videos

Generate video from ordered multimodal references

Create an asynchronous video task from ordered image, video, and audio references. Reference kinds, counts, durations, and controls are validated against the selected model.

post/v1/videos/reference-to-video

Request

  • Base URL: https://api.beatra.ai (the document declares no server; this is the origin it was published from)
  • URL: https://api.beatra.ai/v1/videos/reference-to-video
  • Auth: none declared. Required headers: Idempotency-Key

Headers

x-request-idstring nullable
Idempotency-Keystring required
authorizationstring nullable

Request body

metadataobject nullable

Caller-supplied metadata; ≤16 keys, key ≤64 chars, value ≤512 chars

callback_urlstring nullable

HTTPS URL beatra will POST the final Task envelope to when the Task reaches a terminal state

callback_signing_key_idstring nullable

Optional standalone callback signing key. Omit for unsigned callback delivery; requires callback_url when provided.

model'auto' | 'minimax-h3' | 'wan3.0-video' | 'wan3.0-video-prime' | 'happyhorse-1.1-r2v' | 'wan2.7-r2v' | 'seedance-2' | 'seedance-2-fast' | 'seedance-2-mini' | 'seedance-2.5'

Use auto for request-dependent selection from the ordered live candidates. A concrete model is evaluated exactly as requested and is never substituted.

negative_promptstring nullable

Content or qualities to avoid when supported by the selected model.

aspect_ratio'16:9' | '9:16' | '1:1' | '4:3' | '3:4' | '4:5' | '5:4' | '21:9' | '9:21' | 'adaptive' nullable

Explicit output ratio when the selected model accepts it. Omit for a declared model default, source-derived ratio, or fixed model behavior.

resolution'480p' | '720p' | '1080p' | '2k' | '4k' nullable

Requested model-defined output resolution tier. Omit to use the selected model's declared default; unsupported tiers are rejected rather than coerced.

seedinteger nullable
enhance_promptboolean nullable

Ask the selected model to rewrite the prompt before generation. Omit or use null to keep the prompt exactly as written.

watermarkboolean nullable

Whether generated video should include the model watermark.

generate_audioboolean nullable

Whether the selected model should generate synchronized audio.

web_searchboolean nullable

Whether the selected model may use web search during generation.

return_last_frameboolean nullable

Whether to return the generated video's last frame as an image artifact.

output_format'mp4' | 'mov' nullable

Optional output container. Omit or use mp4 for the existing default; models that advertise mov can return MOV without transcoding.

promptstring nullable

Optional instructions describing how the ordered references should guide the output.

Response

Task accepted

object'task'
task_idstring required
status'queued' | 'running' | 'succeeded' | 'failed' | 'canceled' required
capabilitystring required
workload_type'model' | 'social_operation'
modelstring nullable

Caller-requested model verbatim (may be 'auto'). Null for social_operation tasks.

resolved_modelstring nullable

Actual model that ran (null until execution starts; equals model for explicit-model calls)

model_selection_reasonunknown
metadataobject nullable
inputobject nullable
outputobject nullable
created_atstring date-time required
started_atstring date-time nullable
deadline_atstring date-time nullable
completed_atstring date-time nullable
cancel_requested_atstring date-time nullable

Changes

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