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

# PixVerse V6 Max

> High-quality text-to-video and single-image-to-video with 1–15 second integer durations and optional native audio.

High-quality text-to-video and single-image-to-video with 1–15 second integer durations and optional native audio.

## Quick start

```bash theme={"system"}
curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: pixverse-v6-max-example-001" \
  -d '{
  "model": "pixverse-v6-max",
  "action": "generate",
  "prompt": "A paper boat drifts on a pond with gentle water sounds",
  "duration": 3,
  "resolution": "540p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}'
```

Submission returns a task\_id. Use [`GET /v1/tasks/{task_id}`](https://docs.qingbo.dev/en/api-reference/task/status) to poll the result. Reference assets must use publicly downloadable URLs.

## Parameters

| Parameter | Type or values | Description |
| - | - | - |
| model | `pixverse-v6-max` | Exact model ID. |
| `action` | generate | Only generate is supported. |
| `prompt` | string | Required for text-to-video, up to 5000 characters; optional for image-to-video, up to 2048 characters. |
| `image_urls` | string\[] | Optional; image-to-video accepts exactly one reference. |
| `duration` | integer | Required, 1–15 seconds. |
| `resolution` | 360p / 540p / 720p / 1080p | Defaults to 540p. |
| `aspect_ratio` | string | Text generation defaults to 16:9; also accepts 9:16, 4:3, 3:4, 1:1, 2:3, 3:2 and 21:9. Image-to-video follows its reference and ignores this field. |
| `generate_audio` | boolean | Defaults to false; true selects the higher native-audio rate. |
| `seed` | integer | Optional, 0–2147483647. |

Extension, first/last-frame transitions, multi-image fusion, img\_references, motion\_mode and other V6-only controls are unsupported. Use generate\_audio for sound and resolution for quality.

## Billing and results

Successful tasks charge output seconds multiplied by the resolution/audio per-second rate. Silent and audio output use different rates. Actual output pixel dimensions are authoritative.

Read current rates in the model market or price\_config from GET /v1/models. Images are in result.images and videos in result.videos; url is an array. Failed or cancelled tasks receive a full reservation refund. Read final cost in integer quota (500,000 quota = 1 USD) and confirm billing\_status is settled.

For callbacks, waiting, idempotency and spending limits, see [Submit a task](https://docs.qingbo.dev/en/api-reference/task/submit.md)。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.