> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Hunyuan Video 1.5

> 8.3B-parameter video model with native 720p output (upscalable to 1080p), strong motion coherence, and bilingual prompt understanding up to 10s.

![Hunyuan Video 1.5](https://media.empiriolabs.ai/model-logos/hunyuan-video-1-5.png)

[Tencent](/providers/tencent) · Video Generation

`POST /v1/videos/generations`

8.3B-parameter video model with native 720p output (upscalable to 1080p), strong motion coherence, and bilingual prompt understanding up to 10s.

## At a glance

| Field               | Value                                            |
| ------------------- | ------------------------------------------------ |
| Model id            | `hunyuan-video-1-5`                              |
| Model release date  | 2025-11-20                                       |
| Input modalities    | Text, Image                                      |
| Output modalities   | Video                                            |
| Context window      | -                                                |
| Weight precision    | Mixed FP16/FP8                                   |
| Features            | 1080p_upscale, bilingual                         |
| Native inference    | Yes                                              |
| New                 | No                                               |
| Supported endpoints | `POST /v1/videos/generations`                    |
| Alternate model ids | `hunyuan-video-1.5`, `tencent/hunyuan-video-1.5` |

## Pricing

| Charge           | Spec       | Rate                |
| ---------------- | ---------- | ------------------- |
| 480p             | per second | ~~\$0.075~~ \$0.061 |
| 720p             | per second | \$0.29              |
| 1080p (upscaled) | per second | \$0.67              |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "hunyuan-video-1-5", "prompt": "sunrise over the ocean", "duration": 6}'
```

## Parameters

| Parameter         | Type    | Required | Default  | Description                                                                                                     |
| ----------------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------------------------------- |
| `prompt`          | string  | yes      | -        | Scene description.                                                                                              |
| `mode`            | enum    | no       | `"auto"` | Auto detects image-to-video when an image is attached; otherwise text-to-video. · Allowed: `auto`, `t2v`, `i2v` |
| `resolution`      | enum    | no       | `"480p"` | 480p is the fastest native tier. 1080p is upscaled and capped at 5 seconds. · Allowed: `480p`, `720p`, `1080p`  |
| `aspect_ratio`    | enum    | no       | `"16:9"` | Output aspect ratio. · Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`                                             |
| `duration`        | integer | no       | `5`      | Clip length in seconds. 1080p is capped at 5 seconds. · Range: 1 – 10                                           |
| `cfg_scale`       | number  | no       | `6.0`    | Classifier-free guidance. Higher = follows prompt more strictly. · Range: 1.0 – 20.0                            |
| `steps`           | integer | no       | `25`     | Diffusion steps. More = higher fidelity, slower. · Range: 10 – 50                                               |
| `image`           | string  | no       | -        | Reference image URL for i2v mode.                                                                               |
| `negative_prompt` | string  | no       | `""`     | What to avoid.                                                                                                  |
| `seed`            | number  | no       | -        | Reproducibility seed. · Min: 0                                                                                  |

## Notes

8.3B-parameter Mixture-of-Experts model with strong motion coherence and bilingual prompt understanding.

**Constraints**

* 1080p is upscaled from native 720p and limited to 5s duration

**Image-to-Video formats**

* jpg, jpeg, png, webp, heic, heif, bmp, tiff, tif

**Estimated generation time**

* 480p: \~2 min
* 720p: \~8 min
* 1080p: \~20 min

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/hunyuan-video-1-5`.