Models
Qwen: Qwen3.8 27B
Capabilities, limits, pricing, and endpoints for qwen/qwen3.8-27b.
Canonical model ID: qwen/qwen3.8-27b
Qwen 3.8 27B for writing, reasoning, coding, and image understanding.
Runtime metadata¶
This table is generated from public model metadata. Readiness and capacity are refreshed from GET /v1/models on page load.
| Property | Value |
|---|---|
| Kind | chat |
| Input | text, image |
| Output | text |
| Context | 262,144 tokens |
| Maximum output | 32,768 tokens |
| Supported endpoints | /v1/chat/completions, /v1/responses, /v1/messages |
| Capabilities | tool_calling, json_mode, structured_outputs, reasoning |
| Pricing | Input $0.35 / 1M · Output $2.2 / 1M tokens |
Vision limits¶
Vision limits are model-specific.
| Property | Value |
|---|---|
| Processor pixel budget | 1,048,576 |
Reasoning¶
Reasoning support and controls are model-dependent.
Supported efforts: none, low, medium, xhigh.
Maximum configured reasoning sub-budget: 8,192 tokens.
See the reasoning guide for budget semantics.
Use this model¶
Copy the canonical ID into the model field. Check the endpoint guide before using optional capabilities.