OpenAI

Sora 2

Model ID: model_open-ai-sora-2

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`duration`	`string`	`4`	Duration in seconds [4,8,12]

Sora 2 Pro

Model ID: model_open-ai-sora-2-pro

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`duration`	`string`	`4`	Duration in seconds [4,8,12]
`resolution`	`string`	`standard`	Output resolution. Standard is 1280x720 or 720x1280, high is 1792x1024 or 1024x1792. [standard, high]

Kling

Kling V3 Omni Video

Model ID: model_kling-v3-omni-video

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2500	None	Required. Text prompt for video generation. Supports `<<<image_1>>>`, `<<<video_1>>>` template references.
`startImage`	Start Image	`file`	None	None	None	None	First frame image. Max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1.
`endImage`	End Image	`file`	None	None	None	None	Last frame image. Requires a Start Image. Max 10MB, min 300px.
`referenceImages`	Reference Images	`file_array`	[]	None	7	None	Reference images for elements, scenes, or styles. Max 7 without video, 4 with video.
`referenceVideo`	Reference Video	`file`	None	None	None	None	Reference video. Duration 3-10s, resolution 720-2160px per side, max 200MB.
`videoReferenceType`	Video Reference Type	`string`	feature	None	None	feature, base	'Feature' for style/camera reference, 'Base' for video editing.
`keepOriginalSound`	Keep Original Sound	`boolean`	true	None	None	None	Keep original sound from reference video.
`generateAudio`	Generate Audio	`boolean`	false	None	None	None	Generate native audio. Mutually exclusive with reference video.
`mode`	Mode	`string`	pro	None	None	standard, pro	'Standard' generates 720p, 'Pro' generates 1080p.
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 1:1, 9:16	Required when not using start frame or video editing.
`duration`	Duration	`number`	5	3	15	None	Video duration in seconds (3-15). Ignored for video editing (base).
`multiPrompt`	Multi Prompt	`string`	None	None	2048	None	JSON array of shot definitions for multi-shot mode (max 6 shots).

Kling V3 Pro - Motion Control

Model ID: model_kling-v3-pro-motion-control

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Text prompt describing the desired motion or action.
`image`	Character Image	`file`	None	None	None	None	Required. The character in this image will perform the movements from the reference video.
`video`	Reference Video	`file`	None	None	None	None	Required. Video with the motion to transfer (.mp4, .mov, .webm, .m4v, .gif).
`characterOrientation`	Character Orientation	`string`	image	None	None	image, video	Orientation of the character (Image or Video).
`keepOriginalSound`	Keep Original Sound	`boolean`	true	None	None	None	Whether to keep the original sound from the reference video.
`elements`	Element	`inputs_array`	[]	None	4	None	Optional elements (max 4). Includes Primary Image and up to 3 Additional Images.

Kling V3 Standard - Motion Control

Model ID: model_kling-v3-standard-motion-control

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Text prompt describing the desired motion or action.
`image`	Character Image	`file`	None	None	None	None	Required. Character image; this character will perform the reference movements.
`video`	Reference Video	`file`	None	None	None	None	Required. Reference video with motion to transfer (.mp4, .mov, .webm, .m4v, .gif).
`characterOrientation`	Character Orientation	`string`	video	None	None	image, video	Orientation of the character (Image or Video).
`keepOriginalSound`	Keep Original Sound	`boolean`	true	None	None	None	Whether to keep the original sound from the reference video.
`elements`	Element	`inputs_array`	[]	None	4	None	Optional elements (max 4) with additional reference images.

Kling O1 Reference Video

Model ID: model_kling-o1-video-reference

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Use @Element1, @Image1 syntax
`video`	Reference Video	`assetId`	None	None	None	None	Required. MP4 or MOV
`images`	Reference Images	`assetId[]`	None	None	4	None	Optional style references
`keepAudio`	Keep Audio	`boolean`	true	None	None	None	Keeps original video audio
`elements`	Elements	`object[]`	None	None	2	See below	Characters or objects

Kling O1 Video Editing

Model ID: model_kling-o1-video-edit

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Use @Element1, @Image1 syntax
`video`	Input Video	`assetId`	None	None	None	None	Required. MP4 or MOV
`images`	Reference Images	`assetId[]`	None	None	4	None	Style or appearance references
`keepAudio`	Keep Audio	`boolean`	true	None	None	None	Retains original audio
`elements`	Elements	`object[]`	None	None	2	See below	Characters or objects

Kling O1 Reference Images

Model ID: model_kling-o1-r2v

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Use @Image1, @Element1, etc
`images`	Reference Images	`assetId[]`	None	None	7	None	Style or appearance references
`duration`	Duration	`string`	5	None	None	5, 10	Video length in seconds
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	9:16, 1:1, 16:9	Ignored if a start image is provided
`elements`	Elements	`object[]`	None	None	3	See below	Characters or objects used in video

Kling O1 I2V

Model ID: model_kling-o1-i2v

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	None	None	Required text instruction, max 2048 chars
`image`	First Frame	`assetId`	None	None	None	None	Required. First frame of the video
`lastFrameImage`	Last Frame	`assetId`	None	None	None	None	Optional second keyframe
`duration`	Duration	`string`	5	None	None	5, 10	Duration of generated video in seconds

Kling V2.6 Motion Control

Model ID: model_kling-v2-6-motion-control

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Text prompt to guide the generation
`image`	Reference Image	`assetId`	None	None	None	None	Required. Defines character appearance
`video`	Reference Video	`assetId`	None	None	None	None	Required. Motion source video
`characterOrientation`	Character Orientation	`string`	image	None	None	image, video	Indicates whether the character comes from the image or the video
`mode`	Mode	`string`	pro	None	None	pro, std	Selects Pro or Standard quality
`keepOriginalSound`	Keep Original Sound	`boolean`	true	None	None	None	Keeps the original audio from the reference video

Kling V2.6 I2V Pro

Model ID: model_kling-v2-6-i2v-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	None	None	Required text prompt for video generation
`image`	First Frame	`assetId`	None	None	None	None	Required. First frame of the video
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Generates audio natively
`duration`	Duration	`string`	5	None	None	5, 10	Video duration in seconds
`negativePrompt`	Negative Prompt	`string`	None	None	None	None	Optional

