Access

AI video answer

Which AI video models accept a video reference?

Short answer

Current video-input routes include Runway's video-to-video endpoint and Wan 2.7 editing, reference-to-video, and continuation modes. The same provider can expose several video-input jobs with different fields and limits.

01

Use Runway for a direct video input

Runway's POST /v1/video_to_video endpoint accepts a source through videoUri. Aleph 2 input must be 2 to 30 seconds, no more than 30 FPS, and no larger than 1080p.

02

Use Wan editing for instruction-based change

Wan 2.7 videoedit accepts exactly one input video and up to four optional reference images. It supports instruction-based changes, style transfer, and reference-image edits at 720P or 1080P.

03

Use Wan references for a newly generated scene

Wan 2.7 reference-to-video can accept up to five combined reference images and videos. Name each Video 1 or Image 1 in the same order as the media array when several references are present.

Related guide

Get the full context.

Video-to-video API for editing, references, and continuation

Use a video-to-video API to edit footage, guide a new shot with a video reference, or continue a source clip with clear input and output rules.

Read the video to video API guide

Current prices

Compare each video route.

Open full pricing →
ModelCompared rateCre8vid price5 sec10 secSavings
MiniMax H3MiniMax$0.065$0.029$0.145$0.2955% less
Wan 3.0Alibaba$0.050$0.025$0.125$0.2550% less
Kling 3.0Kuaishou$0.084$0.039$0.195$0.3954% less
Seedance 2.5ByteDance$0.144$0.069$0.35$0.6952% less
Veo 3.1 Fast + audioGoogle$0.100$0.049$0.24$0.4951% less