Vega Video 1.5 Pro โ
โ Back to the Vega Video overview for version comparison and selection.
Endpoint: POST https://tokenhub-intl.tencentcloudmaas.com/v1/wand/vega-videos/tasksAuthentication: Tokenhub API Key / Bearer
Vega Video 1.5 Pro (wand-vega-video-1.5-pro) is the highest-spec Pro-series Vega Video version on Tokenhub (for the flagship tier see 1.0 Max): up to 30 seconds per clip, duration=-1 to let the model decide the length, and asset:// material references.
Allowlist registration required
The Pro series can only be called after allowlisting. Contact the WAND team to be registered.
Basic information โ
| Item | Value |
|---|---|
model value | wand-vega-video-1.5-pro |
| Resolution | 480P / 720P / 1080P / 2K / 4K, default 720P |
| Ratio | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive, default adaptive |
| Duration | An integer from 4 to 30 seconds, or -1 (model decides), default 5 |
| Capabilities | Text-to-video / first-and-last-frame / reference-based |
| Material reference | Supports asset://<id> |
Input modes โ
| Mode | content composition | Condition |
|---|---|---|
| Text-to-video | type=text | At least 1 non-empty text element |
| First-and-last frame | text + image_url | At most 1 first_frame and 1 last_frame; text is required |
| Reference-based | text + image / video / audio | Every media element must declare the matching role |
| Registered material reference | text + asset://<id> | Material status must be DONE, and under the same AppID as the video request |
Request parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
model | Yes | String | Fixed value wand-vega-video-1.5-pro |
content | Yes | Array[Object] | Multimodal input array; must contain at least 1 type=text element |
resolution | No | String | 480P / 720P / 1080P / 2K / 4K. Default 720P |
ratio | No | String | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive. Default adaptive |
duration | No | Integer | An integer from 4 to 30, or -1. Default 5 |
options | No | Object | Option bag. Can be omitted entirely; omitting it or passing {} applies all defaults |
options.return_last_frame | No | Boolean | Whether to return the last-frame image. Default false. content.last_frame_url appears in the query result only when the model actually produced a last frame |
options.return_vega_usage | No | Boolean | Whether the query endpoint returns usage statistics. Default false. When true, a successful response carries a usage block |
content elements โ
content is a union-typed array keyed by type, and the element fields are mutually exclusive. Within one element use only the content field matching its type โ never mix different media fields in the same element.
| Parameter | Required | Type | Description |
|---|---|---|---|
type | Yes | String | text / image_url / video_url / audio_url |
text | Conditional | String | Required and non-empty when type=text. Multiple text elements are concatenated in array order |
image_url | Conditional | Object | Required when type=image_url, shaped {"url": "..."} |
image_url.url | Conditional | String | Image address. Supports a public HTTP/HTTPS URL, inline Base64 (data:<mediatype>;base64,<payload>), and asset://<id> |
video_url | Conditional | Object | Required when type=video_url, shaped {"url": "..."} |
video_url.url | Conditional | String | Video address. Public HTTP/HTTPS URL only โ inline Base64 is not supported |
audio_url | Conditional | Object | Required when type=audio_url, shaped {"url": "..."} |
audio_url.url | Conditional | String | Audio address. Same URL rules as image_url |
role | Conditional | String | What the media is for. Required when type is image_url / video_url / audio_url; unused for type=text |
Valid type / role combinations โ
type | role | Purpose |
|---|---|---|
text | unused | Text prompt |
image_url | first_frame | First frame |
image_url | last_frame | Last frame |
image_url | reference_image | Reference image |
video_url | reference_video (fixed) | Reference video |
audio_url | reference_audio (fixed) | Reference audio |
role is required for all three media types; omitting it or leaving it empty is rejected.
Reference input conditions โ
| Item | Condition |
|---|---|
| First and last frames | At most 1 each. At least 1 type=text element must be present as well |
| Ratio of first/last frames | Derived from the input image when ratio is omitted; a supported ratio may also be set explicitly |
| Recommended reference mix | Up to 9 images, 3 videos, and 3 audio clips, with no more than 12 items in total |
| Audio references | Pair audio with at least 1 reference image or reference video; do not submit audio alone |
| Registered materials | Pass asset://<id> as image_url.url; the material must be DONE |
Do not apply VOD / MPS specs here
The reference counts above are recommendations for composing Tokenhub requests. Do not treat the FileInfos counts or size limits of VOD / MPS as limits for this API.
