Video
Flux 3
flux-3-image-to-videoFlux 3's image-to-video variant animates a single still image into a 5- to 20-second clip at up to 4K, with synchronized audio.
Cost depends on the request settings
AI video generation models_
A video model turns a description, and a source image when supported, into a clip. Check which inputs the model accepts before choosing it. Available durations, resolutions and controls vary by model, so a single headline price does not tell the whole story.
HOW TO COMPARE PRICING
Video cost depends on the selected duration and generation settings. Choose a model, set up the clip and select Create. Cost is calculated automatically and appears beside the result. Generation can take time; its status and result appear in your workspace history. Funds reserved during processing are shown separately from completed charges.
Choose a model and send your request from the workspace. Its cost is calculated automatically and appears beside the result and in your history. Availability, capabilities and rates can change; check the selected model before sending a request.
// LIVE_CATALOG
AVAILABLE MODELS
140 models in this category · Updated:
Video
Flux 3
flux-3-text-to-videoFlux 3 is Black Forest Labs' video model with synchronized audio. This text-to-video variant generates 5- to 20-second clips at up to 4K.
Cost depends on the request settings
Video
Flux 3 Extend
flux-3-extend-videoFlux 3 Extend continues an existing clip beyond its final frame, adding 5 to 20 seconds at up to 4K with synchronized audio.
Cost depends on the request settings
Video
Flux 3 First Last Frame
flux-3-first-last-frame-to-videoFlux 3 First Last Frame generates the transition between a start frame and an end frame, as a 5- to 20-second clip at up to 4K with synchronized audio.
Cost depends on the request settings
Video
Flux 3 Max
flux-3-max-image-to-videoFlux 3 Max's image-to-video variant animates a still image, with an optional end frame, into a 5- to 20-second clip at up to 1080p with synchronized audio.
Cost depends on the request settings
Video
Flux 3 Max
flux-3-max-text-to-videoFlux 3 Max is Black Forest Labs' post-trained Flux 3 video model, built for high visual quality at high speed. This text-to-video variant generates 5- to 20-second clips at up to 1080p with synchronized audio.
Cost depends on the request settings
Video
Gemini Omni Flash
gemini-omni-flash-image-to-videoGemini Omni Flash's image-to-video variant animates a starting image into a 4- to 10-second clip, using Google's Gemini Omni Flash video model.
Cost depends on the request settings
Video
Gemini Omni Flash
gemini-omni-flash-text-to-videoGemini Omni Flash is Google's video model for 4- to 10-second clips from text prompts. Gemini Omni Flash 1.1 is its newer successor.
Cost depends on the request settings
Video
Gemini Omni Flash 1.1
gemini-omni-flash-1-1-image-to-videoGemini Omni Flash 1.1's image-to-video variant animates a starting image into a 4- to 10-second clip at up to 4K, using Google's Gemini Omni Flash 1.1 video model.
Cost depends on the request settings
Video
Gemini Omni Flash 1.1
gemini-omni-flash-1-1-text-to-videoGemini Omni Flash 1.1 is Google's video model; this text-to-video variant turns prompts into 4- to 10-second clips at up to 4K. Sibling variants cover image-to-video, reference-to-video and video editing.
Cost depends on the request settings
Video
Gemini Omni Flash 1.1 Edit
gemini-omni-flash-1-1-video-to-videoGemini Omni Flash 1.1 Edit rewrites an existing clip from a text instruction, keeping its length, at up to 4K. It's the video editing variant of Google's Gemini Omni Flash 1.1.
Cost depends on the request settings
Video
Gemini Omni Flash 1.1 R2V
gemini-omni-flash-1-1-reference-to-videoGemini Omni Flash 1.1 R2V combines several reference images of characters, objects or styles into one 4- to 10-second clip at up to 4K, using Google's Gemini Omni Flash 1.1.
Cost depends on the request settings
Video
Gemini Omni Flash R2V
gemini-omni-flash-reference-to-videoGemini Omni Flash R2V combines several reference images into one 4- to 10-second clip, using Google's Gemini Omni Flash video model.
Cost depends on the request settings
Video
Grok Imagine
grok-imagine-image-to-video-privateGrok Imagine's image-to-video variant turns a starting image into a 1- to 15-second clip at up to 720p, with native audio.
