Model id | qwen/qwen3.6-35b-a3b |
|---|---|
| Version | qwen3.6-35b-a3b-20260415 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 27 Apr 2026 |
| Input types | text, image, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Qwen3.6 35B A3B yet.
Compare Qwen3.6 35B A3B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.