MiniMax H3 (Hailuo 3) is live on EvoLinkTry it with 10 free credits

Grok Imagine Video 1.5 API

Animate one source image into a 1-15 second video with directed motion and native synchronized audio. Use EvoLink's unified async API to estimate cost, submit a task, and route the result into your production workflow.

xAI-Image-to-Video-Live
From ~$0.064 / s for 480p image-to-video output-20%$0.080 official price
Image-to-Video only1 source imageNative audio480p / 720p1-15 seconds
Production routeLive
Best For
Product motion, social clips, and storyboard previews
API Scope
Image-to-video only with exactly one source image
Controls
Motion prompt, 1-15s, and 480p / 720p output
Delivery
480p / 720p video through an async task

Try Grok Imagine Video 1.5 before you integrate the API.

Upload one reference image, estimate credits, and preview image-to-video output before you wire up the async API.

Create a Sample

Upload one image, add a prompt, and set the parameters.
Image-to-VideoSingle reference image - $0.064/s · 4.352 cr/s
Input Image

Required. Upload exactly 1 reference image (image-to-video only).

1

generated-image.png

1 image(s) added

https://cdn.evolink.ai/Model-Example/GrokImagine1.5/generated-image.png
1/1 files
Duration6s
Resolution
Estimated: ~$0.3926.66 cr
Ready
History
Your generation history will appear here

Grok Imagine Video 1.5 pricing for image-to-video.

Plan credits for image-to-video runs. Output is billed by duration and resolution; each input image adds a small fixed fee.

First Test Cost

Image-to-Video - 6s - 480p - 1 image
6s 480p
Credits26.656

One 6s 480p sample with 1 input image

Approx. Cost$0.392

About 25 tests with $10 in credits.

Iterate in 480p to save credits, then switch to 720p when the motion and framing are ready for review.

EvoLink rate$0.392
Official price$0.490
You save-20%

Testing Budget Guide

Pick an amount based on how many tests you expect.
Add Credits
$10
About 26 tests

Good for a first validation.

$50
About 128 tests

Good for iterating on motion and framing.

$100
About 255 tests

Good before production integration.

Common Cost Examples

Draft iteration480p · 6s
~$0.392-20%
26.656 cr$0.490 Official price
HD quality check720p · 6s
~$0.680-20%
46.24 cr$0.850 Official price
Longer clip480p · 15s
~$0.968-20%
65.824 cr$1.210 Official price

Estimated total for one image-to-video run (includes 1 input image). Final cost may vary by duration and resolution.

Grok Imagine Video 1.5 Pricing

-20%
Image-to-Video
Output video, per second · Output video seconds
480p
$0.064/s-20%
4.352 cr/s$0.080 Official price
720p
$0.112/s-20%
7.616 cr/s$0.140 Official price

Output is billed per second (720p = 480p x 1.75). Each input image is charged a small fixed fee and is required for image-to-video.

Build controlled image-to-video workflows with Grok Imagine Video 1.5.

Grok Imagine Video 1.5 is xAI's GA image-to-video model. On EvoLink, each request uses one source image and a required motion prompt to create a 1-15 second 480p or 720p video. The route is designed for short-form generation with native audio, asynchronous task handling, live cost estimation, and one API key shared with other models.

Open the playground
Input
1 reference image + prompt
Output
Short video
Duration
1-15 seconds
Resolution
480p / 720p

What the model adds to an image-to-video workflow

Directed motion from one frame

Use a prepared product shot, portrait, illustration, or storyboard frame as the visual anchor, then describe subject and camera motion in the prompt.

Video and native audio together

The model can generate motion with synchronized ambience, sound effects, and speech in the same pass. Validate audio quality against your own acceptance criteria.

A production-friendly async route

Submit once, track the task by polling or callback, then persist the completed asset before its temporary result URL expires.

Grok Imagine Video 1.5 use cases

Ad & product clips

Ad & product clips

Turn product photography and campaign key visuals into short motion concepts and creative variants.

Try in Playground
Social & UGC

Social & UGC

Create portrait, square, or landscape clips with camera direction and optional audio cues for social workflows.

Try in Playground
Cinematic stories & concept tests

Cinematic stories & concept tests

Explore camera movement, character performance, physical effects, timing, and scene rhythm from a storyboard frame before committing to a larger production.

