Grok Imagine 2.0 API
The Grok Imagine 2.0 API on APIMart gives you two ways to use xAI's Grok Imagine 2.0 image model: the low-cost grok-imagine-2.0-ext for text to image, ratio redraw, layers and region editing, and the official grok-imagine-image-2.0 for 1K or 2K text to image and editing with up to three reference images.
Service Highlights
- Official Discounts
- Pay-as-you-go
- Fast & Low Latency
Image link valid for 72 hours
Grok Imagine 2.0 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-2.0-ext | Image upload | Free | Free | Free | — | — |
| Standard Generation | 0.15Credits(~$0.015)/pic | 0.1425Credits(~$0.0143)/pic | 0.135Credits(~$0.0135)/pic | 0.6Credits(~$0.06)/pic | 75% | |
| Region edit | 0.15Credits(~$0.015)/gen | 0.1425Credits(~$0.0143)/gen | 0.135Credits(~$0.0135)/gen | 0.1875Credits(~$0.0188)/gen | 20% | |
grok-imagine-image-2.0 | 1K low | 0.32Credits(~$0.032)/pic | 0.304Credits(~$0.0304)/pic | 0.288Credits(~$0.0288)/pic | 0.4Credits(~$0.04)/pic | 20% |
| 1K medium | 0.48Credits(~$0.048)/pic | 0.456Credits(~$0.0456)/pic | 0.432Credits(~$0.0432)/pic | 0.6Credits(~$0.06)/pic | 20% | |
| 2K low | 0.48Credits(~$0.048)/pic | 0.456Credits(~$0.0456)/pic | 0.432Credits(~$0.0432)/pic | 0.6Credits(~$0.06)/pic | 20% | |
| 2K medium | 0.64Credits(~$0.064)/pic | 0.608Credits(~$0.0608)/pic | 0.576Credits(~$0.0576)/pic | 0.8Credits(~$0.08)/pic | 20% | |
| Reference image (each) | 0.08Credits(~$0.008)/pic | 0.076Credits(~$0.0076)/pic | 0.072Credits(~$0.0072)/pic | 0.1Credits(~$0.01)/pic | 20% |
* Actual costs are subject to final output.
Grok Imagine 2.0 API Example: Text to Image and Image Editing
Call grok-imagine-image-2.0 on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the image URLs. The example uses the official grok-imagine-image-2.0; for Ext, set model to grok-imagine-2.0-ext with n up to 12 and no reference images. This code sends no X-APIMart-Response-Version header, so the submit response is HTTP 200 with data[0].task_id; the docs example sends that header and gets HTTP 202 with data.id.
- 1
Authenticate Grok Imagine 2.0 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-imagine-image-2.0 task
POST /v1/images/generations with model grok-imagine-image-2.0, your prompt, aspect_ratio, resolution, quality and n. To edit, add image_urls and drop quality. The task ID is in data[0].task_id.
- 3
Get the Grok Imagine 2.0 result
Poll GET /v1/tasks/{task_id} until status is completed, then read the image URL from data.result.images[0].url[0]. Results are kept for 72 hours. Failed tasks are not charged.
See the Grok Imagine 2.0 API reference for every parameter and response field.
curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-image-2.0",
"prompt": "Minimal product photography of a white ceramic cup on a stone surface, soft window light, clean background",
"n": 1,
"aspect_ratio": "16:9",
"resolution": "2k",
"quality": "medium"
}'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-image-2.0",
"prompt": "Minimal product photography of a white ceramic cup on a stone surface, soft window light, clean background",
"n": 1,
"aspect_ratio": "16:9",
"resolution": "2k",
"quality": "medium"
}
resp = requests.post(f"{API_BASE}/v1/images/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"]["images"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(3)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-image-2.0",
"prompt": "Place the product on a marble kitchen counter with morning light and keep the product unchanged",
"n": 1,
"image_urls": [
"https://example.com/product.png"
]
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"Grok Imagine 2.0 API Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: grok-imagine-image-2.0 | grok-imagine-image-2.0. The same model handles text to image and editing. |
prompt | string | Required | Default: — | Image description, or the edit instruction when image_urls is set. Up to 8,000 characters. |
aspect_ratio | string | Optional | Default: auto | Aspect ratio: auto, 1:1, 3:4, 4:3, 9:16, 16:9, 2:3, 3:2, 9:19.5, 19.5:9, 9:20, 20:9, 1:2, 2:1. |
resolution | string | Optional | Default: 1k | Output resolution: 1k or 2k. The price depends on resolution and quality. |
quality | string | Optional | Default: medium | Text to image only: low or medium. Do not send it when image_urls is present. |
n | integer | Optional | Default: 1 | Number of images, 1–10. |
image_urls | array | Optional | Default: — | Reference images for editing, 1–3 public HTTP(S) URLs. Omit the field for text to image. |
nsfw_check | boolean | Optional | Default: false | Set true to moderate the prompt and input images before the task is submitted. |