Cost depends on the request settings
Video
Grok Imagine
grok-imagine-text-to-video-privateGrok Imagine is xAI's video model, generating 1- to 15-second clips at up to 720p from text, with native audio.
Cost depends on the request settings
Video
Grok Imagine
grok-imagine-video-to-video-privateGrok Imagine's video editing variant changes an existing clip from text instructions, in 5-, 10- or 15-second results at up to 720p, with native audio.
Cost depends on the request settings
Video
Grok Imagine 1.5
grok-imagine-1-5-image-to-video-privateGrok Imagine 1.5's image-to-video variant turns a starting image into a 1- to 15-second clip at up to 1080p, with native audio.
Cost depends on the request settings
Video
Grok Imagine 1.5
grok-imagine-1-5-text-to-video-privateGrok Imagine 1.5 is xAI's updated video model, generating 1- to 15-second clips at up to 1080p from text, with native audio.
Cost depends on the request settings
Video
Grok Imagine 1.5 Lite
grok-imagine-1-5-lite-image-to-videoGrok Imagine 1.5 Lite's image-to-video variant quickly turns a starting image into a 1- to 15-second clip at up to 1080p, with native audio.
Cost depends on the request settings
Video
Grok Imagine 1.5 Lite
grok-imagine-1-5-lite-text-to-videoGrok Imagine 1.5 Lite is a quicker, more affordable version of xAI's Grok Imagine 1.5, generating 1- to 15-second clips at up to 1080p from text, with native audio.
Cost depends on the request settings
Video
Grok Imagine 1.5 R2V
grok-imagine-1-5-reference-to-video-privateGrok Imagine 1.5 R2V generates 1- to 15-second clips at up to 720p from up to 7 reference images, with native audio.
Cost depends on the request settings
Video
Grok Imagine R2V
grok-imagine-reference-to-video-privateGrok Imagine R2V generates 1- to 10-second clips at up to 720p from several reference images, which you cite in the prompt as @Image1, @Image2 and so on.
Cost depends on the request settings
Video
HappyHorse 1.0
happyhorse-1-0-image-to-videoHappyHorse 1.0's image-to-video variant animates a starting image into a 3- to 15-second clip at up to 1080p, with native audio.
Cost depends on the request settings
Video
HappyHorse 1.0
happyhorse-1-0-text-to-videoHappyHorse 1.0 is Alibaba's video model with native audio. This text-to-video variant generates high-fidelity 3- to 15-second clips at up to 1080p.
Cost depends on the request settings
Video
HappyHorse 1.0 Edit
happyhorse-1-0-video-to-videoHappyHorse 1.0 Edit changes an existing video from text instructions, with optional reference images, at up to 1080p with native audio.
Cost depends on the request settings
Video
HappyHorse 1.0 Reference
happyhorse-1-0-reference-to-videoHappyHorse 1.0 Reference generates 3- to 15-second clips at up to 1080p from reference images, keeping characters and subjects consistent, with native audio.
Cost depends on the request settings
Video
HappyHorse 1.1
happyhorse-1-1-image-to-videoHappyHorse 1.1's image-to-video variant animates a starting image into a 3- to 15-second clip at up to 1080p, with native audio and multilingual lip-sync.
Cost depends on the request settings
Video
HappyHorse 1.1
happyhorse-1-1-text-to-videoHappyHorse 1.1 is Alibaba's video model, with synchronized native audio and multilingual lip-sync. This text-to-video variant generates 3- to 15-second clips at up to 1080p.
Cost depends on the request settings
Video
HappyHorse 1.1 Reference
happyhorse-1-1-reference-to-videoHappyHorse 1.1 Reference builds 3- to 15-second clips at up to 1080p from reference images, keeping characters consistent, with native audio and multilingual lip-sync.
Cost depends on the request settings
Video
Kling 2.5 Turbo Pro
kling-2.5-turbo-pro-image-to-videoKling 2.5 Turbo Pro's image-to-video variant animates a starting image into a 5- or 10-second clip.
Cost depends on the request settings
Video
Kling 2.5 Turbo Pro
kling-2.5-turbo-pro-text-to-videoKling 2.5 Turbo Pro is Kling AI's full-quality Kling 2.5 video model, generating 5- or 10-second clips from text.
