MiniMax H3 Video Generation

The MiniMax H3 series uses the MiniMax native async API (/api/v2), alongside the Volcengine Seedance shape (/api/v3). Both follow "create task → poll status → read result", but differ in paths, field names, and billing.

MiniMax video is billed per second (per-second price depends on resolution), not per token.

Models and resolutions

Each H3 variant supports different resolutions. The available tiers are determined by the pricing configured for the model:

ModelSupported resolutionsNotes
MiniMax-H3768P / 2KStandard, supports 2K
H3-Highspeed480P / 768PSpeed first
H3-Lite480P / 768PCost first
H3-Max480P / 768PQuality first, minimum 5 seconds

Passing an unsupported resolution returns 400 immediately without submitting to the upstream.

Key parameters

ParameterTypeRequiredDescription
modelstringYesModel call name from the Model Plaza or model list
contentarrayYesInput content; must contain at least one non-empty text item
resolutionstringYes768P / 2K or 480P / 768P depending on the model
durationintegerYesOutput duration in seconds, 4–15 (H3-Max minimum 5)
ratiostringConditionaladaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16; required for text-to-video and cannot be adaptive
callback_urlstringNoTerminal-state callback URL (platform POSTs the result when the task finishes)
aigc_watermarkbooleanNoWhether to add a watermark, default false

content items

FieldTypeDescription
typestringtext / image_url / video_url / audio_url
textstringRequired when type=text
image_url.urlstringPublic URL
rolestringfirst_frame / last_frame / reference_image / reference_video / reference_audio

First/last frame (first_frame + last_frame) and reference generation (reference_*) cannot be mixed.

Endpoints

OperationMethodPath
Create taskPOST/api/v2/video_generation
Query taskGET/api/v2/query/video_generation/{task_id}
List tasksGET/api/v2/query/video_generation
Cancel/deleteDELETE/api/v2/video_generation/{task_id}

Task status: queued → running → succeeded / failed / cancelled.

Text to video

curl -X POST https://www.silvamux.com/api/v2/video_generation \
  -H "Authorization: Bearer $SILVAMUX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<MODEL_CALL_NAME>",
    "content": [{"type": "text", "text": "A golden retriever running on the beach, cinematic"}],
    "resolution": "768P",
    "duration": 5,
    "ratio": "16:9"
  }'

Successful creation responds:

{"task_id": "462160194171102"}

Query a task

curl "https://www.silvamux.com/api/v2/query/video_generation/<TASK_ID>" \
  -H "Authorization: Bearer $SILVAMUX_API_KEY"

A successful response wraps the payload in task:

{
  "task": {
    "id": "462160194171102",
    "model": "<MODEL_CALL_NAME>",
    "status": "succeeded",
    "resolution": "768P",
    "duration": 5,
    "content": { "url": "https://..." },
    "usage": { "total_seconds": 5, "output_seconds": 5 }
  }
}
  • The artifact URL lives at task.content.url, expires, so download it promptly.
  • Billed seconds are in task.usage.total_seconds.

First-frame and reference generation

{
  "model": "<MODEL_CALL_NAME>",
  "content": [
    {"type": "text", "text": "The camera pulls back slowly as steam rises"},
    {
      "type": "image_url",
      "image_url": {"url": "https://example.com/first.png"},
      "role": "first_frame"
    }
  ],
  "resolution": "2K",
  "duration": 5,
  "ratio": "adaptive"
}

Reference generation (reference_image / reference_video / reference_audio) supports up to 9 images, 3 videos, and 3 audio clips; audio cannot appear alone.

Cancel a task

curl -X DELETE "https://www.silvamux.com/api/v2/video_generation/<TASK_ID>" \
  -H "Authorization: Bearer $SILVAMUX_API_KEY"

Cancelling a queued task is free (the pre-authorised amount is fully refunded). The upstream does not allow cancellation once a task is running.

Result callback

When callback_url is provided, the platform POSTs the result to that address on terminal state; the body matches the query API ({"task": {...}}).

Your callback URL is proxied by the platform, so you do not need to implement MiniMax's official challenge handshake.

Without callback_url you can poll the query API yourself; the platform also runs an internal polling fallback.

Billing

Billed by output video seconds, with a per-second price that varies by resolution tier. For example:

  • 768P 5 seconds × unit price
  • 2K 5 seconds × unit price (higher tier)

See the pricing table on the model detail page or the console pricing page for actual unit prices.

Differences from Volcengine Seedance

ItemMiniMax H3Volcengine Seedance
Create path/api/v2/video_generation/api/v3/contents/generations/tasks
Create response{"task_id": ...}{"id": ...}
Query response{"task": {...}}Bare task object
Artifact fieldtask.content.urlcontent.video_url
BillingPer second (by resolution)Per token

The two APIs coexist and their tasks are isolated: the /api/v3 task list excludes MiniMax tasks and vice versa.