Kling V2.6 T2V Pro

Model ID: model_kling-v2-6-t2v-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	None	None	Required text prompt for video generation
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Generates native audio in Chinese or English
`duration`	Duration	`string`	5	None	None	5, 10	Video duration in seconds
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	9:16, 1:1, 16:9	Output video ratio
`cfgScale`	Guidance	`number`	0.5	0	1	None	Higher values follow prompt more closely
`negativePrompt`	Negative Prompt	`string`	None	None	None	None	Optional negative guidance

Kling 2.5 Turbo Image to Video Pro

Model ID: model_kling-v2-5-i2v-turbo-pro

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`imageUrl`	`assetId`	``	Image used as the first frame of the video.
`lastFrame`	`assetId`	``	Image used as the last frame of the video.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`duration`	`string`	`5`	Duration in seconds [5,10]

Kling 2.5 Turbo Image to Video Standard

Model ID: model_kling-v2-5-i2v-turbo-standard

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`duration`	`string`	`5`	Duration in seconds [5,10]

Kling 2.5 Turbo Text to Video

Model ID: model_kling-v2-5-t2v-turbo-pro

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`duration`	`string`	`5`	Duration in seconds [5,10]
`negativePrompt`	`string`	``	Negative prompt used to guide the model away from undesirable features.

Kling 2.1 Master

Model ID: model_kling-v2-1-master

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`startImage`	`assetId`	``	Image used as the first frame of the video.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`duration`	`number`	`5`	Duration in seconds

Kling 2.1 Pro

Model ID: model_kling-v2-1-pro

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`startImage`	`assetId`	``	Image used as the first frame of the video.
`endImage`	`assetId`	``	Image used as the last frame of the video.
`duration`	`number`	`5`	Duration in seconds [5 or 10]
`cfgScale`	`number`	`0.5`	Higher values follow the prompt more closely, lower values are more creative [0,1]
`negativePrompt`	`string`	``	Negative prompt used to guide the model away from undesirable features.

Kling 2.1

Model ID: model_kling-v2-1

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`startImage`	`assetId`	``	Image used as the first frame of the video.
`mode`	`string`	`standard`	Standard has a resolution of 720p, pro is 1080p. Both are 24fps.
`duration`	`number`	`5`	Duration in seconds

Kling Lipsync

Model ID: model_kling-lip-sync

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`videoUrl`	Video	`assetId`	–	–	–	–	2-10s, <100MB, 720p–1080p
`audioFile`	Lip Sync Audio File	`assetId`	–	–	–	–	required if text not provided
`text`	Lip Sync Text	`string`	–	–	–	–	required if audio not provided
`voiceId`	AI Voice List	`string`	en_AOT	–	–	(40+ voices available)	used when text provided
`voiceSpeed`	Voice Speed	`number`	1	0.8	2	–

Kling AI Avatar Pro

Model ID: model_kling-video-ai-avatar-pro

Input	Label	Type	Default	Notes
`imageUrl`	Image	`assetId`	–	required avatar image
`audioUrl`	Audio	`assetId`	–	required
`text`	Add Description	`string`	–	optional cue

Kling 2.0

Model ID:model_kling-v2-0

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`startImage`	`assetId`	``	Image used as the first frame of the video.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`cfgScale`	`number`	`0.5`	Higher values follow the prompt more closely, lower values are more creative [0,1]
`duration`	`number`	`5`	Duration in seconds

Kling 1.6 Pro

Model ID: model_kling-v1-6-pro

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`startImage`	`assetId`	``	Image used as the first frame of the video.
`endImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`referenceImages`	`assetId_array`	``	Use up to 4 reference images (scene elements) for video generation. Start/end images are ignored when using references.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`cfgScale`	`number`	`0.5`	Higher values follow the prompt more closely, lower values are more creative
`duration`	`number`	`5`	Duration in seconds

Kling 1.6

Model ID: model_kling-v1-6-standard

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`startImage`	`assetId`	``	Image used as the first frame of the video.
`referenceImages`	`assetId_array`	``	Use up to 4 reference images (scene elements) for video generation. Start/end images are ignored when using references.
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`cfgScale`	`number`	`0.5`	Higher values follow the prompt more closely, lower values are more creative
`duration`	`number`	`5`	Duration in seconds

LTX

LTX 2.3 Pro

Model ID: model_ltx-2-3-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Text prompt describing the video to generate.
`startImage`	First Frame	`file`	None	None	None	None	First frame image for image-to-video.
`endImage`	End Frame	`file`	None	None	None	None	Optional end frame for interpolation. Video interpolates between first and last frame.
`resolution`	Resolution	`string`	1080p	None	None	1080p, 2k, 4k	Video resolution. Note: audio_to_video, retake, and extend are 1080p only.
`duration`	Duration	`number`	6	None	None	6, 8, 10	Duration of the video in seconds.
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 9:16	Aspect ratio of the generated video.
`fps`	FPS	`number`	25	None	None	24, 25, 48, 50	Frame rate in frames per second.
`cameraMotion`	Camera Motion	`string`	none	None	None	none, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Camera motion effect to apply to the generated video.
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Generate synchronized audio for the video.

LTX 2.3 Fast

Model ID: model_ltx-2-3-fast

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Text prompt describing the video to generate.
`startImage`	First Frame	`file`	None	None	None	None	First frame image for image-to-video generation.
`endImage`	End Frame	`file`	None	None	None	None	End frame for interpolation (requires first frame).
`resolution`	Resolution	`string`	1080p	None	None	1080p, 2k, 4k	Video resolution. Durations >10s only at 1080p.
`duration`	Duration	`number`	6	None	None	6, 8, 10, 12, 14, 16, 18, 20	Duration of the video in seconds.
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 9:16	Aspect ratio of the generated video.
`fps`	FPS	`number`	25	None	None	24, 25, 48, 50	Frame rate in frames per second.
`cameraMotion`	Camera Motion	`string`	none	None	None	none, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, focus_shift	Camera motion effect to apply.
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Generate synchronized audio for the video.