Cost depends on the request settings
Video
Kling 2.6 Pro
kling-2.6-pro-image-to-videoKling 2.6 Pro's image-to-video variant animates a starting image into a 5- or 10-second clip, with optional native audio.
Cost depends on the request settings
Video
Kling 2.6 Pro
kling-2.6-pro-text-to-videoKling 2.6 Pro is Kling AI's full-quality video model with native audio generation. This text-to-video variant generates 5- or 10-second clips, with optional audio.
Cost depends on the request settings
Video
Kling 4.0
kling-v4-image-to-videoKling 4.0's image-to-video variant animates a starting image, with optional end-frame control, into a 3- to 30-second clip at 720p or 1080p with native audio and multi-shot prompts.
Cost depends on the request settings
Video
Kling 4.0
kling-v4-text-to-videoKling 4.0 is Kling AI's fourth-generation video model. This text-to-video variant generates 3- to 30-second clips at 720p or 1080p with native audio, and supports multi-shot prompts.
Cost depends on the request settings
Video
Kling 4.0 Flash
kling-v4-flash-image-to-videoKling 4.0 Flash's image-to-video variant animates a start frame into a 3- to 20-second clip at 720p with native audio.
Cost depends on the request settings
Video
Kling 4.0 Flash
kling-v4-flash-text-to-videoKling 4.0 Flash is a faster version of Kling AI's Kling 4.0, generating 3- to 20-second clips at 720p from text with native audio.
Cost depends on the request settings
Video
Kling 4.0 Flash Edit
kling-v4-flash-video-to-videoKling 4.0 Flash Edit changes a source video from a text instruction and up to 10 reference images, at 720p with native audio. The output follows the length of the source video.
Cost depends on the request settings
Video
Kling 4.0 Flash R2V
kling-v4-flash-reference-to-videoKling 4.0 Flash R2V generates 3- to 20-second clips at 720p with native audio from up to 10 reference images and 5 reference videos, with an optional start frame.
Cost depends on the request settings
Video
Kling 4.0 R2V
kling-v4-reference-to-videoKling 4.0 R2V generates 3- to 30-second clips at 720p or 1080p with native audio from up to 10 reference images and 5 reference videos, with an optional start frame and multi-shot prompts.
Cost depends on the request settings
Video
Kling O3 4K
kling-o3-4k-image-to-videoKling O3 4K's image-to-video variant animates a starting image, with an optional end image, into native 4K stylized or anime motion, in 3- to 15-second clips.
Cost depends on the request settings
Video
Kling O3 4K
kling-o3-4k-text-to-videoKling O3 4K generates native 4K video with Kling AI's O3 model, tuned for stylized and anime looks. This text-to-video variant makes 3- to 15-second clips, with optional audio.
Cost depends on the request settings
Video
Kling O3 4K R2V
kling-o3-4k-reference-to-videoKling O3 4K R2V combines up to 7 character, object or style references into a single native 4K clip of 3 to 15 seconds, with optional audio.
Cost depends on the request settings
Video
Kling O3 Pro
kling-o3-pro-image-to-videoKling O3 Pro's image-to-video variant animates a starting image, with an optional end image, into a 3- to 15-second clip, with optional audio.
Cost depends on the request settings
Video
Kling O3 Pro
kling-o3-pro-text-to-videoKling O3 Pro is the premium tier of Kling AI's O3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.
Cost depends on the request settings
Video
Kling O3 Pro R2V
kling-o3-pro-reference-to-videoKling O3 Pro R2V turns images and elements into 3- to 15-second clips with stable character identity, using a frontal image and reference images for each element.
Cost depends on the request settings
Video
Kling O3 Standard
kling-o3-standard-image-to-videoKling O3 Standard's image-to-video variant animates a starting image, with an optional end image, into a 3- to 15-second clip, with optional audio.
Cost depends on the request settings
Video
Kling O3 Standard
kling-o3-standard-text-to-videoKling O3 Standard is the balanced tier of Kling AI's O3 video model, trading some quality for speed. This text-to-video variant generates 3- to 15-second clips, with optional audio.
Cost depends on the request settings
Video
Kling O3 Standard R2V
kling-o3-standard-reference-to-videoKling O3 Standard R2V turns images and elements into 3- to 15-second clips with stable character identity, at the Standard tier's balance of quality and speed.
