Grok

grok-imagine

Video APIHOT

Grok Video API gives teams an API-first way to use Grok Imagine video generation inside production workflows. It supports prompt-driven text-to-video, reference-based image-to-video, video upscaling, and video extension from one model family.

Use the playground to validate prompts, source images, task IDs, duration, aspect ratio, and payload behavior before connecting Grok video generation to your app, creative tool, or content pipeline.

Model Type:
Pricing

Lowest cost starts at $0.01/s

Selected model
Grok Imagine Text to Video

480p: 2 credits/s - Text to Video - Output seconds × 2

720p: 3 credits/s - Text to Video - Output seconds × 3

480p: 10 credits/s - Text to Video - Output seconds × 10

720p: 14 credits/s - Text to Video - Output seconds × 14

USD estimates use $0.005/credit with the best annual plan. Final billing follows the selected Grok video variant and output settings.

New tasks appear here after you submit.
API Input

Core request fields

Use a predictable payload for prompts, image URLs, source task IDs, aspect ratio, and callback settings.

Request JSON
{
  "model": "grok-imagine/text-to-video",
  "input": {
    "prompt": "A couple of doors open to the right one by one randomly and stay open, to show the inside, each is either a living room, or a kitchen, or a bedroom or an office, with little people living inside.",
    "aspect_ratio": "2:3",
    "mode": "normal",
    "duration": "6",
    "resolution": "480p"
  }
}

Use Grok Imagine Text to Video for generation

The playground, request sample, request fields, and pricing on this page follow the selected model type.

View detailed API docs

Open the full API documentation for endpoints, authentication, task polling, and payload details. /models/grok-imagine.md

promptstringText prompt describing the desired video motion. Required field.
aspect_ratioenumSpecifies the width-to-height ratio of the generated video. Controls the aspect ratio of the output. (2:3, 3:2, 1:1, 16:9, 9:16)
modeenumSpecifies the generation mode affecting the style and intensity of motion. (fun, normal, spicy)
durationnumberThe duration of the generated video (in seconds) (6-30). (Minimum: 6, Maximum: 30, Step: 1)
resolutionenumThe resolution of the generated video. (480p, 720p)
nsfw_checkerbooleanDefaults to false. You can set it to false based on your needs. If set to false, our content filtering will be disabled, and all results will be returned directly by the model itself.
Capabilities

What Grok Video API adds to your video workflow

The page follows the same API-first structure as the reference: test the model, understand the fields, then move into integration.

Text-to-video generation

Turn detailed prompts into short-form video concepts for social posts, ads, product moments, and fast creative exploration.

Image-to-video motion

Animate source images while preserving the subject, composition, and visual direction that your team already approved.

Upscale and extend

Improve successful Grok clips with video upscaling, or continue an existing generation with an extension task.

API-ready payloads

Work with model IDs, prompts, image URLs, task IDs, aspect ratios, callbacks, and task polling in one integration path.

Quick Start

From Grok video test to production request

A compact path for teams that want to validate output quality before wiring Grok video generation into an app.

1. Choose a mode

Select text-to-video for prompt-only creation, image-to-video for source image animation, or a follow-up mode for upscale and extend.

2. Submit generation

Call the API with your account key, model ID, prompt, optional image URLs or source task ID, and callback URL.

3. Poll and reuse

Track the task until it succeeds, then reuse the output URL in your product, campaign workflow, or follow-up video task.

Use Cases

What you can create with Grok Video API

Use the API when your product needs repeatable Grok video output, not just one-off manual generations.

Prompt-led social clips for TikTok, Reels, and Shorts
Animated product stills and campaign visuals
Rapid storyboard and concept video exploration
Video variants for ads, thumbnails, and landing pages
Upscaled versions of successful generated clips
Extended clips for iterative creative pipelines
Community Showcase

Successful Grok video generations from the community

Browse public Grok video outputs that finished successfully, then open any case to inspect the prompt, settings, and result.

View more
videoGrok Imagine

Real life scene, bank Holiday monday, new build living room on sofa, randy dominant 70-year-old Salford bloke next door dad wearing a crisp diffferent cotton business shirt with a sheen large stiff pinched collar, top buttons undone, tucked tightly in

Real life scene, bank Holiday monday, new build living room on sofa, randy dominant 70-year-old Salford bloke next door dad wearing a crisp diffferent cotton business shirt with a sheen large stiff pinched collar, top buttons undone, tucked tightly into dark smart trousers with a black belt., he is otk disciplining a 40 year old, 5 foot, thug scally bloke, who is wearing simlar, filthy talking, swearing

Jul 12, 2026View details
videoGrok Imagine

Use the uploaded image as the only reference. Create an 8-second vertical (9:16) ultra-realistic cinematic fashion video. The woman must remain exactly the same person as in the reference image. Preserve her facial features, skin tone, hairstyle, body p

