Model Capabilities

Video Editing

Edit an existing video by providing a source video along with your prompt. The model understands the video content and applies your requested changes.

The input video must have the .mp4 extension and be encoded with .mp4 supported codecs such as H.265 / H.264 / AV1, etc.
The maximum length of the input video provided via the video_url parameter is 8.7 seconds.
The duration, aspect_ratio, and resolution parameters are not supported for video editing; the output retains the duration and aspect ratio of the input, and matches its resolution, capped at 720p.

The demo below shows video editing in action. grok-imagine-video delivers high-fidelity edits with strong scene preservation, modifying only what you ask for while keeping the rest of the video intact:

In the Vercel AI SDK, video editing is triggered by setting providerOptions.xai.mode to "edit-video" and passing providerOptions.xai.videoUrl with a source video URL. The prompt describes the desired modifications; duration, aspectRatio, and resolution are ignored because the output inherits these properties from the input video, capped at 720p.

Concurrent Requests

When you need to apply several edits to the same source video, run requests concurrently. This is useful for branching multiple edits from the same intermediate result.

import os
import asyncio
import xai_sdk

async def edit_concurrently():
    client = xai_sdk.AsyncClient(api_key=os.getenv("XAI_API_KEY"))

    source_video = "https://data.x.ai/docs/video-generation/portrait-wave.mp4"

    prompts = [
        "Give the woman a silver necklace",
        "Change the color of the woman's outfit to red",
        "Give the woman a wide-brimmed black hat",
    ]

    tasks = [
        client.video.generate(
            prompt=prompt,
            model="grok-imagine-video",
            video_url=source_video,
        )
        for prompt in prompts
    ]

    results = await asyncio.gather(*tasks)

    for prompt, result in zip(prompts, results):
        print(f"{prompt}: {result.url}")

asyncio.run(edit_concurrently())

import { xai, type XaiVideoModelOptions } from "@ai-sdk/xai";
import { experimental_generateVideo as generateVideo } from "ai";

const providerOptions = {
    xai: {
        mode: "edit-video",
        videoUrl: "https://example.com/source-video.mp4",
        pollTimeoutMs: 600000,
    } satisfies XaiVideoModelOptions,
};

const step1 = await generateVideo({
    model: xai.video("grok-imagine-video"),
    prompt: "Add a party hat to the person",
    providerOptions,
});

const step1VideoUrl = step1.providerMetadata?.xai?.videoUrl as string;

const [withSunglasses, withScarf] = await Promise.all([
    generateVideo({
        model: xai.video("grok-imagine-video"),
        prompt: "Add sunglasses",
        providerOptions: {
            xai: {
                mode: "edit-video",
                videoUrl: step1VideoUrl,
                pollTimeoutMs: 600000,
            } satisfies XaiVideoModelOptions,
        },
    }),
    generateVideo({
        model: xai.video("grok-imagine-video"),
        prompt: "Add a scarf",
        providerOptions: {
            xai: {
                mode: "edit-video",
                videoUrl: step1VideoUrl,
                pollTimeoutMs: 600000,
            } satisfies XaiVideoModelOptions,
        },
    }),
]);

console.log(withSunglasses.providerMetadata?.xai?.videoUrl);
console.log(withScarf.providerMetadata?.xai?.videoUrl);

Video Generation — Generate videos from text prompts
Image-to-Video — Animate a still image
Video Extension — Extend existing videos
API Reference — Full endpoint documentation
Imagine API Landing Page — Showcase of the Imagine API in action

Did you find this page helpful?

Last updated: April 2, 2026

Model Capabilities

Video Editing

Concurrent Requests

Related