Cost depends on the request settings
Video
Kling V3 4K
kling-v3-4k-text-to-videoKling V3 4K generates video at native 4K without upscaling, using Kling AI's V3 model. This text-to-video variant makes 3- to 15-second clips, with optional audio.
Cost depends on the request settings
Video
Kling V3 4K R2V
kling-v3-4k-reference-to-videoKling V3 4K R2V animates a start frame into native 4K video, using reference elements to keep characters and objects consistent, in 3- to 15-second clips with optional audio.
Cost depends on the request settings
Video
Kling V3 Pro
kling-v3-pro-image-to-videoKling V3 Pro's image-to-video variant animates a start frame, with an optional end frame, into a 3- to 15-second clip, with optional audio.
Cost depends on the request settings
Video
Kling V3 Pro
kling-v3-pro-text-to-videoKling V3 Pro is the enhanced-quality tier of Kling AI's V3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.
Cost depends on the request settings
Video
Kling V3 Pro Motion Control
kling-v3-pro-motion-controlKling V3 Pro Motion Control transfers the movements in a reference video onto a character image, at Kling V3 Pro quality. The output follows the length of the source video.
Cost depends on the request settings
Video
Kling V3 Standard
kling-v3-standard-image-to-videoKling V3 Standard's image-to-video variant animates a start frame, with an optional end frame, into a 3- to 15-second clip, with optional audio.
Cost depends on the request settings
Video
Kling V3 Standard
kling-v3-standard-text-to-videoKling V3 Standard is the balanced tier of Kling AI's V3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.
Cost depends on the request settings
Video
Kling V3 Standard Motion Control
kling-v3-standard-motion-controlKling V3 Standard Motion Control transfers the movements in a reference video onto a character image, a cost-effective option for portraits and simple animations. The output follows the length of the source video.
Cost depends on the request settings
Video
Kling V3 Turbo Pro
kling-v3-turbo-pro-image-to-videoKling V3 Turbo Pro's image-to-video variant animates a start frame into a 3- to 15-second clip at 1080p, with multi-shot storyboards.
Cost depends on the request settings
Video
Kling V3 Turbo Pro
kling-v3-turbo-pro-text-to-videoKling V3 Turbo Pro is a faster version of Kling V3 Pro, generating 3- to 15-second clips at 1080p from text, with multi-shot storyboards.
Cost depends on the request settings
Video
Kling V3 Turbo Standard
kling-v3-turbo-standard-image-to-videoKling V3 Turbo Standard's image-to-video variant animates a start frame into a 3- to 15-second clip at 720p, with multi-shot storyboards.
Cost depends on the request settings
Video
Kling V3 Turbo Standard
kling-v3-turbo-standard-text-to-videoKling V3 Turbo Standard is a faster, cost-effective version of Kling V3, generating 3- to 15-second clips at 720p from text, with multi-shot storyboards.
Cost depends on the request settings
VideoUNCENSORED
Longcat Distilled
longcat-distilled-image-to-videoLongcat Distilled is the faster, distilled version of Meituan's open-weight LongCat-Video model. This image-to-video variant animates a starting image into a 5- to 30-second clip at 720p.
Cost depends on the request settings
VideoUNCENSORED
Longcat Distilled
longcat-distilled-text-to-videoLongcat Distilled is the faster, distilled version of Meituan's open-weight LongCat-Video model. This text-to-video variant generates 5- to 30-second clips at 720p.
Cost depends on the request settings
VideoUNCENSORED
Longcat Full Quality
longcat-image-to-videoLongcat Full Quality runs Meituan's open-weight LongCat-Video model at full quality, built for longer clips. This image-to-video variant animates a starting image into a 5- to 30-second clip at 720p.
Cost depends on the request settings
VideoUNCENSORED
Longcat Full Quality
longcat-text-to-videoLongcat Full Quality runs Meituan's open-weight LongCat-Video model at full quality, built for longer clips. This text-to-video variant generates 5- to 30-second clips at 720p.
