> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infery.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Alibaba (Qwen)

> Qwen text, vision, image, audio, video, embedding and rerank models.

Alibaba Cloud's Qwen model family available through Infery, covering text, vision, image generation, audio, video, embeddings and reranking.

<Note>Alibaba is a PRC-based provider. See our [Privacy Policy](/privacy#transfers) for data transfer details. PRC providers require explicit opt-in.</Note>

## Text models

| Model             | Slug                | Context | Max output | Stream | Tools | JSON | Vision | Files                                |
| ----------------- | ------------------- | ------- | ---------- | ------ | ----- | ---- | ------ | ------------------------------------ |
| Qwen Flash        | `qwen-flash`        | 1M      | 32K        | ✓      | ✓     | ✓    | —      | —                                    |
| Qwen Plus         | `qwen-plus`         | 1M      | 32K        | ✓      | ✓     | ✓    | —      | —                                    |
| Qwen Turbo        | `qwen-turbo`        | 128K    | 16K        | ✓      | ✓     | ✓    | —      | —                                    |
| Qwen Long         | `qwen-long`         | 10M     | 32K        | ✓      | —     | —    | —      | —                                    |
| Qwen VL Plus      | `qwen-vl-plus`      | 128K    | 8K         | ✓      | —     | —    | ✓      | PDF, images, video (10 files, 10 MB) |
| Qwen VL Max       | `qwen-vl-max`       | 128K    | 8K         | ✓      | —     | —    | ✓      | PDF, images, video (10 files, 10 MB) |
| Qwen3 Max         | `qwen3-max`         | 256K    | 32K        | ✓      | ✓     | ✓    | ✓      | PDF, images, video (10 files, 10 MB) |
| Qwen3 Omni Flash  | `qwen3-omni-flash`  | 64K     | 16K        | ✓      | —     | —    | ✓      | PDF, images, audio, video (10 files) |
| Qwen3 Coder Plus  | `qwen3-coder-plus`  | 1M      | 64K        | ✓      | ✓     | —    | —      | —                                    |
| Qwen3.5 Flash     | `qwen3-5-flash`     | 1M      | 64K        | ✓      | ✓     | ✓    | ✓      | PDF, images, video (10 files, 10 MB) |
| Qwen3.5 Plus      | `qwen3-5-plus`      | 1M      | 64K        | ✓      | ✓     | ✓    | ✓      | PDF, images, video (10 files, 10 MB) |
| Qwen3.5 Omni Plus | `qwen3-5-omni-plus` | 256K    | 32K        | ✓      | —     | —    | ✓      | PDF, images, audio, video (10 files) |
| QwQ Plus          | `qwq-plus`          | 128K    | 8K         | ✓      | —     | —    | —      | —                                    |

## Embedding models

| Model                  | Slug                     | Max input |
| ---------------------- | ------------------------ | --------- |
| Qwen Text Embedding v3 | `qwen-text-embedding-v3` | 8K        |

## Image models

| Model              | Slug                 | Sizes              | Max N | Aspect ratios                       | Edits              |
| ------------------ | -------------------- | ------------------ | ----- | ----------------------------------- | ------------------ |
| Qwen Image 2.0 Pro | `qwen-image-2-0-pro` | 1024² to 1920×1080 | 4     | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 | ✓ (up to 5 images) |
| Wan 2.6 Image      | `wan2-7-image`       | 1024² to 1920×1080 | 4     | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 | ✓ (up to 5 images) |
| Z-Image Turbo      | `z-image-turbo`      | 1024², 1280²       | 4     | 1:1, 16:9, 9:16, 4:3, 3:4           | ✓ (1 image)        |

## Audio models

### Text-to-speech

| Model             | Slug                | Output formats |
| ----------------- | ------------------- | -------------- |
| CosyVoice V2      | `cosyvoice-v2`      | mp3, wav, pcm  |
| CosyVoice V3 Plus | `cosyvoice-v3-plus` | mp3, wav, pcm  |

### Speech-to-text

| Model           | Slug              | Response formats | Max file | Inputs                         |
| --------------- | ----------------- | ---------------- | -------- | ------------------------------ |
| Paraformer V2   | `paraformer-v2`   | json, text       | 500 MB   | mp3, wav, flac, ogg, webm, mp4 |
| Qwen3 ASR Flash | `qwen3-asr-flash` | json, text       | 500 MB   | mp3, wav, flac, ogg, webm, mp4 |

## Video models

| Model                  | Slug         | Durations    | Resolutions | Aspect ratios   | Image-to-video |
| ---------------------- | ------------ | ------------ | ----------- | --------------- | -------------- |
| Wan 2.7 Text-to-Video  | `wan2-7-t2v` | 3, 5, 8, 10s | 480p, 720p  | 16:9, 9:16, 1:1 | —              |
| Wan 2.7 Image-to-Video | `wan2-7-i2v` | 3, 5, 8, 10s | 480p, 720p  | 16:9, 9:16, 1:1 | ✓ (1 image)    |

## Rerank models

| Model        | Slug           | Max input |
| ------------ | -------------- | --------- |
| Qwen3 Rerank | `qwen3-rerank` | 32K       |