Use the uploaded image as the only reference. Create an 8-second vertical (9:16) ultra-realistic cinematic fashion video. The woman must remain exactly the same person as in the reference image. Preserve her facial features, skin tone, hairstyle, body proportions, natural expression, and overall appearance consistently throughout the entire video. The dress must remain exactly the same dress shown in the reference image. Do not redesign, restyle, or modify it in any way. Preserve the exact yellow color, the same cotton fabric texture, embroidery, covered buttons, stitching, round neckline, sleeves, waist seam, silhouette, length, wrinkles, folds, and every visible detail exactly as in the original image. The back of the dress is extremely important. Keep it exactly the same as the reference image. It has a simple, clean back with only the waist seam. There must be NO belt, NO sash, NO ribbon, NO bow, NO back tie, NO pleats, NO gathers, NO decorative elements, NO extra seams, and NO redesign of the back. The woman begins sitting naturally on the sofa in the seaside lounge. She smiles gently, stands up naturally, then slowly walks through the elegant Mediterranean seaside corridor beside the ocean. The corridor has white walls, blue wooden railings, Mediterranean flowers, green vines, and beautiful coastal plants. The sea remains visible beside her during the walk. Her walking is slow, elegant, and completely natural. She has realistic posture, subtle arm movement, natural breathing, and soft hair movement from the sea breeze. The dress moves only with realistic fabric physics while keeping its exact original shape and design. The camera starts with a medium shot, then smoothly follows behind her with a stabilized cinematic tracking shot, clearly showing the original back of the dress while she walks. At the end of the corridor, she gently stops, turns her head toward the sea, and smiles softly while looking at the horizon. Bright Mediterranean afternoon sunlight, realistic shadows, natural ocean reflections, crystal-blue water, gentle waves, subtle movement of flowers and leaves in the breeze. Professional luxury fashion commercial, photorealistic, 4K HDR, full-frame cinema camera, natural skin texture, sharp details, stable camera movement, no AI look. Negative Prompt: No dress redesign, no color change, no fabric change, no belt, no sash, no ribbon, no bow, no pleats, no gathers, no extra seams, no accessories, no body reshaping, no face changes, no identity drift, no clothing deformation, no flickering, no warped hands, no distorted anatomy, no AI artifacts.

Jul 12, 2026View details
videoGrok Imagine

1950s Ad card and board dice game for family named "crack me"

1950s Ad card and board dice game for family named "crack me"

Jul 12, 2026View details
videoGrok Imagine

No zoom, no music, static camera. She doesnt change her pose but arch her back and relies on the block from the back. She imitate medieval torture like sit and stand impaling on black rubber stake

No zoom, no music, static camera. She doesnt change her pose but arch her back and relies on the block from the back. She imitate medieval torture like sit and stand impaling on black rubber stake

Jul 12, 2026View details
videoGrok Imagine

No music, no zoom, static camera, keep their poses. used by him with an animal passion and frenzy pace in supernatural tempo from the very start of the video

No music, no zoom, static camera, keep their poses. used by him with an animal passion and frenzy pace in supernatural tempo from the very start of the video

Jul 12, 2026View details
videoGrok Imagine

No music, no zoom, static camera, keep their pose. hardly used by him with an animal passion and frenzy in supernatural tempo from the very start of the video

No music, no zoom, static camera, keep their pose. hardly used by him with an animal passion and frenzy in supernatural tempo from the very start of the video

Jul 12, 2026View details
Production Notes

Built for real Grok video API workflows

Account-gated execution

Users sign in, submit jobs, and consume credits through the existing SdanceAI generation flow.

Reference and task inputs

Image-to-video accepts source image URLs, while upscale and extend workflows can continue from completed video task IDs.

Mode-aware iteration

Start with text or image generation, then move promising outputs into upscale or extension workflows when needed.

FAQ

Grok Video API questions

What is Grok Video API best for?

It is best for repeatable short-form video generation, including prompt-led clips, animated source images, video variants, upscaled outputs, and extended creative sequences.

Which Grok video modes are available?

The current page exposes Grok Imagine Text to Video, Grok Imagine Image to Video, Grok Imagine Video Upscale, and Grok Imagine Video Extend.

What is the difference between Text to Video and Image to Video?

Text to Video starts from a prompt only. Image to Video uses one or more source images plus a prompt, which is better when you need subject or composition continuity.

When should I use upscale or extend?

Use upscale when you already have a successful Grok video and want a higher-quality version. Use extend when you want to continue a completed generation into a longer sequence.

Where can I test it before integrating?

Use the playground on this page to test prompts, image URLs, source task IDs, aspect ratios, callbacks, and API payload behavior before moving into production.

Does the API support callbacks?

Yes. The request schema includes callback settings where supported, so your service can receive task completion notifications.

Can I use Grok Video API for commercial workflows?

This page is configured for production video workflows. For commercial use, review your account plan, credit balance, model availability, and applicable content policy requirements.

Can I animate an existing product image?

Yes. Use the image-to-video mode with a source image URL and a prompt that describes the motion, camera behavior, and final visual direction.

How should I manage cost?

Start with quick prompt or image-to-video tests, then reserve upscale and extension tasks for clips that are already close to your target.

Can I inspect the actual API fields?

Yes. Select a Grok video mode on this page and the request JSON, field list, and pricing panel will update to match that model.

Start building

Turn Grok video into your production workflow

Open the generator, test a Grok video prompt or source image, then use the API docs when you are ready to wire it into production.

API-ready
workflow
4 modes
video tools
Task ID
follow-ups