Request examples โ
Text-to-video โ
curl -X POST 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/vega-videos/tasks' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"model": "wand-vega-video-1.5-pro",
"content": [
{"type": "text", "text": "A woman walks down a rain-soaked neon street, cinematic camera move, natural motion."}
],
"resolution": "1080P",
"ratio": "16:9",
"duration": 20
}'First-and-last-frame generation โ
{
"model": "wand-vega-video-1.5-pro",
"content": [
{"type": "text", "text": "Transition naturally from the first frame to the last frame, keeping the lighting continuous."},
{"type": "image_url", "image_url": {"url": "https://example.com/start.jpg"}, "role": "first_frame"},
{"type": "image_url", "image_url": {"url": "https://example.com/end.jpg"}, "role": "last_frame"}
],
"resolution": "2K",
"duration": 8
}Reference-based generation โ
{
"model": "wand-vega-video-1.5-pro",
"content": [
{"type": "text", "text": "The character from the reference image moves naturally inside the reference video's scene, in rhythm with the music."},
{"type": "image_url", "image_url": {"url": "https://example.com/character.jpg"}, "role": "reference_image"},
{"type": "video_url", "video_url": {"url": "https://example.com/scene.mp4"}, "role": "reference_video"},
{"type": "audio_url", "audio_url": {"url": "https://example.com/bgm.mp3"}, "role": "reference_audio"}
],
"resolution": "1080P",
"ratio": "16:9",
"duration": -1,
"options": {"return_last_frame": true, "return_vega_usage": true}
}Referencing a registered material โ
Material registration and query are covered in Material management; real-person material additionally requires liveness verification first.
{
"model": "wand-vega-video-1.5-pro",
"content": [
{"type": "text", "text": "The subject slowly turns to face the camera as sunlight falls across the frame."},
{"type": "image_url", "image_url": {"url": "asset://asset-20260914103210-5832"}, "role": "reference_image"}
],
"resolution": "1080P",
"ratio": "16:9",
"duration": 5
}Response parameters โ
A successful submission returns HTTP 201 Created with no error block. Task acceptance does not mean the video is finished.
| Parameter | Type | Description |
|---|---|---|
id | String | Task ID, used to poll task status |
model | String | Echo of the submitted model value |
status | String | Task status. Always queued on successful submission |
{
"id": "1300000000-video-68b7c1d4a1f2e3d4c5b6a79808192a3b4c5d6e7f8-0000",
"model": "wand-vega-video-1.5-pro",
"status": "queued"
}Querying task results โ
Endpoint: GET https://tokenhub-intl.tencentcloudmaas.com/v1/wand/vega-videos/tasks/{id}
curl -X GET 'https://tokenhub-intl.tencentcloudmaas.com/v1/wand/vega-videos/tasks/<task_id>' \
-H 'Authorization: Bearer YOUR_API_KEY'| Parameter | Type | Description |
|---|---|---|
id | String | Task ID |
model | String | Echo of the submitted model value โ not an identifier of the model that actually produced the result |
status | String | queued / running / succeeded / failed |
content | Object | Generation result, returned only when status=succeeded |
content.video_url | String | Temporary download address of the finished video, valid for 12 hours |
content.last_frame_url | String | Last-frame image address. Returned only when options.return_last_frame=true and the model actually produced a last frame |
usage | Object | Token usage statistics. Returned only when options.return_vega_usage=true was submitted and status=succeeded; the block is present even when the counts are 0 |
usage.completion_tokens | Integer | Tokens consumed by output (video generation) |
usage.total_tokens | Integer | Total tokens consumed by the task (input + output) |
error | Object | Failure details, returned only when status=failed |
error.code | String | Task-level error code, e.g. InternalError / TaskTimeout |
error.message | String | Failure reason |
Handling by status โ
status | Meaning | Handling |
|---|---|---|
queued | Waiting | Keep querying the same task ID every 3โ5 seconds |
running | Generating | Keep querying the same task ID |
succeeded | Done | Download the result and stop querying |
failed | Failed | Read error to diagnose, then stop querying |
{
"id": "1300000000-video-68b7c1d4a1f2e3d4c5b6a79808192a3b4c5d6e7f8-0000",
"model": "wand-vega-video-1.5-pro",
"status": "succeeded",
"content": {
"video_url": "https://aigc-video.example.com/xxx/result.mp4",
"last_frame_url": "https://aigc-video.example.com/xxx/last-frame.jpg"
},
"usage": {"completion_tokens": 128000, "total_tokens": 129024}
}Re-host the result before the URL expires. Tasks that time out while waiting return failed with TaskTimeout.
Error codes โ
The error-code vocabulary is shared with the other versions and the material API โ see the unified error codes on the overview page.