curl -X POST "https://example.com/v1/videos" \ -H "Content-Type: application/json" \ -d '{ "prompt": "A cinematic drone shot flying through a neon-lit futuristic city at night", "seconds": 8 }'
The video generation model to use. Supports current Veo and Sora video models, including provider-prefixed variants like openai/sora-2 or avalanche/veo-3.1-generate-preview.
Default"veo-3.1-generate-preview"
prompt*string
Text prompt describing the video to generate.
Length1 <= length
size?string
Output resolution in OpenAI widthxheight format. Supported values depend on the selected model and provider mapping.
callback_url?string
LLMGateway extension. When set, a signed webhook is delivered after the job reaches a terminal state.
Formaturi
callback_secret?string
LLMGateway extension. Shared secret used to sign webhook deliveries with HMAC-SHA256.
Length1 <= length
input_reference?||array<|>
Reference image input alias. Accepts HTTPS URLs or base64 data URLs and routes to provider-specific image-guided video generation when supported.
last_frame?|
Optional ending frame for frame-to-video generation. Requires image and is routed to providers that support first/last-frame generation.
seconds*integer
Output duration in seconds. Supported values depend on the selected model and provider mapping.
Range1 <= value
audio?boolean
Whether the generated video should include audio. Support depends on the selected model and provider mapping.
Defaulttrue
n?integer
image?|
Input image for image-to-video generation. Supports HTTPS URLs and base64 data URLs. Routed to provider-specific image-to-video generation when supported by the selected model.
reference_images?array<|>
One to three reference images for provider-specific asset or material-guided video generation.
Items1 <= items <= 3
reference_videos?array<|>
One to three reference videos (HTTPS URLs) for omni-reference video generation. Currently only supported on ByteDance Seedance 2.0 models and can be combined with reference_images.
Items1 <= items <= 3
reference_audios?array<|>
One to three reference audio clips (HTTPS URLs) for omni-reference video generation. Currently only supported on ByteDance Seedance 2.0 models and can be combined with reference_images and reference_videos.