Cost depends on the request settings
Video
LTX Video 2.3 Fast
ltx-2-v2-3-fast-image-to-videoLTX Video 2.3 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.3 video model. This image-to-video variant animates a starting image into a 6- to 20-second clip at up to 4K, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.3 Fast
ltx-2-v2-3-fast-text-to-videoLTX Video 2.3 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.3 video model. This text-to-video variant generates 6- to 20-second clips at up to 4K, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.3 Full Quality
ltx-2-v2-3-full-image-to-videoLTX Video 2.3 Full Quality runs Lightricks' open-weight LTX-2.3 at full quality. This image-to-video variant animates a starting image into a 6-, 8- or 10-second clip at up to 4K, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.3 Full Quality
ltx-2-v2-3-full-text-to-videoLTX Video 2.3 Full Quality runs Lightricks' open-weight LTX-2.3 at full quality. This text-to-video variant generates 6-, 8- or 10-second clips at up to 4K, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.5 Fast
ltx-2-5-fast-image-to-videoLTX Video 2.5 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.5 video model. This image-to-video variant animates a starting image into a 6- to 20-second clip at up to 4K, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.5 Fast
ltx-2-5-fast-text-to-videoLTX Video 2.5 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.5 video model. This text-to-video variant generates 6- to 20-second clips at up to 4K, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.5 Pro
ltx-2-5-pro-image-to-videoLTX Video 2.5 Pro is the quality-focused tier of Lightricks' open-weight LTX-2.5. This image-to-video variant animates a starting image into a 6-, 8- or 10-second clip at up to 1080p, with optional audio.
Cost depends on the request settings
Video
LTX Video 2.5 Pro
ltx-2-5-pro-text-to-videoLTX Video 2.5 Pro is the quality-focused tier of Lightricks' open-weight LTX-2.5. This text-to-video variant generates 6-, 8- or 10-second clips at up to 1080p, with optional audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3
minimax-h3-image-to-videoMiniMax H3's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 2K with native audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3
minimax-h3-text-to-videoMiniMax H3, also called Hailuo 3, is MiniMax's video model. This text-to-video variant generates 5- to 15-second clips at up to 2K with native audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Enhanced
minimax-h3-enhanced-text-to-videoMiniMax H3 Enhanced is a version of MiniMax's H3 (Hailuo 3) tuned for uncensored output. This text-to-video variant generates 5- to 15-second clips at up to 2K with native audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max
minimax-h3-max-image-to-videoMiniMax H3 Max's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 1080p with native stereo audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max
minimax-h3-max-text-to-videoMiniMax H3 Max is a post-trained variant of MiniMax's H3 video model. This text-to-video variant generates 5- to 15-second clips at up to 1080p with native stereo audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max Multi-Angle
minimax-h3-max-multi-angleMiniMax H3 Max Multi-Angle moves a virtual camera around a single image, with precise control of orbit, elevation and distance, producing 5- to 15-second clips at up to 1080p with native audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max R2V
minimax-h3-max-reference-to-videoMiniMax H3 Max R2V generates 5- to 15-second clips at up to 1080p from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and so on, with native audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max Recast
minimax-h3-max-recastMiniMax H3 Max Recast replaces the people in a source video with people from reference photos, preserving the original motion, camera, cuts and soundtrack, at up to 1080p.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max Turbo
minimax-h3-max-turbo-image-to-videoMiniMax H3 Max Turbo's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 1080p with native stereo audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 Max Turbo
minimax-h3-max-turbo-text-to-videoMiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, generating 5- to 15-second clips at up to 1080p from text with native stereo audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 R2V
minimax-h3-reference-to-videoMiniMax H3 R2V generates 5- to 15-second clips at up to 2K from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and so on, with native audio.
Cost depends on the request settings
VideoUNCENSORED
MiniMax H3 R2V Enhanced
minimax-h3-enhanced-reference-to-videoMiniMax H3 R2V Enhanced generates uncensored 5- to 15-second clips at up to 2K from reference images and audio, with native audio.
Cost depends on the request settings
VideoUNCENSORED
Ovi
ovi-image-to-videoOvi is Character.AI's open-weight audio-video model, based on Wan, that animates a starting image into a 5-second clip with native audio. It runs fast and is served uncensored.
Cost depends on the request settings
Video
PixVerse C1
pixverse-c1-image-to-videoPixVerse C1's image-to-video variant animates a starting image into a cinematic 3- to 15-second clip at up to 1080p, with optional native audio.
