Extend one source video before or after its current content
Create an asynchronous continuation immediately before or after one source video. `duration` is required and always means the final returned-video duration; it must exceed the trusted source duration.
Request Body
application/jsonRequiredmetadataMetadataCaller-supplied metadata; ≤16 keys, key ≤64 chars, value ≤512 chars
callback_urlCallback UrlHTTPS URL Beatra will POST the final Task envelope to when the Task reaches a terminal state
callback_signing_key_idCallback Signing Key IdOptional standalone callback signing key. Omit for unsigned callback delivery; requires callback_url when provided.
modelModelUse auto for request-dependent selection from the ordered live candidates. A concrete model is evaluated exactly as requested and is never substituted.
"auto"Value in: "auto" | "wan2.7-i2v" | "seedance-2" | "seedance-2-fast" | "seedance-2-mini"negative_promptNegative PromptContent or qualities to avoid when supported by the selected model.
durationRequired final returned-video duration in integer seconds. It must exceed the trusted source-video duration; model-specific admission may narrow the range.
2Maximum: 15aspect_ratioAspect RatioExplicit output ratio when the selected model accepts it. Omit for a declared model default, source-derived ratio, or fixed model behavior.
resolutionResolutionRequested output short-edge tier. Omit to use the selected model's declared default; unsupported tiers are rejected rather than coerced.
seedSeedenhance_promptEnhance PromptAsk the selected model to improve the prompt before generation.
watermarkWatermarkWhether generated video should include the model watermark.
generate_audioGenerate AudioWhether the selected model should generate synchronized audio.
web_searchWeb SearchWhether the selected model may use web search during generation.
return_last_frameReturn Last FrameWhether to return the generated video's last frame as an image artifact.
videoThe single source video to continue.
directionGenerate new content immediately before or after the source video's content.
"before" | "after"instructionRequired instruction describing how the source video should continue.
1Maximum length: 5000referencesReferencesOptional ordered image or audio references. Additional video references are forbidden because this operation accepts exactly one source video.
Header Parameters
X-Request-IdstringOptional client request id echoed in the response.
Idempotency-Key1Maximum length: 128AuthorizationBearer API key.
Task accepted