# Qwen-MT Translation Model Parameters

## Introduction

Qwen-MT is a translation-specific model in the Tongyi Qianwen series, optimized for multilingual translation scenarios. This model supports bidirectional translation between multiple languages, providing efficient inference performance while maintaining translation quality.

## Parameters

### Basic Parameters

| Field | Type | Required | Description |
| :--- | :--- | :--- | :--- |
| `model` | String | Yes | Model name, e.g., `qwen-mt-flash` |
| `messages` | Array | Yes | List of conversation messages |
| `translation_options` | Object | No | Translation configuration options |

### translation_options Parameters

| Field | Type | Required | Description |
| :--- | :--- | :--- | :--- |
| `source_lang` | String | No | Source language, e.g., `"Chinese"`, `"auto"` |
| `target_lang` | String | No | Target language, e.g., `"English"`, `"Japanese"` |

### Supported Languages

| Language | English Name | Code |
| :--- | :--- | :--- |
| Auto Detect | Auto | `auto` |
| English | English | `en` |
| Simplified Chinese | Chinese | `zh` |
| Traditional Chinese | Traditional Chinese | `zh_tw` |
| Russian | Russian | `ru` |
| Japanese | Japanese | `ja` |
| Korean | Korean | `ko` |
| Spanish | Spanish | `es` |
| French | French | `fr` |
| Portuguese | Portuguese | `pt` |
| German | German | `de` |
| Italian | Italian | `it` |
| Thai | Thai | `th` |
| Vietnamese | Vietnamese | `vi` |
| Indonesian | Indonesian | `id` |
| Malay | Malay | `ms` |
| Arabic | Arabic | `ar` |
| Hindi | Hindi | `hi` |
| Hebrew | Hebrew | `he` |
| Burmese | Burmese | `my` |
| Tamil | Tamil | `ta` |
| Urdu | Urdu | `ur` |
| Bengali | Bengali | `bn` |
| Polish | Polish | `pl` |
| Dutch | Dutch | `nl` |
| Romanian | Romanian | `ro` |
| Turkish | Turkish | `tr` |
| Khmer | Khmer | `km` |
| Lao | Lao | `lo` |
| Cantonese | Cantonese | `yue` |
| Czech | Czech | `cs` |
| Greek | Greek | `el` |
| Swedish | Swedish | `sv` |
| Hungarian | Hungarian | `hu` |
| Danish | Danish | `da` |
| Finnish | Finnish | `fi` |
| Ukrainian | Ukrainian | `uk` |
| Bulgarian | Bulgarian | `bg` |
| Serbian | Serbian | `sr` |
| Telugu | Telugu | `te` |
| Afrikaans | Afrikaans | `af` |
| Armenian | Armenian | `hy` |
| Assamese | Assamese | `as` |
| Asturian | Asturian | `ast` |
| Basque | Basque | `eu` |
| Belarusian | Belarusian | `be` |
| Bosnian | Bosnian | `bs` |
| Catalan | Catalan | `ca` |
| Cebuano | Cebuano | `ceb` |
| Croatian | Croatian | `hr` |
| Egyptian Arabic | Egyptian Arabic | `arz` |
| Estonian | Estonian | `et` |
| Galician | Galician | `gl` |
| Georgian | Georgian | `ka` |
| Gujarati | Gujarati | `gu` |
| Icelandic | Icelandic | `is` |
| Javanese | Javanese | `jv` |
| Kannada | Kannada | `kn` |
| Kazakh | Kazakh | `kk` |
| Latvian | Latvian | `lv` |
| Lithuanian | Lithuanian | `lt` |
| Luxembourgish | Luxembourgish | `lb` |
| Macedonian | Macedonian | `mk` |
| Maithili | Maithili | `mai` |
| Maltese | Maltese | `mt` |
| Marathi | Marathi | `mr` |
| Mesopotamian Arabic | Mesopotamian Arabic | `acm` |
| Moroccan Arabic | Moroccan Arabic | `ary` |
| Najdi Arabic | Najdi Arabic | `ars` |
| Nepali | Nepali | `ne` |
| North Azerbaijani | North Azerbaijani | `az` |
| North Levantine Arabic | North Levantine Arabic | `apc` |
| Northern Uzbek | Northern Uzbek | `uz` |
| Norwegian Bokmål | Norwegian Bokmål | `nb` |
| Norwegian Nynorsk | Norwegian Nynorsk | `nn` |
| Occitan | Occitan | `oc` |
| Odia | Odia | `or` |
| Pangasinan | Pangasinan | `pag` |
| Sicilian | Sicilian | `scn` |
| Sindhi | Sindhi | `sd` |
| Sinhala | Sinhala | `si` |
| Slovak | Slovak | `sk` |
| Slovenian | Slovenian | `sl` |
| South Levantine Arabic | South Levantine Arabic | `ajp` |
| Swahili | Swahili | `sw` |
| Tagalog | Tagalog | `tl` |
| Ta'izzi-Adeni Arabic | Ta'izzi-Adeni Arabic | `acq` |
| Tosk Albanian | Tosk Albanian | `sq` |
| Tunisian Arabic | Tunisian Arabic | `aeb` |
| Venetian | Venetian | `vec` |
| Waray | Waray | `war` |
| Welsh | Welsh | `cy` |
| Western Persian | Western Persian | `fa` |

**Note**: `source_lang` and `target_lang` can use language codes (e.g., `en`, `zh`) or English language names (e.g., `English`, `Chinese`).

## API Example

### cURL Example

```bash
curl -s -X POST https://api.modelverse.cn/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen-mt-flash",
  "messages": [
    {
      "role": "user",
      "content": "看完这个视频我没有笑"
    }
  ],
  "translation_options": {
    "source_lang": "auto",
    "target_lang": "English"
  }
}'
```

## Response Example

```json
{
  "choices": [
    {
      "message": {
        "content": "I didn't laugh after watching this video.",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 9,
    "total_tokens": 41
  },
  "created": 1782376798,
  "system_fingerprint": null,
  "model": "qwen-mt-flash",
  "id": "chatcmpl-1f33275d-d0bf-999d-bfa8-0f6029ff5ae4"
}
```

## Notes

1. **Language Auto Detection**: When `source_lang` is set to `"auto"`, the model will automatically detect the source language
2. **Language Name Format**: `source_lang` and `target_lang` can use language codes (e.g., `"en"`, `"zh"`) or English language names (e.g., `"English"`, `"Chinese"`)
3. **translation_options**: Translation parameters need to be placed in the `translation_options` object
4. **Long Text Processing**: It is recommended to segment long text for translation to achieve better translation quality
5. **Technical Terms**: For technical terms in specific domains, it is recommended to provide context in the prompt

## Model Support

- `qwen-mt-flash`