LTX-2 19b

Model ID: model_ltx-2-19b

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	5000	None	Required. Text prompt for video generation (1-5000 characters)
`image`	First Frame	`assetId`	None	None	None	None	Input image for image-to-video (applied at frame 0). Leave empty for text-to-video.
`imageStrength`	Strength	`number`	1	0	1	None	Image conditioning strength (0-1) for image-to-video.
`negativePrompt`	Negative Prompt	`string`	None	None	5000	None	What to avoid in generation
`duration`	Duration	`number`	6	3	20	None	Video duration in seconds. Durations below 6s may produce lower quality.
`aspectRatio`	Aspect Ratio	`string`	auto	None	None	auto, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9	Video aspect ratio. 'Match Input' detects from input image.
`resolution`	Resolution	`string`	1080p	None	None	720p, 1080p, 1440p, 2160p	Video resolution. Ignored if width and height are provided.
`width`	Width	`number`	None	64	4096	None	Explicit video width in pixels. Must be used with height. Rounded to multiple of 64.
`height`	Height	`number`	None	64	4096	None	Explicit video height in pixels. Must be used with width. Rounded to multiple of 64.
`fps`	Frame Rate	`number`	25	1	60	None	Frame rate in frames per second (1-60)
`cameraMotion`	Camera Motion	`string`	none	None	None	none, static, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down	Camera movement type in the generated video
`cameraMotionStrength`	Camera Motion Strength	`number`	1	0	2	None	Strength of camera motion (0-2)
`numInferenceSteps`	Steps	`number`	40	1	100	None	Number of inference steps. Higher = better quality, slower.
`guidanceScale`	Guidance	`number`	3	1	20	None	Guidance scale. Higher = stronger prompt adherence.
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Whether to generate synchronized audio
`enhancePrompt`	Enhance Prompt	`boolean`	false	None	None	None	Enhance the prompt for better video generation
`seed`	Seed	`number`	None	0	None	None	Random seed for reproducibility. Leave blank for random.

LTX-2 19b Fast

Model ID: model_ltx-2-19b-fast

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	5000	None	Required. Text prompt for video generation (1-5000 characters)
`image`	First Frame	`assetId`	None	None	None	None	Input image for image-to-video (applied at frame 0). Leave empty for text-to-video.
`imageStrength`	Strength	`number`	1	0	1	None	Image conditioning strength (0-1) for image-to-video.
`duration`	Duration	`number`	6	3	20	None	Video duration in seconds (3-20). Durations below 6s may produce lower quality. >10s only at 1080p/25fps.
`aspectRatio`	Aspect Ratio	`string`	auto	None	None	auto, 21:9, 16:9, 4:3, 3:4, 1:1, 9:16	Video aspect ratio. 'Match Input' detects from input image.
`resolution`	Resolution	`string`	1080p	None	None	720p, 1080p, 1440p, 2160p	Video resolution. Ignored if width and height are provided.
`width`	Width	`number`	None	64	4096	None	Explicit video width in pixels. Must be used with height. Rounded to multiple of 64.
`height`	Height	`number`	None	64	4096	None	Explicit video height in pixels. Must be used with width. Rounded to multiple of 64.
`fps`	Frame Rate	`number`	25	1	60	None	Frame rate in frames per second (1-60)
`cameraMotion`	Camera Motion	`string`	none	None	None	none, static, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down	Camera movement type in the generated video
`cameraMotionStrength`	Camera Motion Strength	`number`	1	0	2	None	Strength of camera motion (0-2)
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Whether to generate synchronized audio
`enhancePrompt`	Enhance Prompt	`boolean`	false	None	None	None	Enhance the prompt for better video generation
`seed`	Seed	`number`	None	0	None	None	Random seed for reproducibility. Leave blank for random.

LTX-2 19b Extend Video

Model ID: model_ltx-2-19b-extend-video

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	5000	None	Required. Text prompt describing how the video should continue
`video`	Input Video	`assetId`	None	None	None	None	Required. Input video to extend. The model generates continuation frames based on this video.
`videoStrength`	Video Strength	`number`	1	0	1	None	Video conditioning strength. Higher = more faithful to input video motion/style.
`extendDuration`	Extend Duration	`number`	4	1	20	None	Duration of new video to generate in seconds. Additional duration added after the input video.
`contextDuration`	Context Duration	`number`	None	0.1	None	None	Seconds from input video to use as context. Leave empty to use entire video.
`aspectRatio`	Aspect Ratio	`string`	auto	None	None	auto, 21:9, 16:9, 4:3, 3:4, 1:1, 9:16	Video aspect ratio. 'Match Input' detects from input video.
`resolution`	Resolution	`string`	auto	None	None	auto, 720p, 1080p, 1440p, 2160p	Video resolution. 'Match Input' replicates input video dimensions (recommended for extend).
`width`	Width	`number`	None	64	4096	None	Explicit video width in pixels. Must be used with height. Rounded to multiple of 64.
`height`	Height	`number`	None	64	4096	None	Explicit video height in pixels. Must be used with width. Rounded to multiple of 64.
`fps`	FPS	`number`	None	1	60	None	Output frame rate (1-60 fps). Leave empty to match input video.
`numInferenceSteps`	Steps	`number`	40	1	100	None	Number of denoising steps (more = higher quality, slower)
`guidanceScale`	Guidance	`number`	3	1	20	None	Classifier-free guidance scale (higher = more prompt adherence)
`cameraMotion`	Camera Motion	`string`	none	None	None	none, static, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down	Camera movement type in the generated continuation
`cameraMotionStrength`	Camera Motion Strength	`number`	1	0	2	None	Strength of camera motion
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Whether to generate synchronized audio
`audioStrength`	Audio Strength	`number`	1	0	1	None	Audio conditioning strength (0-1). Higher preserves more input audio characteristics.
`enhancePrompt`	Enhance Prompt	`boolean`	false	None	None	None	Enhance the prompt for better video generation
`seed`	Seed	`number`	None	0	None	None	Random seed for reproducibility. Leave blank for random.
`negativePrompt`	Negative Prompt	`string`	None	None	5000	None	What to avoid in generation

