Create a video task (MiniMax shape)

The vendor-shaped entry point for MiniMax video generation. If you already have MiniMax code, point base_url at Amux — request and response shapes match what your client already sends.

This endpoint is asynchronous: submitting returns a task ID and you poll for the result. That is the vendor API's own contract, not an Amux limitation.

The task ID is an Amux ID

The task_id you get back is the Amux task ID, not the upstream one. The upstream handle stays internal: it would reveal which provider served the call, and it is not accepted on any Amux endpoint.

Every retrieval endpoint accepts only this ID. GET /v1/tasks/{id} and the MiniMax-shaped alias below read the same task, so SDKs that build the polling URL themselves keep working.

Three differences from the Model Studio shape

Model Studio shapeThis one
PromptPrompt or media, at least oneRequired
Mediainput.media[], type is the rolecontent[], type is the media kind, the role is on role
CombiningFirst/last frame excludes reference materialCan be given together

Billing is identical to /v1/tasks

Routing, price book and the reservation taken at submit time are the same. Choosing this endpoint over the unified one changes the wire format, nothing else.

Note that this model bills for input material: reference images per image and reference video by its input duration, both at the rate of the chosen output resolution; reference audio is free. The reservation covers 15 seconds of output, plus another 15 seconds of input when a reference video is present, and the difference is released at settlement.

post/v2/video_generation

Request

  • Base URL: https://gateway.amux.ai
  • URL: https://gateway.amux.ai/v2/video_generation
  • Auth: HTTP bearer

Request body

modelstring required

The Amux model ID. Two models serve this endpoint today:

ModelResolutionDurationMaterial
minimax/minimax-h3768P 2K4-15sFrames + reference
minimax/minimax-h3-max480P 768P5-15sFrames only
resolution'768P' | '2K'

Output resolution tier. This field is a pricing dimension: both the generated video and any input video are billed at the chosen tier's rate.

durationinteger

Output length in seconds, an integer from 4 to 15. This model has no automatic duration (-1).

ratio'adaptive' | '21:9' | '16:9' | '4:3' | '1:1' | '3:4' | '9:16'

Aspect ratio. adaptive follows the input material.

aigc_watermarkboolean

Whether to stamp an AIGC watermark on the output.

callback_urlstring uri

Called back when the task reaches a terminal state. This is Amux's webhook_url -- we simply accept it under the vendor's field name; the payload matches the unified endpoint exactly (the {event, sent_at, task} envelope, an Amux-Signature header, and backoff retries).

https only, and never a private address. The URL is validated at submit time.

Example request

{
  "model": "minimax/minimax-h3",
  "content": [
    {
      "type": "text",
      "text": "A ginger cat running through fresh snow, slow motion"
    }
  ],
  "resolution": "768P",
  "duration": 5
}

Response

Accepted. The body carries only task_id — take it to GET /v1/tasks/{id} (or the alias below) and poll.

task_idstring

The Amux task ID. Every retrieval endpoint accepts only this ID.

Changes

No recorded changes to this operation across all 1 revision of this API.