Grok Imagine Video API
The Grok Imagine API for video on APIMart runs xAI's grok-imagine-video model: text to video, image to video from one or more reference images, and editing of an existing clip. Clips last 1–15 seconds at 480p or 720p, and you pay per second of output.
Service Highlights
- Official Discounts
- Pay-as-you-go
- Fast & Low Latency
Generate from a prompt, with optional reference images to guide the result.
Review the prompt and input images before submission. Flagged requests create no task and incur no charge.
The video link is valid for 72 hours. Download or save it promptly.
Grok Imagine Video API Pricing
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
grok-imagine-video | Reference image (each) | 0.016Credits(~$0.0016)/pic | 0.0152Credits(~$0.0015)/pic | 0.0144Credits(~$0.0014)/pic | 0.02Credits(~$0.002)/pic | 20% |
| Reference video (per source second) | 0.08Credits(~$0.008)/sec | 0.076Credits(~$0.0076)/sec | 0.072Credits(~$0.0072)/sec | 0.1Credits(~$0.01)/sec | 20% | |
| 480P | 0.4Credits(~$0.04)/sec | 0.38Credits(~$0.038)/sec | 0.36Credits(~$0.036)/sec | 0.5Credits(~$0.05)/sec | 20% | |
| 720P | 0.56Credits(~$0.056)/sec | 0.532Credits(~$0.0532)/sec | 0.504Credits(~$0.0504)/sec | 0.7Credits(~$0.07)/sec | 20% |
* Actual costs are subject to final output.
xAI Grok Imagine Video API for Text to Video, Image to Video and Video Editing
One endpoint, three modes: send a prompt for text to video, add image_urls to animate stills, or pass video.url to edit footage you already have. Need 1080p? Grok Imagine Video 1.5 has its own page; this page covers the base grok-imagine-video model, the only one that supports video editing.
50K+
Active Users
99.9%
Uptime
2x
Faster
—
Cost Savings
Grok Imagine Video API Example: Text to Video and Image to Video
Call the Grok Imagine Video API on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint to get the video URL.
- 1
Authenticate Grok Imagine Video API requests
Save the key you created above in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
- 2
Submit a Grok video task
POST /v1/videos/generations with model grok-imagine-video, your prompt, duration, resolution and aspect_ratio. Add image_urls for image to video, or send video.url alone to edit a clip. The task ID is in data[0].task_id.
- 3
Get the Grok Imagine Video result
Poll GET /v1/tasks/{task_id} until status is completed, then read the video URL from data.result.videos[0].url[0] and save it before expires_at. A failed task returns its reason in data.error.message and costs nothing.
See the Grok Imagine Video API reference for every field, response and error code.
curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-video",
"prompt": "A slow dolly-in on a ceramic coffee mug on a wooden table as steam rises, warm morning light through a window, shallow depth of field",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9"
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "grok-imagine-video",
"prompt": "A slow dolly-in on a ceramic coffee mug on a wooden table as steam rises, warm morning light through a window, shallow depth of field",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9"
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["videos"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(10)
else:
raise TimeoutError(f"task {task_id} did not finish in time")curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-video",
"prompt": "The woman in the photo turns toward the camera and smiles as the wind moves her hair, slow push-in, soft daylight",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"image_urls": [
"https://example.com/portrait.jpg"
]
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"Grok Imagine Video API Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: grok-imagine-video | grok-imagine-video. Use grok-imagine-video-1.5 for 1080p output; video editing works only with grok-imagine-video. |
prompt | string | Required | Default: — | Video description or editing instruction, 1 to 8,000 characters after trimming spaces. |
duration | integer | Optional | Default: 8 | Output length, a whole number from 1 to 15 seconds. Generation only. |
resolution | string | Optional | Default: 480p | 480p or 720p. Generation only. |
aspect_ratio | string | Optional | Default: auto | auto, 16:9, 9:16, 1:1, 4:3, 3:4, 3:2 or 2:3. Generation only. |
image_urls | array | Optional | Default: — | Public HTTPS image URLs for Grok image to video. Order is kept and each image is billed. Omit the field for text to video instead of sending an empty array. |
video.url | string | Optional | Default: — | Public HTTPS URL of the source video for editing. Send only model, prompt, video and optional nsfw_check in an edit request. |
nsfw_check | boolean | Optional | Default: false | Set true to moderate the prompt and input images before the task is submitted. |
