Qwen-MT-Flash is a lightweight translation model from the Qwen series, upgraded with the Qwen3 architecture. It supports translation across 92 languages and provides terminology intervention, format preservation, and domain-specific adaptation. It suits applications that require a balance of speed, quality, and cost.
Inference Service Provider
The inference service provider for qwen-mt-flash is QwenCloud.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Supported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 8192 | Max Output Length | 8192 |
Context Window | 16384 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit QwenCloud console for promotional offers.
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- US (Virginia)
Scope: International
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input | 0.16 | Per 1M tokens |
Output | 0.49 | Per 1M tokens |
Rate Limits
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- US (Virginia)
Scope: International
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 100,000 |