LTX-2 19b Keyframes to Video

Model ID: model_ltx-2-19b-keyframes-to-video

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	5000	None	Required. Text prompt describing the video content and transitions.
`keyframes`	Keyframes	`inputs_array`	None	2	None	None	Required. List of keyframe images with timestamps and strengths. At least 2 required.
`negativePrompt`	Negative Prompt	`string`	None	None	5000	None	Negative prompt to guide what to avoid in generation.
`resolution`	Resolution	`string`	1080p	None	None	720p, 1080p, 1440p, 2160p	Video resolution. Ignored if width and height are provided.
`width`	Width	`number`	None	64	4096	None	Explicit video width in pixels. Must be used with height.
`height`	Height	`number`	None	64	4096	None	Explicit video height in pixels. Must be used with width.
`cameraMotion`	Type	`string`	none	None	None	none, static, dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down	Camera movement type in the generated video.
`cameraMotionStrength`	Strength	`number`	1	0	2	None	Strength of camera motion. Higher values = stronger effect.
`duration`	Duration	`number`	6	3	20	None	Video duration in seconds. Durations below 6s may produce lower quality.
`aspectRatio`	Aspect Ratio	`string`	auto	None	None	auto, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9	'Match Input' (auto) detects from first keyframe image.
`fps`	Frame Rate	`number`	25	1	60	None	Frame rate in frames per second.
`numInferenceSteps`	Steps	`number`	40	1	100	None	Number of inference steps. Higher = better quality, slower.
`guidanceScale`	Guidance	`number`	3	1	20	None	CFG guidance scale. Higher = stronger prompt adherence.
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Whether to generate synchronized audio.
`enhancePrompt`	Enhance Prompt	`boolean`	false	None	None	None	Use Gemma to enhance the prompt for better video generation.
`seed`	Seed	`number`	None	0	None	None	Random seed for reproducibility. Leave blank for random.

Runway

Runway Gen4.5

Model ID: model_runway-gen4-5

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	1000	None	Required. Describe your video
`image`	First Frame	`assetId`	None	None	None	None	Image used as the first frame of the video.
`aspectRatio`	Aspect Ratio	`string`	1280:720	None	None	1584:672, 1280:720, 1104:832, 960:960, 832:1104, 720:1280, 672:1584	Aspect ratio of the video. Ignored if first frame is provided. For Text to Video, only 16:9 and 9:16 are supported.
`duration`	Duration	`number`	5	2	10	None	Duration in seconds
`seed`	Seed	`number`	None	0	4294967295	None	Use a seed for reproducible results. Leave blank to use a random seed.

Runway Gen4 Turbo

Model ID: model_runway-gen4-turbo

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`duration`	`number`	`5`	Duration in seconds
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Bytedance

Seedance 1.5 Pro

Model ID: model_bytedance-seedance-1-5-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Describe the video to generate
`image`	First Frame	`assetId`	None	None	None	None	Optional. Required if `lastFrameImage` is provided
`lastFrameImage`	Last Frame	`assetId`	None	None	None	None	Optional. Only works if a first frame is provided
`duration`	Duration	`number`	5	2	12	None	Duration of the video in seconds
`resolution`	Resolution	`string`	720p			1080p, 720p, 480p	Output resolution
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	9:21, 9:16, 3:4, 1:1, 4:3, 16:9, 21:9	Ignored if a first frame image is provided
`cameraFixed`	Camera Fixed	`boolean`	false	None	None	None	Fixes the camera position
`generateAudio`	Generate Audio	`boolean`	true	None	None	None	Enables audio generation
`seed`	Seed	`number`	None	None	None	None	Optional seed for reproducible results

Seedance 1 Pro Fast

Model ID: model_bytedance-seedance-1-pro-fast

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`duration`	`number`	`5`	Duration in seconds
`resolution`	`string`	`1080p`	Output video resolution
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`cameraFixed`	`boolean`	`False`	Whether to fix camera position
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Seedance 1 Pro

Model ID: model_bytedance-seedance-1-pro

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`lastFrameImage`	`assetId`	``	Image used as the last frame of the video.
`duration`	`number`	`5`	Duration in seconds
`resolution`	`string`	`1080p`	Output video resolution
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`cameraFixed`	`boolean`	`False`	Whether to fix camera position
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Seedance 1 Lite

Model ID: model_bytedance-seedance-1-lite

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`referenceImages1	`assetIds[]`	``	Reference images to guide video generation for characters, avatars, clothing, environments, or multi-character interactions.
`duration`	`number`	`5`	Duration in seconds
`resolution`	`string`	`1080p`	Output video resolution
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video. Ignored if first frame is provided.
`cameraFixed`	`boolean`	`False`	Whether to fix camera position
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Google VEO

VEO3.1 Fast

Model ID: model_veo3-1-fast

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	First Frame of your video
`lastFrameImage`	`assetId`	``	Last Frame of your video
`negativePrompt`	`string`	``	Negative text prompt
`resolution`	`string`	`720p`	Resolution of the generated video . `"allowedValues": ["720p", "1080p"]`
`generateAudio`	`boolean`	`true`	Generate audio for the video
`aspectRatio`	`string`	`16:9`	Aspect ratio for the generated video. If the aspect ratio of the input image does not match the selected video ratio, the model may crop the image to fit. `"allowedValues": ["16:9", "9:16"]`
`duration`	`number`	`8`	Video duration. `"allowedValues": [4, 6, 8]`
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

VEO3.1

Model ID: model_veo3-1

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280, depending on the aspect ratio you choose.
`lastFrameImage`	`assetId`	``	Last frame of the video to start generating from. When provided with an input image, creates a transition between the two images.
`referenceImages`	`assetId[]`	``	1 to 3 reference images for subject-consistent generation (reference-to-video, or R2V).
`referenceImagesType`	`string`	`ASSET`	The type of the reference image, which defines how the reference image will be used to generate the video. ASSET is a reference image that provides assets to the generated video, such as the scene, an object, a character, etc. STYLE is A reference image that provides aesthetics including colors, lighting, texture, etc., to be used as the style of the generated video, such as 'anime', 'photography', 'origami', etc. `"allowedValues": ["ASSET", "GUIDANCE"]`
`negativePrompt`	`string`	``	Negative text prompt
`resolution`	`string`	`720p`	Resolution of the generated video . `"allowedValues": ["720p", "1080p"]`
`generateAudio`	`boolean`	`true`	Generate audio for the video
`aspectRatio`	`string`	`16:9`	Aspect ratio for the generated video. If the aspect ratio of the input image does not match the selected video ratio, the model may crop the image to fit. `"allowedValues": ["16:9", "9:16"]`
`duration`	`number`	`8`	Video duration. `"allowedValues": [4, 6, 8]`
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

VEO3 Fast

Model ID: model_veo3-fast

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

VEO3

Model ID: model_veo3

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280, depending on the aspect ratio you choose.
`generateAudio`	`boolean`	`True`	Generate audio for the video
`aspectRatio`	`string`	`16:9`	Video aspect ratio
`duration`	`number`	`8`	Video duration
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

VEO2

Model ID: model_veo2

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280, depending on the aspect ratio you choose.
`aspectRatio`	`string`	`16:9`	Video aspect ratio
`duration`	`number`	`5`	Video duration
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Luma

Luma Ray 2 540p

Model ID: model_luma-ray-2-540p

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`endImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`duration`	`number`	`5`	Duration in seconds
`aspectRatio`	`string`	`16:9`	Aspect ratio of the generated video
`loop`	`boolean`	`False`	Matches the first and last frames for smooth, seamless looping.
`concepts`	`string_array`	``	List of camera concepts to apply to the video generation.

