PixVerse · Video
PixVerse · Introduction
PixVerse (AIsphere) video models (v5.6 / v6 / C1): text-to-video and image / first-last frame video (no reference mode); v6 / C1 can generate audio; 540P up to 4K, 5 / 8 / 10 s. Billed per tier (credits/sec) x duration. Returns a taskId; poll for the result.
How to call
- Submit:
POST /api/cqt/generator/pixverse, returns a taskId. - Query:
GET /api/cqt/info/pixverse?id=taskId, poll until status = succeeded.
Capability map
POSTText to VideoNEW
Generate a video from a text description.
POSTImage / First-Last Frame VideoNEW
Given a first-frame image (optionally a last frame too), generate a video that starts from the first frame and transitions toward the last.
💰 See the pricing page for prices →
Common Errors
| Code | msg | Meaning | How to fix |
|---|---|---|---|
| 400 | model must be one of: [...] | model is not a sub-model of this channel | Use a model from the sub-model table |
| 400 | <model> does not support ... | The sub-model does not support this mode / resolution (e.g. vidu-q3 is reference-only, kling has no 540P) | Switch to a supported mode / resolution or another sub-model; the error lists the supported tiers |
| 400 | duration must be ... seconds for <model> | Duration is out of range for the sub-model | Adjust duration per the table (e.g. kling-o1 / 2.6 / 2.5-turbo / 2.1 / 2.0 / 1.6 accept only 5 or 10) |
| 400 | firstFrameUrl/lastFrameUrl cannot be combined with imageUrls/videoUrls | First/last frames were sent together with reference materials | Use either first/last frames or reference materials, not both |
| 400 | prompt is required | Text-to-video is missing prompt | Add prompt |
| 500 | generation_failed | Generation failed; data.errorMsg has details (credits auto-refunded) | Adjust based on the error and retry; contact support if it persists |
Errors are returned as a bizCode, e.g. bizCode=451, msg=prompt_unsafe.
Tip: after saving your API Key via Authorize, every capability page supports "Try it".