Generate videos
$0.0150/1k tokensSeedance 2.5 Image-to-Video
Generate video with duration, resolution and native audio controls.
ByteDance
Image to video API for AI agents
Scrollport gives AI agents 2 tools to turn images into video, from ByteDance and xAI, through one connection. Prices are per 1k tokens or video second, depending on the tool, paid per use from one prepaid wallet with no subscription, provider accounts or API keys. Agents use them over MCP, the CLI or the HTTP API.
Updated
Turn images into video with Scrollport
Use verified tools with pay-per-use pricing. Provider access is included. Tools that work in your own apps ask you to connect that account.
Connect your first agent to receive $1 trial credit.
Compare Image to video API tools
Prices are per 1k tokens or video second, depending on the tool, so compare what each tool returns and a typical run's cost before choosing.
| Tool | Provider | What it returns | Price |
|---|---|---|---|
| Seedance 2.5 Image-to-Video | ByteDance | Generate video with duration, resolution and native audio controls. | $0.0150/1k tokens |
| Grok Imagine Video 1.5 Image-to-Video | xAI | Generate video from an input image and text prompt with duration and resolution controls. | $0.1960/video second |
2 available tools
Questions about Image to video API
How much do image to video API tools cost?
Prices are per 1k tokens or video second, depending on the tool. You pay per use from one prepaid wallet with no subscription. Your agent sees the exact price before each run, and connecting your first agent adds $1 of trial credit.
What is the best image to video API for an AI agent?
It depends on what you need back and how much you will run it. Seedance 2.5 Image-to-Video (ByteDance, $0.0150/1k tokens): Generate video with duration, resolution and native audio controls. Grok Imagine Video 1.5 Image-to-Video (xAI, $0.1960/video second): Generate video from an input image and text prompt with duration and resolution controls. Your agent can inspect the closest match and see its exact price before it runs.
Learn more about image-to-video generation
Treat the source image as the first frame of a shot. Tell your agent what should move, how the camera should behave and which visual details must remain stable.
Direct one clear shot
Describe subject motion, environmental motion and camera movement separately. A short, coherent action usually produces a more controllable result than several scene changes in one generation.
What makes a good source image for image-to-video?
Use a clean image with a readable subject, plausible depth and enough room for the intended movement. Avoid conflicting poses, cropped moving parts or details that must stay exact at very small scale.
Test motion before duration
Generate a short representative shot first. Review identity, geometry, camera direction, unwanted movement and the final frame before extending the duration or adding the shot to a sequence.
Example prompt
This example gives the agent separate subject and camera directions.
Example prompt to give your agent
Use Scrollport's Image-to-video tools to animate [SOURCE IMAGE] into a [DURATION] shot for [USE]. The subject should [SUBJECT MOTION], the environment should [ENVIRONMENTAL MOTION], and the camera should [CAMERA MOVEMENT]. Preserve [IDENTITY OR OBJECT DETAILS], avoid [UNWANTED MOTION], and show me the price before the paid run.