Luma Ray 2 Flash 540p

Model ID: model_luma-ray-flash-2-540p

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video
`endImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`duration`	`number`	`5`	Duration in seconds
`aspectRatio`	`string`	`16:9`	Aspect ratio of the generated video
`loop`	`boolean`	`False`	Matches the first and last frames for smooth, seamless looping.
`concepts`	`string_array`	``	List of camera concepts to apply to the video generation.

Luma Ray 2 720p

Model ID: model_luma-ray-2-720p

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`endImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`duration`	`number`	`5`	Duration in seconds
`aspectRatio`	`string`	`16:9`	Aspect ratio of the generated video
`loop`	`boolean`	`False`	Matches the first and last frames for smooth, seamless looping.
`concepts`	`string_array`	``	List of camera concepts to apply to the video generation.

Luma Ray 2 Flash 720p

Model ID: model_luma-ray-flash-2-720p

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.e
`endImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`duration`	`number`	`5`	Duration in seconds
`aspectRatio`	`string`	`16:9`	Aspect ratio of the generated video
`loop`	`boolean`	`False`	Matches the first and last frames for smooth, seamless looping.
`concepts`	`string_array`	``	List of camera concepts to apply to the video generation

Veed

Veed Fabric 1.0

Model ID: model_veed-fabric-1-0

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`image`	Image	`assetId`	None	None	None	None	Required. Input image used as the visual source
`audioUrl`	Audio	`assetId`	None	None	None	None	Required. Input audio used to drive speech and motion
`resolution`	Resolution	`string`	720p	None	None	480p, 720p	Output video resolution

Vidu

Vidu Q3 Turbo I2V

Model ID: model_vidu-i2v-q3-turbo

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`generationType`	Generation Type	`string`	image_to_video	None	None	image_to_video, start_end_to_video	Required. Select the type of video generation. For Image to Video, use only one image. For Start/End to Video, use two images.
`images`	Images	`assetId[]`	None	None	2	None	Required. For Image to Video, use only one image. For Start/End to Video, use two images: the first as the start frame and the second as the end frame.
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation.
`duration`	Duration	`number`	5	1	16	None	Video duration in seconds.
`resolution`	Resolution	`string`	720p	None	None	540p, 720p, 1080p	Video resolution.
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video.
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q3 Pro I2V

Model ID: model_vidu-i2v-q3-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`generationType`	Generation Type	`string`	image_to_video	None	None	image_to_video, start_end_to_video	Required. Select the type of video generation. For Image to Video, use only one image. For Start/End to Video, use two images.
`images`	Images	`assetId[]`	None	None	2	None	Required. For Image to Video, use only one image. For Start/End to Video, use two images: the first as the start frame and the second as the end frame.
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation
`duration`	Duration	`number`	5	1	16	None	Video duration in seconds
`resolution`	Resolution	`string`	720p	None	None	540p, 720p, 1080p	Video resolution
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q3 Turbo T2V

Model ID: model_vidu-t2v-q3-turbo

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`		None	2000	None	Text prompt describing the desired video generation
`resolution`	Resolution	`string`	720p	None	None	540p, 720p, 1080p	Video resolution
`duration`	Duration	`number`	5	1	16	None	Video duration in seconds
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 9:16, 1:1, 3:4, 4:3	Aspect ratio of the output video
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q3 Pro T2V

Model ID: model_vidu-t2v-q3-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation
`resolution`	Resolution	`string`	720p	None	None	540p, 720p, 1080p	Video resolution
`duration`	Duration	`number`	5	1	16	None	Video duration in seconds
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 9:16, 1:1, 3:4, 4:3	Aspect ratio of the output video
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q2 T2V

Model ID: model_vidu-t2v-q2

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation
`resolution`	Resolution	`string`	720p	None	None	540p, 720p, 1080p	Video resolution
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 9:16, 1:1, 3:4, 4:3	Aspect ratio of the output video
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q2 Pro Reference2V

Model ID: model_vidu-reference2v-q2-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`images`	Reference Images	`assetId[]`	None	None	7	None	Add up to 7 reference images for your video. Required if `videos` is not defined.
`videos`	Reference Videos	`assetId[]`	None	None	2	None	Add up to 2 reference videos for your video. Must provide either this or images. Required if `images` is not defined. Video resolution cannot be less than 128*128, aspect ratio must be between 1:4 and 4:1, and size must not exceed 100M.
`prompt`	Prompt	`string`	None	None	5000	None	Required. Text prompt describing the desired video generation
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds (1-10)
`resolution`	Resolution	`string`	1080p	None	None	540p, 720p, 1080p	Video resolution
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 1:1, 9:16	Aspect ratio of the output video.
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q2 Pro Reference2V

Model ID: model_vidu-reference2v-q2

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`images`	Reference Images	`assetId[]`	None	None	7	None	Add up to 7 reference images for your video. Required if `videos` is not defined.
`videos`	Reference Videos	`assetId[]`	None	None	2	None	Add up to 2 reference videos for your video. Must provide either this or images. Required if `images` is not defined.
`prompt`	Prompt	`string`	None	None	5000	None	Required. Text prompt describing the desired video generation
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds (1-10)
`resolution`	Resolution	`string`	1080p	None	None	540p, 720p, 1080p	Video resolution
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 1:1, 9:16	Aspect ratio of the output video.
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q2 Turbo I2V

Model ID: model_vidu-i2v-q2-pro-turbo

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`generationType`	Generation Type	`string`	image_to_video	None	None	image_to_video, start_end_to_video	Required. Select the type of video generation. For Image to Video, use only one image. For Start/End to Video, use two images.
`images`	Images	`assetId[]`	None	None	2	None	Required. For Image to Video, use only one image. For Start/End to Video, use two images: the first as the start frame and the second as the end frame.
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds (1-10 for image-to-video, 1-8 for start-end)
`resolution`	Resolution	`string`	720p	None	None	720p, 1080p	Video resolution
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video. Does not take effect for 9 or 10 seconds.
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q2 Pro Fast I2V

