First Frame to Video Generation

Video generation V2 API. Input via multimodal content array (text / image / video / audio). Supports text-to-video, image-to-video (first/last frame), and multimodal reference-to-video with 2K output.

POST /minimax/v2/video_generation

Image-to-video (t2va)

cURL

curl --request POST \
  --url https://baze-api.powerbuyin.top/minimax/v2/video_generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "model": "MiniMax-H3",
  "content": [
    {
      "type": "text",
      "text": "Pull focus to the people in the background and add more steam to the ramen bowl."
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png"
      },
      "role": "first_frame"
    }
  ],
  "resolution": "2K",
  "duration": 5,
  "ratio": "adaptive"
}
'

200

{
  "output": {
    "task_id": "424010985738629"
  }
}

Authorizations

Authorization · string · header · required

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

Headers

Content-Type · enum<string> · default: application/json · required

Media type of the request body. Set to application/json.

Available options: application/json

Body

application/json

model · enum<string> · required

Model name. Currently available: MiniMax-H3, MiniMax-H3-Max.

• MiniMax-H3: supports text-to-video, image-to-video (first / last frame), and multimodal reference-to-video; resolution 768P / 2K, duration 4 ~ 15 seconds.
• MiniMax-H3-Max: fast generation version. Supports text-to-video and image-to-video (first / last frame) only; multimodal references (reference image / reference video / reference audio) are not supported; resolution 480P / 768P, 2K is not supported; duration 5 ~ 15 seconds.

Available options: MiniMax-H3, MiniMax-H3-Max

content · object[] · required

Multimodal input content array describing the information used to generate the video. Each element is distinguished by type (text / image_url / video_url / audio_url) and can be annotated with a role.

Each request must contain a non-empty text item (prompt is required); omission will return a parameter error. Supported input combinations (corresponding to different generation scenarios):

Image-to-video (first frame): text + 1 image_url (role=first_frame or omitted). Image-to-video (last frame): text + 1 image_url (role=last_frame). Image-to-video (first-last frame): text + 2 image_url (roles first_frame and last_frame respectively). Image-to-video and multimodal reference-to-video are mutually exclusive: if any of reference_image / reference_video / reference_audio roles appear in content, first_frame / last_frame must not appear (and vice versa); they cannot be mixed.

Input media limits (total request body size ≤ 64 MB; use public URLs for large files, do not use Base64)

Image image_url:

Item	Limit
Format	JPG, JPEG, PNG, WEBP, HEIC, HEIF
Single file size	≤ 30 MB
Width/height range	[256, 5760] px
Aspect ratio (w/h)	[0.4, 2.5]
Count	first frame ≤ 1, last frame ≤ 1, reference images ≤ 9

Show child attributes

resolution · enum<string> · default: 768P · required

Video resolution. Available values: 480P, 768P, 2K.

• MiniMax-H3: supports 768P and 2K.
• MiniMax-H3-Max: supports 480P and 768P (default 768P, 2K is not supported).

Available options: 480P, 768P, 2K

duration · enum<integer> · default: 5 · required

Video duration in seconds. Required, integer.

• MiniMax-H3: 4 ~ 15 seconds.
• MiniMax-H3-Max: 5 ~ 15 seconds (4 seconds is not supported).

Available options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

ratio · enum<string>

Output video aspect ratio, default adaptive (automatically selects the most suitable aspect ratio based on input; the actual ratio can be retrieved from the ratio field in the query API).

Image-to-video (i2va, content includes first_frame / last_frame images): the aspect ratio is determined by the input images, ratio is always set to adaptive; passing in other reasonable values won’t cause errors, but they will be ignored and treated as adaptive.

Available options: adaptive

callback_url · string

Callback notification URL for task status changes. After configuration, the MiniMax server will first send a verification request containing a challenge field (must return the challenge value unchanged within 3 seconds to complete verification). Once verified, whenever the task status changes, a POST push will be sent to this URL, with the push body structure matching the query task API response.

Callback status values: queued, running, succeeded, failed, cancelled.

Response

200 - application/json

Returns task_id upon successful creation. Use this task_id to call the query task API to retrieve task status and results.

Query task success response example

{
  "task": {
    "id": "424010985738629",
    "model": "MiniMax-H3",
    "status": "succeeded",
    "created_at": 1785125529,
    "updated_at": 1785125946,
    "content": {
      "url": "https://your-cdn.example.com/h3-generated-2k-output.mp4"
    },
    "resolution": "2K",
    "duration": 5,
    "usage": {
      "total_seconds": 5,
      "input_seconds": 0,
      "output_seconds": 5,
      "input_image_count": 0
    },
    "ratio": "16:9",
    "task_type": "generation",
    "modality": "video"
  }
}

task_id · string

Task ID, used to query task status and results.