Cost depends on the request settings
Video
PixVerse C1
pixverse-c1-text-to-videoPixVerse C1 is PixVerse's film-grade video model, generating 3- to 15-second clips at up to 1080p from text, with optional native audio.
Cost depends on the request settings
Video
PixVerse C1 R2V
pixverse-c1-reference-to-videoPixVerse C1 R2V generates character-consistent 3- to 15-second clips at up to 1080p from reference images of subjects and backgrounds, with optional native audio.
Cost depends on the request settings
Video
PixVerse C1 Transition
pixverse-c1-transitionPixVerse C1 Transition creates a seamless cinematic transition between a start image and an end image, as a 3- to 15-second clip at up to 1080p, with optional native audio.
Cost depends on the request settings
Video
PixVerse v5.6
pixverse-v5.6-image-to-videoPixVerse v5.6's image-to-video variant animates a starting image into a 5- or 8-second clip at up to 1080p, with optional audio.
Cost depends on the request settings
Video
PixVerse v5.6
pixverse-v5.6-text-to-videoPixVerse v5.6 is PixVerse's video model. This text-to-video variant generates 5- or 8-second clips at up to 1080p, with optional audio.
Cost depends on the request settings
Video
PixVerse v5.6 Transition
pixverse-v5.6-transitionPixVerse v5.6 Transition creates a smooth transition between a start image and an end image, as a 5- or 8-second clip at up to 1080p, with optional audio.
Cost depends on the request settings
Video
Runway Gen-4 Turbo
runway-gen4-turboRunway Gen-4 Turbo is a faster version of Runway's Gen-4 video model, animating a starting image into a 2- to 10-second clip.
Cost depends on the request settings
Video
Runway Gen-4.5
runway-gen4-5Runway Gen-4.5 is Runway's video model. This image-to-video variant animates a starting image into a 2- to 10-second clip.
Cost depends on the request settings
Video
Runway Gen-4.5
runway-gen4-5-textRunway Gen-4.5's text-to-video variant generates 2- to 10-second clips from prompts of up to 1,000 characters, using Runway's Gen-4.5 video model.
Cost depends on the request settings
Video
Seedance 2.0
seedance-2-0-image-to-video-basicSeedance 2.0's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 4K, with optional synchronized dialogue and sound.
Cost depends on the request settings
Video
Seedance 2.0
seedance-2-0-text-to-video-basicSeedance 2.0 is ByteDance Seed's cinematic video model, with native audio and lip-sync in more than eight languages. This text-to-video variant generates 4- to 15-second clips at up to 4K.
Cost depends on the request settings
Video
Seedance 2.0 Fast
seedance-2-0-fast-image-to-video-basicSeedance 2.0 Fast's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 720p, with optional synchronized audio.
Cost depends on the request settings
Video
Seedance 2.0 Fast
seedance-2-0-fast-text-to-video-basicSeedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0, generating 4- to 15-second clips at up to 720p from text, with optional native audio and lip-sync.
Cost depends on the request settings
Video
Seedance 2.0 Fast R2V
seedance-2-0-fast-reference-to-video-basicSeedance 2.0 Fast R2V is the reference-driven variant of Seedance 2.0 Fast, generating, editing or extending 4- to 15-second clips at up to 720p from reference images, videos and audio.
Cost depends on the request settings
Video
Seedance 2.0 Mini
seedance-2-0-mini-image-to-video-basicSeedance 2.0 Mini's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 720p, with optional native audio, for high-volume work.
Cost depends on the request settings
Video
Seedance 2.0 Mini
seedance-2-0-mini-text-to-video-basicSeedance 2.0 Mini is ByteDance Seed's cost-effective Seedance 2.0 model for high-volume video creation. This text-to-video variant generates 4- to 15-second clips at up to 720p, with optional native audio.
Cost depends on the request settings
Video
Seedance 2.0 Mini R2V
seedance-2-0-mini-reference-to-video-basicSeedance 2.0 Mini R2V is the reference-driven variant of Seedance 2.0 Mini, building 4- to 15-second clips at up to 720p from reference images, videos and audio.
