Create H3-Context-IR Task

Version: v1.0.0 | Last Updated: 2026-08-13
This platform fully supports the MiniMax Video Generation V2 (MiniMax-H3) official API. Requests and responses are transparently proxied, and all parameter semantics remain consistent with the official API.

H3-Context-IR performs deep understanding of multimodal context — text, images, audio, and video — analyzing the relationships among the materials and between the materials and the target output, applying complex logical reasoning, and converting the result into a structured expression that enriches semantic detail while preserving the user's original intent as much as possible.

Note: This endpoint only returns an enhanced video prompt. It does not create a video generation task.

This is an asynchronous endpoint: on success it returns a task_id. The task's task_type is h3_context_ir and its modality is text. Once the task succeeds, retrieve the enhanced prompt from content.prompt in the Query Task response. The enhanced prompt can be used directly in Create Video Generation Task, and it is also the "final prompt" that must be resubmitted when regenerating by source video.

POST https://platform.dataeyes.ai/hailuo/v2/h3_context_ir

Request Parameters

Parameter	Type	Required	Default	Description
`model`	string (enum)	Yes	—	Model name. Currently: `MiniMax-H3`
`content`	array	Yes	—	Multimodal context input array; must include one non-empty `text` item. Combination rules, element structure, and media limits are the same as in Create Video Generation Task
`duration`	integer	Yes	—	Target video duration in seconds, integer. Allowed values: `4`-`15`
`ratio`	string (enum)	Conditional	`adaptive`	Target aspect ratio; same rules as in Create Video Generation Task
`callback_url`	string	No	—	Webhook URL for status changes; behaves the same as in Create Video Generation Task

This endpoint has no resolution parameter.

Request Example

Response Example

{
  "task_id": "426586401755526"
}

Once the task succeeds, the query response looks like (excerpt):

{
  "task": {
    "id": "426586401755526",
    "model": "MiniMax-H3",
    "status": "succeeded",
    "content": {
      "prompt": "integrated_multimodal_description: [Shot 1] Cinematic, wide shot with a slow push in on a female captain ..."
    },
    "duration": 5,
    "usage": {
      "total_tokens": 9090,
      "prompt_tokens": 5664,
      "completion_tokens": 3426
    },
    "ratio": "16:9",
    "task_type": "h3_context_ir",
    "modality": "text"
  }
}

Billing

Billed per token: after the task succeeds, input is settled on usage.prompt_tokens and output on usage.completion_tokens. Nothing is pre-charged at submission, and failed tasks are not billed. See Overview · Billing & Settlement.

03-Create-H3-Context-IR

Create H3-Context-IR Task#

Request Parameters#

Request Example#

Response Example#

Billing#

Create H3-Context-IR Task

Request Parameters

Request Example

Response Example

Billing