Access

AI video answer

Does a video generation API support text and images?

Short answer

Many APIs support both text-to-video and image-to-video, while some also accept first and last frames, multiple images, video references, audio, or existing footage. The supported combination depends on the selected model and route.

01

Use text for a new scene

Text-to-video prompts define the subject, scene, physical action, camera, light, style, timing, and sound. The model invents the opening frame as well as the motion.

This mode gives more variation and works well when no approved composition exists yet.

02

Use an image for control

Image-to-video uses the source image as the opening frame or visual anchor. The prompt focuses on subject motion, scene reactions, camera movement, sound, and the final frame.

A clean, well-composed image can preserve product shape, wardrobe, identity, lighting, and scene design better than text alone.

03

Use advanced inputs when needed

First-and-last-frame mode controls both endpoints. Reference images or videos can guide identity, style, objects, voices, or movement. Video-to-video changes existing footage.

The API should expose only the controls supported by the chosen route and reject incompatible media before starting the job.

Related guide

Get the full context.

AI video generation API: five model routes

Generate AI video through one API with text-to-video, image-to-video, model routing, cost estimates, spending limits, normalized jobs, and fallback rules.

Read the video generation 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