Xai · Video model

Grok Imagine

Text-to-video and image-to-video from xAI, billed by the second.

One API key. Every model.

480P 720P per second
Example
AI video
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with Grok Imagine.

One model. Three ways to call it. Same key, same bill.

480P

Video generation

480P. One call. Same key. Same bill.

$0.09 / second

720P

Video generation

720P. One call. Same key. Same bill.

$0.09 / second

Capabilities

What it does best.

Grok Imagine capabilities

  • Accepts text, image, and video as inputs. Enables text-to-video, image-to-video, and video-to-video workflows from one endpoint[^1]
  • Outputs video at 480p or 720p resolution, billed per second of generated output[^2]
  • Supports fourteen aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, 9:19.5, 20:9, 9:20, and auto (model selects the best ratio for your prompt)[^3]
  • Generates still images at 1K and 2K resolutions via the same Imagine API[^4]
  • Batch image generation supported: submit concurrent requests or use the n parameter to generate several images in one call[^5]
  • OpenAI-SDK drop-in compatible. Point your existing OpenAI client to https://api.x.ai/v1 and swap the model name[^6]
  • Delivers output as a temporary URL or base64-encoded data. No separate download step needed[^7]
  • Content moderation enforced via a respect_moderation flag. Outputs that fail moderation are filtered before delivery[^8]
  • Image-to-video and video input conditioning billed separately by the vendor. See the official docs for media input fee details
API

Call Grok Imagine in three lines.

One key. One base URL. Same SDK shape you already use.

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/video/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.video.generate({
  model: "models/xai/grok-imagine",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.video.generate(
    model="models/xai/grok-imagine",
    prompt="neon city, rain, tracking shot",
)
Response
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/xai/grok-imagine",
  "output": {
    "video_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

Grok Imagine · 480P
0.9 tokens
per second · $0.09
Video model
$0.09 / second · 480P
One key. Every model. One invoice. 1 token = $0.10
8s clip ≈ 7 tokens ($0.72)
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

480P

Final renders, studios
Resolution 480P
Price $0.09 / second

720P

Rapid tests, high volume
Resolution 720P
Price $0.09 / second
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Short-form social video Need a 9:16 vertical clip for Instagram Stories or TikTok? Grok Imagine natively supports the 9:16 aspect ratio. Go from brief to ready-to-post video in seconds[^3].

Product scene generation Build a multi-scene product video by generating several short clips. Run 10 scenes at 3 seconds each at $0.085/sec on Coinis and get a full product narrative without a film crew[^2].

UGC-style ad creative Generate 15-second clips that look like authentic user content. Ideal for paid social teams that need volume without production overhead[^1].

Sales explainer plates Create short 4-second visual cuts to anchor an explainer or sales deck video. Fast turnaround means you can iterate on messaging in real time[^2].

Image-to-video brand asset animation Have a product photo or brand illustration? Feed it to the model as a conditioning input and get an animated video out. No motion designer required[^1].

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

Grok Imagine FAQs

How much does Grok Imagine cost per second of video on Coinis?

On Coinis, Grok Imagine video is priced at $0.085/sec for both 480p and 720p output. A 4-second clip costs 4 x $0.085. A 15-second clip costs 15 x $0.085. You pay only for the seconds of video generated.

What is the difference between 480p and 720p, and is 720p worth the extra cost?

480p is the standard-definition tier suited for social previews, drafts, and high-volume pipelines where file size matters. 720p delivers HD output suited for ad placements, product videos, and anything viewed on a larger screen. On Coinis both tiers share the same $0.085/sec retail rate, so the choice is purely about output quality.

Can I use Grok Imagine for image-to-video, or only text-to-video?

Grok Imagine supports text, image, and video as inputs. You can pass an existing product photo or brand illustration as a conditioning input to generate an animated video output. Image and video input conditioning is billed separately by the vendor. See the official docs at https://docs.x.ai/developers/pricing for media input fee details.

Is there a Grok Imagine API, and is it OpenAI-compatible?

Yes. The Grok Imagine video endpoint on Coinis is available at POST https://api.app.coinis.com/v1/video/generate. The underlying xAI Imagine API is OpenAI-SDK-compatible. Teams already using the OpenAI Python or Node client can point their base URL to https://api.x.ai/v1 and swap the model name. The full API reference is on the Grok Imagine API sub-page.

How does Grok Imagine compare to other video models in the Coinis catalog?

Grok Imagine handles text-to-video, image-to-video, and video-to-video in one endpoint. Most catalog alternatives specialize in one mode. For higher-resolution or longer-form video, Coinis also offers Google Veo 3, Kling 2.1, and Runway Gen-4. Each model page includes its own pricing and capability details so you can compare before you generate.

What aspect ratios and clip lengths does Grok Imagine support?

Grok Imagine supports fourteen named aspect ratios including 1:1, 16:9, 9:16, 4:3, 19.5:9, 20:9, and an auto mode where the model picks the best ratio for your prompt. Clip length is flexible and billed per second of output. When editing a single image the output aspect ratio is locked to match the input image.

Are there content moderation or regional availability limits I should know about before building on Grok Imagine?

Two things to plan for. First, Grok Imagine enforces content moderation via a respect_moderation flag. Outputs that fail the policy check are filtered and not returned, so budget for occasional filtered requests in high-volume workflows. Second, model availability may vary by geography and account type. Check the official xAI docs or your Coinis account settings to confirm access before building a production pipeline.

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .