Skip to main content
POST
/
v1
/
videos
Hailuo First-Last Frame to Video
curl --request POST \
  --url https://api.powertokens.ai/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "MiniMax-Hailuo-02",
  "images": [
    "https://example.com/assets/frame-start.png",
    "https://example.com/assets/frame-end.png"
  ],
  "prompt": "The child grows up naturally.",
  "seconds": "6",
  "size": "1080P"
}
'
{
  "id": "<string>",
  "task_id": "<string>",
  "object": "video",
  "model": "<string>",
  "status": "queued",
  "progress": 0,
  "created_at": 123
}

Authorizations

​
Authorization
string
header
required

Pass Authorization: Bearer <token> in the request header.

Body

application/json
​
model
enum<string>
required

Model name for this capability.

Available options:
MiniMax-Hailuo-02
​
images
string[]
required

First and last frame image array, in fixed order [first frame, last frame].

Required array length: 2 elements
​
prompt
string

Optional video prompt.

Maximum string length: 2000
​
seconds
enum<string>

Target video duration in seconds. (1080P only supports 6 seconds.)

Available options:
6,
10
​
size
enum<string>

Target output resolution. First-Last Frame to Video model currently supports 768P and 1080P.

Available options:
768P,
1080P

Response

Submitted successfully. Returns an OpenAI-compatible video task object.

​
id
string
​
task_id
string
​
object
string
Example:

"video"

​
model
string
​
status
string
Example:

"queued"

​
progress
integer
Example:

0

​
created_at
integer<int64>