Grok Imagine Video icon
Video by xAI

Grok Imagine Video API

xAI video from Grok Imagine.

Integrate Grok Imagine Video with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.

model: "grok-imagine-video"

What's special about Grok Imagine Video

  • 7 aspect ratios, including 1:1, 16:9, 9:16.
  • Generates clips from 6s to 15s.
  • Image-to-video and reference-image support.
  • Fast turnaround — about 180s per generation on average.
  • Pay-as-you-go pricing with no xAI account required — you only pay for successful generations.
  • One API key, unified billing, idempotency and webhooks across every Apiframe model.

Made with Grok Imagine Video

A few outputs generated through the Grok Imagine Video API on Apiframe.

Sample coming soon

Drone shot flying over a tropical coastline at sunrise, smooth cinematic motion

Sample coming soon

A vintage car driving through a rainy neon city at night, reflections on the asphalt

Sample coming soon

Time-lapse of clouds rolling over a mountain range in warm golden light

Overview

Endpoint
POST /v2/videos/generate
Model ID
grok-imagine-video
Params key
grokParams
Modality
video
Provider
xAI
Pricing
Pay-as-you-go
Avg. completion
~180s

Capabilities

Aspect ratios1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
Durations6s, 10s, 15s
Image inputSupported
Avg. time~180s

Quick start

Send a single POST /v2/videos/generate request with your API key to generate with Grok Imagine Video. The call returns a jobId you can poll or receive via webhook.

curl -X POST https://api.apiframe.ai/v2/videos/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
        "model": "grok-imagine-video",
        "grokParams": {
            "reference_images": [
                "https://example.com/input.jpg"
            ]
        }
    }'
import requests

response = requests.post(
    "https://api.apiframe.ai/v2/videos/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
        "model": "grok-imagine-video",
        "grokParams": {
            "reference_images": [
                "https://example.com/input.jpg"
            ]
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }
const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
    "model": "grok-imagine-video",
    "grokParams": {
      "reference_images": [
        "https://example.com/input.jpg"
      ]
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

Response & job lifecycle

Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).

1. Submission response (202)

{
  "jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
  "status": "QUEUED"
}

2. Poll for the result

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"
import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])
let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

Input schema

Request parameters accepted by the Grok Imagine Video endpoint. Model-specific options are nested under the params object shown below.

Parameter Type Required Default Allowed / range Description
prompt string required Text description of what to generate.
model string required "grok-imagine-video" "grok-imagine-video" The model identifier for this endpoint.
grokParams.reference_images string[] (URLs) optional Reference images

Frequently Asked Questions

Common questions about the Grok Imagine Video API.

Is there an API for Grok Imagine Video?

Yes. Apiframe exposes Grok Imagine Video through a single REST endpoint (`POST /v2/videos/generate` with `model: "grok-imagine-video"`). You get one unified API, key, and billing across every supported model — no separate xAI account required.

How much does the Grok Imagine Video API cost?

Grok Imagine Video uses simple pay-as-you-go pricing on Apiframe — you only pay for successful generations. See the pricing page for plans and volume discounts.

How do I call the Grok Imagine Video API?

Send a POST request to `/v2/videos/generate` with your `X-API-Key` and a JSON body containing `model: "grok-imagine-video"`. The call returns a `jobId`; poll `GET /v2/jobs/{id}` or use a webhook to receive the result.

What parameters does Grok Imagine Video support?

Grok Imagine Video accepts 1 model-specific parameters (nested under `grokParams`) plus the common `prompt` and `webhook_url` fields. See the input schema above for the full list with types and defaults.

Still have questions?

Start building with the Grok Imagine Video API

Get your API key and integrate Grok Imagine Video in minutes — Pay-as-you-go.

Free credits to start
One API for every model
Webhooks, SDKs & idempotency
No provider account required

Questions? Join our Discord or contact sales.