Cost depends on the request settings
Video
Seedance 2.0 R2V
seedance-2-0-reference-to-video-basicSeedance 2.0 R2V builds 4- to 15-second clips at up to 4K from reference images, videos and audio, and can also edit or extend existing footage. It's the reference-driven variant of ByteDance Seed's Seedance 2.0.
Cost depends on the request settings
Video
Seedance 2.5
seedance-2-5-image-to-video-basicSeedance 2.5's image-to-video variant turns a starting image into a 4- to 30-second clip at up to 1080p, with optional native audio.
Cost depends on the request settings
Video
Seedance 2.5
seedance-2-5-text-to-video-basicSeedance 2.5 is the next generation of ByteDance Seed's cinematic video model, with native audio and stories of up to 30 seconds. This text-to-video variant generates 4- to 30-second clips at up to 1080p.
Cost depends on the request settings
Video
Seedance 2.5 Edit
seedance-2-5-edit-video-basicSeedance 2.5 Edit changes a 4- to 30-second source video by swapping subjects, objects or styles, while keeping its original motion, camera and length. Reference images are optional, and output is up to 1080p.
Cost depends on the request settings
Video
Seedance 2.5 R2V
seedance-2-5-reference-to-video-basicSeedance 2.5 R2V builds 4- to 30-second clips at up to 1080p from up to 30 reference images plus reference videos and audio, and can edit or extend footage. It's the reference-driven variant of ByteDance Seed's Seedance 2.5.
Cost depends on the request settings
Video
Topaz Video Upscale
topaz-video-upscaleTopaz Video Upscale uses Topaz Labs' upscaling to enlarge an existing video 2x or 4x while restoring detail. The output keeps the source video's length.
Cost depends on the request settings
Video
Veo 3.1 Fast
veo3.1-fast-image-to-videoVeo 3.1 Fast's image-to-video variant animates a starting image into a 4-, 6- or 8-second clip at up to 4K, with optional audio.
Cost depends on the request settings
Video
Veo 3.1 Fast
veo3.1-fast-text-to-videoVeo 3.1 Fast is a faster version of Google's Veo 3.1 video model. This text-to-video variant generates 4-, 6- or 8-second clips at up to 4K, with optional audio.
Cost depends on the request settings
Video
Veo 3.1 Full Quality
veo3.1-full-image-to-videoVeo 3.1 Full Quality's image-to-video variant animates a starting image into a 4-, 6- or 8-second clip at up to 4K, with optional audio.
Cost depends on the request settings
Video
Veo 3.1 Full Quality
veo3.1-full-text-to-videoVeo 3.1 Full Quality runs Google's Veo 3.1 video model at full quality. This text-to-video variant generates 4-, 6- or 8-second clips at up to 4K, with optional audio.
Cost depends on the request settings
Video
Vidu Q3
vidu-q3-image-to-videoVidu Q3's image-to-video variant animates a starting image into a 3- to 16-second clip at up to 1080p, with optional audio.
Cost depends on the request settings
Video
Vidu Q3
vidu-q3-text-to-videoVidu Q3 is Vidu's video model. This text-to-video variant generates 3- to 16-second clips at up to 1080p, with optional audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.2 Enhanced
wan-2-2-enhanced-image-to-videoWan 2.2 Enhanced is a version of Alibaba's Wan 2.2 for uncensored image-to-video, animating a starting image into a 5- or 8-second clip at up to 720p.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.5 Preview
wan-2.5-preview-image-to-videoWan 2.5 Preview is a preview release of Alibaba's Wan 2.5, served uncensored. This image-to-video variant animates a starting image into a 5- or 10-second clip at up to 1080p with native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.5 Preview
wan-2.5-preview-text-to-videoWan 2.5 Preview is a preview release of Alibaba's Wan 2.5, served uncensored. This text-to-video variant generates 5- or 10-second clips at up to 1080p with native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.6
wan-2.6-image-to-videoWan 2.6 is Alibaba's video model with audio support. This image-to-video variant animates a starting image into a 5-, 10- or 15-second clip at up to 1080p, with optional audio, and can follow an audio track you provide.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.6
wan-2.6-text-to-videoWan 2.6 is Alibaba's video model with audio support. This text-to-video variant generates 5-, 10- or 15-second clips at up to 1080p, with optional audio, and can follow an audio track you provide.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.6 Flash
wan-2.6-flash-image-to-videoWan 2.6 Flash is a fast version of Alibaba's Wan 2.6 for image-to-video, animating a starting image into a 5-, 10- or 15-second clip at up to 1080p with native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.7