Model ID: model_vidu-i2v-q2-pro-fast

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`generationType`	Generation Type	`string`	image_to_video	None	None	image_to_video, start_end_to_video	Required. Select the type of video generation. For Image to Video, use only one image. For Start/End to Video, use two images.
`images`	Images	`assetId[]`	None	None	2	None	Required. For Image to Video, use only one image. For Start/End to Video, use two images: the first as the start frame and the second as the end frame.
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds (1-10 for image-to-video, 1-8 for start-end)
`resolution`	Resolution	`string`	720p	None	None	720p, 1080p	Video resolution
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video. Does not take effect for 9 or 10 seconds.
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Vidu Q2 Pro I2V

Model ID: model_vidu-i2v-q2-pro

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`generationType`	Generation Type	`string`	image_to_video	None	None	image_to_video, start_end_to_video	Required. Select the type of video generation. For Image to Video, use only one image. For Start/End to Video, use two images.
`images`	Images	`assetId[]`	None	None	2	None	Required. For Image to Video, use only one image. For Start/End to Video, use two images: the first as the start frame and the second as the end frame.
`prompt`	Prompt	`string`		None	5000	None	Text prompt describing the desired video generation
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds (1-10 for image-to-video, 1-8 for start-end)
`resolution`	Resolution	`string`	720p	None	None	720p, 1080p	Video resolution
`audio`	Audio	`boolean`	false	None	None	None	Whether to add background music to the generated video. Does not take effect for 9 or 10 seconds.
`seed`	Seed	`number`	None	None	None	None	Use a seed for reproducible results. Leave blank to use a random seed.

Pixverse

Pixverse v5

Model ID: model_pixverse-v5

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`lastFrameImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`quality`	`string`	`540p`	Video resolution ["360p", "540p", "720p", "1080p"]
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video ["9:16", "1:1", "16:9"]
`duration`	`number`	`5`	Duration in seconds.
`effect`	`string`	`None`	Special effect to apply to the video
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Pixverse v4.5

Model ID: model_pixverse-v4-5

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`lastFrameImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`quality`	`string`	`540p`	Video resolution
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video
`duration`	`number`	`5`	Duration in seconds. (1080p does not support 8 second duration)
`motionMode`	`string`	`normal`	Motion mode for the video. Smooth videos generate more frames, so they cost more. (smooth is only available when using a 5 second duration, 1080p does not support smooth motion)
`style`	`string`	`None`	Style of the video
`effect`	`string`	`None`	Special effect to apply to the video
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Pixverse v4

Model ID: model_pixverse-v4

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`lastFrameImage`	`assetId`	``	Used to generate a video that transitions from the first frame to this image. Requires a first frame image.
`quality`	`string`	`540p`	Video resolution
`aspectRatio`	`string`	`16:9`	Aspect ratio of the video
`duration`	`number`	`5`	Duration in seconds. (1080p does not support 8 second duration)
`motionMode`	`string`	`normal`	Motion mode for the video. Smooth videos generate more frames, so they cost more. (smooth is only available when using a 5 second duration, 1080p does not support smooth motion)
`style`	`string`	`None`	Style of the video
`effect`	`string`	`None`	Special effect to apply to the video
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan

Wan 2.6 T2V

Model ID: model_wan-2-6-t2v

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required text prompt for video generation
`audio`	Audio	`assetId`	None	None	None	None	Optional audio file for voice or music synchronization
`negativePrompt`	Negative Prompt	`string`	None	None	2048	None	Optional negative guidance
`size`	Resolution	`string`	1280*720	None	None	1280_720, 720_1280, 1920_1080, 1080_1920	Video resolution and aspect ratio
`duration`	Duration	`number`	5	None	None	5, 10, 15	Duration in seconds
`enablePromptExpansion`	Enable Prompt Expansion	`boolean`	true	None	None	None	Enables prompt optimization
`multiShots`	Multi Shots	`boolean`	true	None	None	None	Enables intelligent multi shot segmentation
`seed`	Seed	`number`	None	None	None	None	Optional reproducibility seed

Wan 2.6 I2V

Model ID: model_wan-2-6-i2v

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`image`	Image	`assetId`	None	None	None	None	Required input image for video generation
`prompt`	Prompt	`string`	None	None	2048	None	Required text prompt
`audio`	Audio	`assetId`	None	None	None	None	Optional audio file for synchronization
`negativePrompt`	Negative Prompt	`string`	None	None	2048	None	Optional negative guidance
`resolution`	Resolution	`string`	720p	None	None	720p, 1080p	Output video resolution
`duration`	Duration	`number`	5	None	None	5, 10, 15	Duration in seconds
`enablePromptExpansion`	Enable Prompt Expansion	`boolean`	true	None	None	None	Enables prompt optimization
`multiShots`	Multi Shots	`boolean`	true	None	None	None	Enables intelligent multi shot segmentation
`seed`	Seed	`number`	None	None	None	None	Optional reproducibility seed

