MiniMax H3 Max Turbo Video Extend

POST/v1/run

MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, continues an existing video with 1-15 seconds of new footage with native audio.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to minimax/h3-max-turbo/video-extend.

Default: minimax/h3-max-turbo/video-extend

stringpromptrequired

What happens next. Describe the continuation, not the source.

Optional<string>aspect_ratio

Output aspect ratio. Matches the source video when omitted.

Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

stringvideorequired

URL of the video to extend. Must be 1.625 s to 60 s long, up to 50 MB, aspect ratio between 0.4 and 2.5.

Optional<string>resolution

Output video resolution.

Allowed values: 480P, 768P, 1080P, 2K

Default: 768P

Optional<integer>duration

Seconds of new footage to add after the source. The actual duration may be slightly longer.

Range: 1 to 15

Default: 5

Optional<integer>seed

Seed for the continuation. Random when omitted.

Optional<array<string>>reference_audio_urls

Optional audio references for the continuation (2–15 seconds each, 15 seconds combined). The full extended video retains its original source soundtrack, and its ending still conditions the transition. These clips guide the newly generated audio instead of using that soundtrack as an audio reference. Assign each clip a role in the prompt, such as 'Audio 1 for the voice' and 'Audio 2 for background music'.

Optional<string>output

'extended' returns the whole source video followed by the new footage. 'continuation' returns only the generated continuation.

Allowed values: extended, continuation

Default: extended

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: video-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/h3-max-turbo/video-extend",
  "prompt": "The red panda keeps walking along the log, then looks up at a bird.",
  "aspect_ratio": "21:9",
  "video": "https://storage.googleapis.com/falserverless/example_inputs/flux-3-red-panda.mp4",
  "duration": 5
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "f3d2e8a1-7c4b-4a12-9d2e-123456789abc",
  "model": "minimax/h3-max-turbo/video-extend",
  "status": "running"
}