MiniMax H3 Max | BeatAPI API Documentation

curl -X POST https://api.beatapi.io/v1/videos/tasks \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "model": "minimax-h3-max",
  "prompt": "A slow cinematic push through a misty mountain village at dawn.",
  "duration": 5,
  "resolution": "768P"
}'

{
  "data": {
    "capability_id": "minimax-h3-max",
    "capability_version": null,
    "completed_at": null,
    "created_at": 1782210000,
    "error_code": null,
    "error_message": null,
    "id": "task_8K2qA",
    "media_type": "video",
    "model": "minimax-h3-max",
    "object": "task",
    "output": null,
    "request_id": "req_abc123",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1782210000,
    "usage": {
      "billable_duration_seconds": 5,
      "credits_charged": 0.4,
      "credits_refunded": 0,
      "credits_reserved": 0.4,
      "credits_settled": 0
    }
  }
}

A post-trained H3 tuned for prompt adherence. Text or first and last frames, at 480P or 768P.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit `images`.
First frame	`model`, `prompt`, `images`	Provide one image URL.
First and last frames	`model`, `prompt`, `images`	Provide two image URLs in first-to-last order.

Async flow: Create the task, save data.id, then poll the Task with GET /v1/tasks/{task_id}. On succeeded, read data.output.media. On failed, read data.error_code and data.error_message, then follow the error and retry policy.

Using a local file? upload a local input first and pass the returned data.url.

A post-trained H3 tuned for prompt adherence. Text or first and last frames, at 480P or 768P. ### Supported modes | Mode | Required input | Rules | | --- | --- | --- | | Text to video | `model`, `prompt` | Omit `images`. | | First frame | `model`, `prompt`, `images` | Provide one image URL. | | First and last frames | `model`, `prompt`, `images` | Provide two image URLs in first-to-last order. | **Async flow:** Create the task, save `data.id`, then [poll the Task](/quick-guide#get-task-status) with `GET /v1/tasks/{task_id}`. On `succeeded`, read `data.output.media`. On `failed`, read `data.error_code` and `data.error_message`, then follow the [error and retry policy](/quick-guide#errors-and-retry-policy). **Using a local file?** [upload a local input](/quick-guide#upload-an-input-file) first and pass the returned `data.url`.

Authentication

AuthorizationBearer

Send your API key as Authorization: Bearer <BEATAPI_API_KEY>.

Request

This endpoint expects an object.

model"minimax-h3-max"Required

Must be minimax-h3-max.

promptstringRequired1-5000 characters

What should happen in the shot — the motion, the expression, the camera.

imageslist of stringsOptional

Public HTTPS images. One starts the render from a first frame; a second becomes the last frame, in first-to-last order.

durationintegerOptional>=1Defaults to 5

Requested output duration in seconds. Billed per second at the rate for the chosen resolution. If a duration is unsupported, the API returns 400.

resolutionenumOptionalDefaults to 768P

Output resolution. Upper-case P, and the only two values this model accepts. Price scales with it.

seedintegerOptional>=0

Reuse a seed to re-render the same motion. A random seed is chosen when omitted.

Response

Video generation task accepted

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

409

Conflict Error

429

Too Many Requests Error

Supported modes

Authentication

Headers

Request

Response

Errors

Supported modes