Wan 2.2 – Vace Fun A14B Reframe

Model ID: model_wan-2-2-vace-fun-a14b-reframe

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`videoUrl`	Video	`assetId`	–	–	–	–	Required input video
`prompt`	Prompt	`string`	–	–	–	–	Text prompt for video generation (max 2048 chars)
`negativePrompt`	Negative Prompt	`string`	–	–	–	–	Negative text prompt (max 2048 chars)
`matchInputNumFrames`	Match Input Num Frames	`boolean`	false	–	–	–	Match input video frame count
`numFrames`	Number of Frames	`number`	81	81	241	–	Frames to generate
`matchInputFramesPerSecond`	Match Input FPS	`boolean`	false	–	–	–	If true, FPS matches input
`framesPerSecond`	Frames Per Second	`number`	16	5	30	–	FPS for output (ignored if matchInputFramesPerSecond=true)
`resolution`	Resolution	`string`	720p	–	–	720p, 580p, 480p	Output resolution
`aspectRatio`	Aspect Ratio	`string`	auto	–	–	auto, 16:9, 1:1, 9:16	Output aspect ratio
`numInferenceSteps`	Steps	`number`	30	2	50	–	Inference steps
`guidanceScale`	Guidance	`number`	5	1	10	–	Guidance scale
`enablePromptExpansion`	Enable Prompt Expansion	`boolean`	false	–	–	–	Expands/augments prompt automatically
`acceleration`	Acceleration	`string`	regular	–	–	regular, none	Processing acceleration mode
`videoQuality`	Video Quality	`string`	high	–	–	maximum, high, medium, low	Output video quality
`videoWriteMode`	Video Write Mode	`string`	balanced	–	–	balanced, fast, small	Video writing mode
`numInterpolatedFrames`	Number of Interpolated Frames	`number`	1	0	5	–	Interpolated frames between originals
`interpolatorModel`	Interpolator Model	`string`	film	–	–	film, rife	Frame interpolation method
`zoomFactor`	Zoom Factor	`number`	0	0	0.9	–	Zooms into video (cutting edges). 0 = none
`trimBorders`	Trim Borders	`boolean`	true	–	–	–	Trims borders from the video
`temporalDownsampleFactor`	Temporal Downsample Factor	`number`	0	0	5	–	Skips frames. 0 = none
`seed`	Seed	`number`	–	–	–	–	Optional reproducibility seed

Wan 2.2 – Vace Fun A14B Outpainting

Model ID: model_wan-2-2-vace-fun-a14b-outpainting

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	–	–	–	–	Required text prompt (max 2048 chars)
`videoUrl`	Video	`assetId`	–	–	–	–	Required input video
`expandLeft`	Expand Left	`boolean`	true	–	–	–	Expand video to the left
`expandRight`	Expand Right	`boolean`	true	–	–	–	Expand video to the right
`expandTop`	Expand Top	`boolean`	true	–	–	–	Expand video upwards
`expandBottom`	Expand Bottom	`boolean`	true	–	–	–	Expand video downwards
`expandRatio`	Expand Ratio	`number`	0.25	0	1	–	0.25 = +25% expansion on sides
`negativePrompt`	Negative Prompt	`string`	–	–	–	–	Negative text prompt (max 2048 chars)
`refImageUrls`	Reference Images	`assetId array`	[]	–	10	–	Up to 10 reference images
`matchInputNumFrames`	Match Input Num Frames	`boolean`	false	–	–	–	Match input video frame count
`numFrames`	Number of Frames	`number`	81	81	241	–	Number of frames generated
`matchInputFramesPerSecond`	Match Input FPS	`boolean`	false	–	–	–	If true, matches FPS from input
`framesPerSecond`	Frames Per Second	`number`	16	5	30	–	FPS for output (ignored if matchInputFramesPerSecond=true)
`resolution`	Resolution	`string`	720p	–	–	720p, 580p, 480p	Output resolution
`aspectRatio`	Aspect Ratio	`string`	auto	–	–	auto, 16:9, 1:1, 9:16	Output aspect ratio
`numInferenceSteps`	Steps	`number`	30	2	50	–	Inference steps
`guidanceScale`	Guidance	`number`	5	1	10	–	Guidance scale
`enablePromptExpansion`	Enable Prompt Expansion	`boolean`	false	–	–	–	Expands/augments prompt automatically
`acceleration`	Acceleration	`string`	regular	–	–	regular, none	Processing acceleration mode
`videoQuality`	Video Quality	`string`	high	–	–	maximum, high, medium, low	Output video quality
`videoWriteMode`	Video Write Mode	`string`	balanced	–	–	balanced, fast, small	Video writing mode
`numInterpolatedFrames`	Number of Interpolated Frames	`number`	1	0	5	–	Interpolated frames between originals
`interpolatorModel`	Interpolator Model	`string`	film	–	–	film, rife	Interpolation method
`seed`	Seed	`number`	–	–	–	–	Optional reproducibility seed

Wan 2.5 Image to Video

Model ID: model_wan-2-5-t2v

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`audio`	`assetId`	``	Audio file for voice/music synchronization. 3-30s, ≤15MB.
`image`	`assetId`	``	Image to use for your video
`negativePrompt`	`string`	``	Negative prompt used to guide the model away from undesirable features.
`resolution`	`string`	`720p`	Video resolution and aspect ratio. ["480p", "720p", "1080p"]
`duration`	`number`	`5`	Video duration
`enablePromptExpansion`	`boolean`	`true`	Whether to enable prompt rewriting using LLM.
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan 2.5 Text to Video

Model ID: model_wan-2-5-t2v

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`audio`	`assetId`	``	Audio file for voice/music synchronization. 3-30s, ≤15MB.
`negativePrompt`	`string`	``	Negative prompt used to guide the model away from undesirable features.
`size`	`string`	`1280x720`	Video resolution and aspect ratio. [ "832_480", "480_832", "1280_720", "720_1280", "1920_1080", "1080_1920"],
`duration`	`number`	`5`	Video duration
`enablePromptExpansion`	`boolean`	`true`	Whether to enable prompt rewriting using LLM.
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan 2.2 A14b Image to Video

Model ID: model_wan-2-2-i2v-a14b

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`lastImage`	`assetId`	``	Input image for last frame generation. This only works if an image start frame is given too.
`numFrames`	`number`	`81`	Number of video frames. 81 frames give the best results
`resolution`	`string`	`720p`	Video resolution - `720p` or `480p`
`framesPerSecond`	`number`	`16`	Frames per second
`fastMode`	`string`	`Balanced`	Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
`sampleSteps`	`number`	`30`	Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
`sampleShift`	`number`	`5`	Sample shift factor
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan 2.2 Text to Video

Model ID: model_wan-2-2-t2v

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`resolution`	`string`	`720p`	Video resolution - `720p` or `480p`
`numFrames`	`number`	`81`	Video duration in frames (based on standard 16fps playback)
`framesPerSecond`	`number`	`16`	Frames per second. [5,30]
`sampleShift`	`number`	`8`	Sampling shift factor for flow matching (recommended range: 8-12)
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan 2.1.1 3b

Model ID: model_wan-2-1-1-3b

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`aspectRatio`	`string`	`16:9`	Video aspect ratio
`frameNum`	`number`	`81`	Video duration in frames (based on standard 16fps playback)
`sampleSteps`	`number`	`30`	Number of sampling steps (higher = better quality but slower)
`sampleGuideScale`	`number`	`6`	Higher values follow the prompt more closely, lower values are more creative
`sampleShift`	`number`	`8`	Sampling shift factor for flow matching (recommended range: 8-12)
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan 2.1 720p

