Model ID
qwen-3-8-27b
Qwen 3.8 27B
Model Overview
Section titled “Model Overview”Publisher
Qwen
Model Specifications
Section titled “Model Specifications”| Specification | Value |
|---|---|
| API ID | qwen-3-8-27b |
| Parameter Count | 27B |
Capabilities
Section titled “Capabilities”| Capability | Supported |
|---|---|
Chat completions (/v1/chat/completions) |
Yes |
| Tool / function calling | Yes |
Structured output (response_format) |
Yes |
Responses API (/v1/responses) |
Yes |
Anthropic Messages API (/v1/messages) |
Yes |
Image input (image_url) |
Yes |
Video input (file) |
Yes |
| Reasoning | Yes |
Qwen 3.8 27B is the multimodal model in the catalog: it accepts image (image_url) and video (file) content parts alongside text. See Multi Modality for request examples.
Reasoning
Section titled “Reasoning”| Property | Value |
|---|---|
| Reasoning supported | Yes |
| Toggleable | Yes |
| How to toggle | chat_template_kwargs with {"enable_thinking": true} or {"enable_thinking": false} |
| Reasoning effort levels | low, medium, xhigh (default) |
| How to set effort | reasoning_effort parameter |
Set chat_template_kwargs.enable_thinking to true to turn reasoning on or false to turn it off. When reasoning is enabled, control the depth by setting reasoning_effort to "low", "medium", or "xhigh" (default). none also disables reasoning on this model. A level this model does not support falls back to its default effort (xhigh).
For a full example, see Reasoning Example.