Skip to content

MiniMax H3 Image-to-Video ​

This page is generated from the upstream official OpenAPI documentation. Endpoints, parameters and examples match the official docs; brand and API domain are replaced with ModelFold.

Endpoint ​

POST /jobs/createTask

Full URL: https://ai.modelfold.online/v1/jobs/createTask

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Output videos include a stereo audio track generated with the video; dialogue, music and sound effects can be described in the prompt. Audio cannot be turned off.

Query Task Status ​

After submitting a task, you can check its progress and retrieve the result through the unified query endpoint:

  • Get Task Details — Learn how to check task status and retrieve the generated result

TIP

In production, we recommend using the callBackUrl parameter to receive an automatic notification when generation is complete instead of polling the status endpoint.

Request Parameters ​

Body (application/json) ​

ParameterTypeRequiredDescription
modelstringYesThe name of the model used for the generation task. Used for MiniMax H3 image-to-video. Default:"minimax-h3/image-to-video"。 Allowed values:minimax-h3/image-to-video。 示例:minimax-h3/image-to-video。
callBackUrlstringNoThe callback URL after the task is completed.
input`stringstring`Yes
  input.promptstringYesVideo generation prompt, length is between 1 and 7000 characters. 示例:Let the character in the scene turn around naturally and smile, camera slowly pushing forward。
  input.first_frame_urlstringNoFirst frame image URL. Note: Either first_frame_url or last_frame_url must be provided. Publicly accessible HTTP(S) URL; supports JPG, JPEG, PNG, WEBP, HEIC, HEIF formats; single image size not exceeding 30 MB, image side length between 256 and 5760 pixels, aspect ratio between 0.4 and 2.5. 示例:https://example.com/first-frame.jpg。
  input.last_frame_urlstringNoLast frame image URL. Note: Either first_frame_url or last_frame_url must be provided. Image restrictions are the same as first_frame_url. 示例:https://example.com/last-frame.jpg。
  input.durationintegerYesGenerated video duration, supporting integer values from 4 to 15 seconds. Default:6。 Allowed values:4 / 5 / 6 / 7 / 8 / 9 / 10 / 11 / 12 / 13 / 14 / 15。 示例:6。
  input.resolutionstringNoVideo resolution. Default:"2K"。 Allowed values:768P / 2K。 示例:2K。

Request Example ​

bash
curl -X POST "https://ai.modelfold.online/v1/jobs/createTask" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3/image-to-video",
  "callBackUrl": "https://example.com/callback",
  "input": {
    "prompt": "Let the character in the scene turn around naturally and smile, camera slowly pushing forward",
    "first_frame_url": "https://example.com/first-frame.jpg",
    "last_frame_url": "https://example.com/last-frame.jpg",
    "duration": 6
  }
}'
json
{
  "model": "minimax-h3/image-to-video",
  "callBackUrl": "https://example.com/callback",
  "input": {
    "prompt": "Let the character in the scene turn around naturally and smile, camera slowly pushing forward",
    "first_frame_url": "https://example.com/first-frame.jpg",
    "last_frame_url": "https://example.com/last-frame.jpg",
    "duration": 6
  }
}

Response ​

200 — success ​

Callback ​

videoTaskCompleted ​

Callback URL: {request.body#/callBackUrl} (the callBackUrl in the request body).

The system sends this callback when the minimax-h3/image-to-video task succeeds or fails.

Callback body parameters

参数类型必填说明
codeinteger是Unified callback code: 200 for success, 501 for failure. Allowed values:200 / 501。 示例:200。
msgstring是Unified callback message. Allowed values:Playground task completed successfully. / Playground task failed.。 示例:Playground task completed successfully.。
dataobject是—
  data.taskIdstring是The unique task identifier.
  data.modelstring是The model used for the task. Allowed values:minimax-h3/image-to-video。 示例:minimax-h3/image-to-video。
  data.statestring是Terminal task state. Allowed values:success / fail。 示例:success。
  data.paramstring是JSON string containing the submitted task parameters.
  data.resultJsonstring否JSON string containing resultUrls, firstFrameUrl, lastFrameUrl, or resultObject when successful. Present only when state is success.
  data.failCodestring否Failure code, a numeric string such as "400" or "500". Present only when state is fail.
  data.failMsgstring否Failure reason. Present only when state is fail.
  data.costTimeinteger否Processing time in seconds. Present on both success and failure callbacks.
  data.completeTimeinteger否Task completion timestamp.
  data.createTimeinteger否Task creation timestamp.
  data.updateTimeinteger否Use completeTime as the completion time; updateTime may equal createTime.
  data.creditsConsumednumber否Credits consumed by the task; 0 for failed tasks.

Task completed successfully

json
{
  "code": 200,
  "msg": "Playground task completed successfully.",
  "data": {
    "taskId": "task_example_video_webhook_001",
    "model": "minimax-h3/image-to-video",
    "state": "success",
    "param": "{\"input\":\"{\\\"prompt\\\":\\\"Let the character in the scene turn around naturally and smile, camera slowly pushing forward\\\",\\\"first_frame_url\\\":\\\"https://example.com/input-image.jpg\\\",\\\"last_frame_url\\\":\\\"https://example.com/input-image.jpg\\\",\\\"duration\\\":6}\",\"callBackUrl\":\"https://example.com/callback\",\"model\":\"minimax-h3/image-to-video\"}",
    "resultJson": "{\"resultUrls\":[\"https://example.com/generated-video.mp4\"]}",
    "costTime": 12,
    "completeTime": 1234567890,
    "createTime": 1234560000,
    "updateTime": 1234567890,
    "creditsConsumed": 1.23
  }
}

Task failed

json
{
  "code": 501,
  "msg": "Playground task failed.",
  "data": {
    "taskId": "task_example_video_webhook_001",
    "model": "minimax-h3/image-to-video",
    "state": "fail",
    "param": "{\"input\":\"{\\\"prompt\\\":\\\"Let the character in the scene turn around naturally and smile, camera slowly pushing forward\\\",\\\"first_frame_url\\\":\\\"https://example.com/input-image.jpg\\\",\\\"last_frame_url\\\":\\\"https://example.com/input-image.jpg\\\",\\\"duration\\\":6}\",\"callBackUrl\":\"https://example.com/callback\",\"model\":\"minimax-h3/image-to-video\"}",
    "failCode": "400",
    "failMsg": "<error detail>",
    "costTime": 12,
    "creditsConsumed": 0
  }
}

ModelFold — one API for all the best AI models.