Model ID: model_wan-2-1-i2v-720p

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`numFrames`	`number`	`81`	Number of video frames. 81 frames give the best results
`maxArea`	`string`	`1280x720`	Maximum area of generated image. The input image will shrink to fit these dimensions
`framesPerSecond`	`number`	`16`	Frames per second
`fastMode`	`string`	`Balanced`	Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
`sampleSteps`	`number`	`30`	Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
`sampleGuideScale`	`number`	`5`	Higher values follow the prompt more closely, lower values are more creative
`sampleShift`	`number`	`5`	Sample shift factor
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Wan 2.1 480p

Model ID: model_wan-2-1-i2v-480p

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`image`	`assetId`	``	Image used as the first frame of the video.
`numFrames`	`number`	`81`	Number of video frames. 81 frames give the best results
`maxArea`	`string`	`832x480`	Maximum area of generated image. The input image will shrink to fit these dimensions
`framesPerSecond`	`number`	`16`	Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
`fastMode`	`string`	`Balanced`	Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
`sampleSteps`	`number`	`30`	Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
`sampleGuideScale`	`number`	`5`	Higher values follow the prompt more closely, lower values are more creative
`sampleShift`	`number`	`3`	Sample shift factor
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Minimax

Minimax Hailuo 2.3

Model ID: model_minimax-hailuo-2-3

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`firstFrameImage`	`assetId`	``	Image used as the first frame of the video.
`duration`	`number`	`6`	Duration of the video in seconds. 10 seconds is only available for 768p resolution. `"allowedValues": [6, 10]`
`resolution`	`string`	`1080p`	Pick between standard 768p, or pro 1080p resolution. The pro model is not just high resolution, it is also higher quality. `"allowedValues": ["768p", "1080p"]`
`promptOptimizer`	`boolean`	`True`	Use prompt optimizer

Minimax Hailuo 2.3 Fast

Model ID: model_minimax-hailuo-2-3-fast

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`firstFrameImage`	`assetId`	``	Image used as the first frame of the video.
`duration`	`number`	`6`	Duration of the video in seconds. 10 seconds is only available for 768p resolution. `"allowedValues": [6, 10]`
`resolution`	`string`	`1080p`	Pick between standard 768p, or pro 1080p resolution. The pro model is not just high resolution, it is also higher quality. `"allowedValues": ["768p", "1080p"]`
`promptOptimizer`	`boolean`	`True`	Use prompt optimizer

Minimax Hailuo 02

Model ID: model_minimax-hailuo-02

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`firstFrameImage`	`assetId`	``	Image used as the first frame of the video.
`lastFrameImage`	`assetId`	``	Image used as the last frame of the video.
`duration`	`number`	`6`	Duration of the video in seconds. 10 seconds is only available for 768p resolution.
`resolution`	`string`	`1080p`	Pick between standard 768p, or pro 1080p resolution. The pro model is not just high resolution, it is also higher quality. `"allowedValues": ["768p", "1080p"]`
`promptOptimizer`	`boolean`	`True`	Use prompt optimizer

Minimax Video

Model ID: model_minimax-video-01

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`firstFrameImage`	`assetId`	``	Image used as the first frame of the video.
`subjectReference`	`assetId`	``	An optional character reference image to use as the subject in the generated video
`promptOptimizer`	`boolean`	`True`	Use prompt optimizer

Minimax Director

Model ID: model_minimax-video-01-director

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video. Try Prompt Spark or check our Help Center for detailed prompt tips for this model.
`firstFrameImage`	`assetId`	``	Image used as the first frame of the video.
`promptOptimizer`	`boolean`	`True`	Use prompt optimizer

Minimax Live

Model ID: model_minimax-video-01-live

Parameter	Type	Default	Description
`image`	`assetId`	``	Image used as the first frame of the video.
`prompt`	`string`	``	Describe your video
`promptOptimizer`	`boolean`	`True`	Use prompt optimizer

Hunyuan Video

Model ID: model_hunyuan-video

Parameter	Type	Default	Description
`prompt`	`string`	``	Describe your video
`width`	`number`	`864`	Width of the video in pixels (must be divisible by 16)
`height`	`number`	`480`	Height of the video in pixels (must be divisible by 16)
`videoLength`	`number`	`129`	Number of frames to generate (must be 4k+1, ex: 49 or 129)
`inferSteps`	`number`	`50`	Number of denoising steps
`embeddedGuidanceScale`	`number`	`6`	Higher values follow the prompt more closely, lower values are more creative
`fps`	`number`	`24`	Frames per second of the output video
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.

Pruna

P-Video

Model ID: model_p-video

Input	Label	Type	Default	Min	Max	Allowed Values	Notes
`prompt`	Prompt	`string`	None	None	2048	None	Required. Text prompt for video generation.
`image`	Image	`file`	None	None	None	None	Input image to generate video from.
`audio`	Audio	`file`	None	None	None	None	Input audio to condition video generation.
`duration`	Duration	`number`	5	1	10	None	Video duration in seconds. Ignored if audio is provided.
`aspectRatio`	Aspect Ratio	`string`	16:9	None	None	16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16	Ignored when an input image is provided.
`resolution`	resolution	`string`	720p	None	None	720p, 1080p	Resolution of the output video.
`fps`	FPS	`number`	24	None	None	24, 48	Frames per second of the video.
`draft`	Draft	`boolean`	false	None	None	None	Generates a lower-quality preview of the video.
`promptUpsampling`	Prompt Upsampling	`boolean`	true	None	None	None	Use upsampling to enhance the input prompt.
`saveAudio`	Save Audio	`boolean`	true	None	None	None	Save the video with audio.
`seed`	Seed	`number`	None	None	None	None	Set for reproducible generation.

Framepack

Model ID: model_framepack

Parameter	Type	Default	Description
`image`	`assetId`	``	Image used as the first frame of the video
`prompt`	`string`	``	Describe your video
`videoLength`	`number`	`5`	Duration in seconds
`steps`	`number`	`25`	Number of steps. Recommended value: 25
`cfgScale`	`number`	`10`	Distilled CFG scale. Recommended value: 10
`teaCache`	`boolean`	`True`	Makes generation faster with minimal quality impact
`seed`	`number`	``	Use a seed for reproducible results. Leave blank to use a random seed.