Try in Playground

Grok Imagine Video 1.5 production contract on EvoLink

Generation mode
Grok Imagine Video 1.5Single-image image-to-video only
Production impactThe source image fixes the opening composition.
Choose another route whenYou need prompt-only text-to-video.
Input contract
Grok Imagine Video 1.51 image + non-empty prompt
Production impactValidate both inputs before submitting the task.
Choose another route whenYou need multiple references or first/last frames.
Duration & output
Grok Imagine Video 1.51-15s at 480p or 720p
Production impactCost scales with duration and resolution.
Choose another route whenYou require longer clips or 1080p on EvoLink.
Output framing
Grok Imagine Video 1.5Follows the source image
Production impactPrepare the source image in the intended final framing.
Choose another route whenYou need a first-and-last-frame transition.
Delivery
Grok Imagine Video 1.5Async task with polling or callback
Production impactQueue tasks and make terminal handling idempotent.
Choose another route whenYour workflow requires an immediate synchronous result.
Billing
Grok Imagine Video 1.5Per output second + per input image
Production impactEstimate each task and cap retry spending.
Choose another route whenYou need a fixed cost independent of duration.

Key Details

GA upstream, preview alias on EvoLink

xAI lists grok-imagine-video-1.5 as the stable model. EvoLink currently accepts grok-imagine-video-1.5-preview, so use the ID shown in EvoLink examples.

Strict single-image input contract

Send exactly one JPEG, PNG, or WebP image up to 10 MB and a non-empty prompt. Text-to-video and reference-to-video are not supported by this route.

Async delivery with temporary results

Submit a task, poll or receive a callback, and persist the finished video. EvoLink result URLs are available for 24 hours.

Why use Grok Imagine Video 1.5 through EvoLink

Transparent Pricing

Use live route pricing to estimate duration, resolution, and input-image cost before generation.

Unified API

Call Grok Imagine and other video models through one authentication and integration layer.

Unified Balance

Manage credits, spending, and model usage in the same EvoLink account.

Task Status Tracking

Track pending, processing, completed, and failed tasks through a consistent async workflow.

Model Choice

Keep Grok 1.5 for single-frame animation and route other modalities to a better-matched model.

Grok Imagine Model Family

View all models
Grok Imagine Video (1.0)

Grok Imagine Video (1.0)

The broader Grok Imagine video route for text-to-video, image-to-video, reference, edit, and extend workflows.

View ->

Other video models on EvoLink

Seedance 2.0

Seedance 2.0

A video model for text, image, and reference-driven generation with native audio.

View ->
Gemini Omni

Gemini Omni

Google unified multimodal video generation.

View ->
Wan 2.7

Wan 2.7

Alibaba multi-style text, image, and reference-to-video.

View ->
Hailuo 3

Hailuo 3

MiniMax high-quality cinematic video generation.

View ->

FAQ

What is Grok Imagine Video 1.5?

Grok Imagine Video 1.5 is xAI's GA image-to-video model. It turns one source image and a motion prompt into a short video with native audio capabilities.

Which model ID should I use on EvoLink?

Use grok-imagine-video-1.5-preview in EvoLink requests. xAI's upstream stable ID is grok-imagine-video-1.5, but model IDs are channel-specific.

Why does the EvoLink model ID still include preview?

The preview name remains an upstream alias and is the current public ID for the EvoLink route. It does not mean xAI still classifies the 1.5 release as Preview.

Does Grok Imagine Video 1.5 support text-to-video?

No. Grok Imagine Video 1.5 is image-to-video only. Use the broader Grok Imagine Video route or another video model when you need prompt-only generation.

Can I use multiple reference images or first and last frames?

No. The EvoLink route requires exactly one source image. Grok Imagine Video 1.5 does not support reference-to-video or a first-and-last-frame workflow.

What image and prompt inputs are required?

Send one JPEG, PNG, or WebP image up to 10 MB and a non-empty prompt of up to 2,000 tokens (CJK text uses more tokens per character). Validate both before submitting the async task.

How much does Grok Imagine Video 1.5 cost?

EvoLink bills output by duration and resolution and adds the input-image charge. Use the live pricing section and playground estimate for the current route price instead of relying on a copied static figure.

What resolutions and durations are supported?

The EvoLink route supports 480p and 720p output and durations from 1 to 15 seconds. xAI also documents 1080p upstream, but it is not currently exposed by this EvoLink route.

How is the output framing determined?

This route does not expose an aspect-ratio parameter. Prepare the source image in the framing you want the generated video to follow.

Does Grok Imagine Video 1.5 generate audio?

The model is designed to generate synchronized ambience, sound effects, and speech with the video. Audio quality can vary by scene, so test it against your own acceptance criteria.

How do I receive the finished video?

Generation is asynchronous. Submit a task, poll its status or provide an HTTPS callback, and persist the returned video when the task completes.

How long is the result URL available?

EvoLink result URLs are available for 24 hours. Copy completed assets to your own object storage instead of using the temporary URL in production.

Are failed or moderated requests always free?

Do not assume that every failed or moderated request is free. Inspect the task's returned usage and billing fields and confirm the current account record before retrying.