wan-2-7-image-to-videoWan 2.7's image-to-video variant animates a starting image, or a first-and-last-frame pair, into an uncensored 5-, 10- or 15-second clip at up to 1080p. It can follow an audio track you provide.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.7
wan-2-7-text-to-videoWan 2.7 is Alibaba's video model, served uncensored, for high-fidelity text-to-video in 5-, 10- or 15-second clips at up to 1080p. It can follow an audio track you provide.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.7 Edit
wan-2-7-video-to-videoWan 2.7 Edit changes an existing video from text instructions, with an optional reference image, at up to 1080p. It's the uncensored editing variant of Alibaba's Wan 2.7.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.7 Enhanced
wan-2-7-enhanced-image-to-videoWan 2.7 Enhanced is a version of Alibaba's Wan 2.7 for uncensored video with native audio. This image-to-video variant animates a starting image into a 5-, 10- or 15-second clip at up to 1080p.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.7 Enhanced
wan-2-7-enhanced-text-to-videoWan 2.7 Enhanced is a version of Alibaba's Wan 2.7 for uncensored video with native audio. This text-to-video variant generates 5-, 10- or 15-second clips at up to 1080p.
Cost depends on the request settings
VideoUNCENSORED
Wan 2.7 Reference
wan-2-7-reference-to-videoWan 2.7 Reference generates uncensored 5- or 10-second clips at up to 1080p from reference images, keeping characters and subjects consistent, with native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0
wan-3-0-image-to-videoWan 3.0's image-to-video variant animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 1080p, with optional native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0
wan-3-0-text-to-videoWan 3.0 is Alibaba's video model, generating 2- to 30-second clips at up to 1080p from text, with optional native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Prime
wan-3-0-prime-image-to-videoWan 3.0 Prime's image-to-video variant quickly animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 1080p.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Prime
wan-3-0-prime-text-to-videoWan 3.0 Prime is a high-speed version of Alibaba's Wan 3.0, generating 2- to 30-second clips at up to 1080p from text much faster, with optional native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Prime Pro
wan-3-0-prime-pro-image-to-videoWan 3.0 Prime Pro's image-to-video variant quickly animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 4K.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Prime Pro
wan-3-0-prime-pro-text-to-videoWan 3.0 Prime Pro combines the speed of Wan 3.0 Prime with the 4K output of Wan 3.0 Pro, generating 2- to 30-second clips from text, with optional native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Prime Pro Reference
wan-3-0-prime-pro-reference-to-videoWan 3.0 Prime Pro Reference is the fastest 4K reference variant of Wan 3.0, building 2- to 30-second clips from reference images, videos and audio with consistent subjects.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Prime Reference
wan-3-0-prime-reference-to-videoWan 3.0 Prime Reference is the high-speed reference variant of Wan 3.0, building 2- to 30-second clips at up to 1080p from reference images, videos and audio with consistent subjects.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Pro
wan-3-0-pro-image-to-videoWan 3.0 Pro's image-to-video variant animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 4K.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Pro
wan-3-0-pro-text-to-videoWan 3.0 Pro is the highest-resolution tier of Alibaba's Wan 3.0, generating 2- to 30-second clips at up to 4K from text, with optional native audio.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Pro Reference
wan-3-0-pro-reference-to-videoWan 3.0 Pro Reference builds 2- to 30-second clips at up to 4K from reference images, videos and audio, keeping subjects consistent at the pixel level.
Cost depends on the request settings
VideoUNCENSORED
Wan 3.0 Reference
wan-3-0-reference-to-videoWan 3.0 Reference generates 2- to 30-second clips at up to 1080p from reference images, videos and audio, keeping subjects consistent at the pixel level.
Cost depends on the request settings
UNDERSTANDING UNCENSORED AND MAX
The UNCENSORED label comes from model specifications and identifies models designed for fewer refusals. It does not guarantee accuracy or an answer to every request. Max is a reasoning-effort setting on models that support it; each card lists the available modes. Rules and capabilities depend on the selected model.
OPEN THE INTERACTIVE CATALOG ↗