Qwen-MT-Uni is a fully multimodal translation model for images, text, audio, and a wide range of document formats. Through a unified pipeline of format detection, intelligent routing, content extraction, cross-modal translation, and original-format reconstruction, it delivers high-fidelity, end-to-end translation across input types.
Inference service provider
Inference for qwen-mt-uni is provided by Alibaba Cloud Model Studio.
Model capabilities
| Capability | Supported | Capability | Supported |
|---|---|---|---|
Input modality | Text / Document / Image / Audio | Output modality | Text / Document / Image / Audio |
Playground | No | Function calling | No |
Structured output | No | Web search | No |
Prefix completion | No | Context cache | No |
Batch inference | No | Fine-tuning | No |
Context limits
| Parameter | Value |
|---|---|
Max file size | 100 MB |
Max document pages | 200 pages |
Audio duration | 3 seconds – 60 minutes |
Pricing
This page lists the standard model prices only. For promotions and time-limited discounts, see the Model Studio console.
- China (Beijing)
| Input modality | Input price (CNY per 1M tokens) |
|---|---|
Text | 65 |
Document | 20 |
Image | 32 |
Audio | 400 |
Rate limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (requests per minute) | 162 |
TPM (tokens per minute) | 2,592,000 |
Async concurrency | 3 |
Async queue size | 500 |