Grok Imagine covers xAI's image models released in January 2026, offered at a flat per-image rate in two quality tiers, standard and high, picked with the quality field. One request returns up to 4 images in 13 aspect ratios plus auto, from 1:1 to tall 9:20 and wide 20:9, at 1k or 2k (a 16:9 image at 2k is 2816x1584). It can also edit a single source image. Prompts go up to 10,000 characters and are rendered as written.
Best for
- Phone wallpapers and stories in tall 9:19.5 or 9:20 formats
- Batches of up to 4 variations per prompt
- Simple edits of one photo, such as restyling or adding an object
- Draft rounds in standard quality before a final pass in high
Prompting tips
- Explore with
quality: standard, then switch tohighfor the images you will publish. - Match the ratio to the screen: 9:19.5 and 9:20 fit modern phones, 19.5:9 and 20:9 fit wide banners.
- For edits, send exactly one image in
image_urlsand describe the change. - Your prompt is not rewritten, so spell out style and lighting yourself.
FAQ
How much does the Grok Imagine API cost?
Grok Imagine is billed at a flat rate per image, with a separate rate for each quality tier: $0.0246 per image. Failed generations are not charged.
What resolution does Grok Imagine output?
1k or 2k. At 2k, a 16:9 image comes out at 2816x1584.
Can Grok Imagine combine several reference images?
No, editing takes one source image. For multi-reference edits try Qwen Image 2.1 or Nano Banana 2.
How to call Grok Imagine via API
curl https://jantaris.com/v1/generate?wait=60 \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "auto",
"resolution": "1k"
}
}'import os, time, requests
API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}
task = requests.post(f"{API}/generate", headers=H, json={
"model": "grok-imagine",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "auto",
"resolution": "1k"
}
}).json()
while task["status"] in ("queued", "running"):
time.sleep(3)
task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()
print(task["status"], task["cost"], [o["url"] for o in task["output"]])const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };
let task = await (await fetch(`${API}/generate`, {
method: "POST",
headers,
body: JSON.stringify({
"model": "grok-imagine",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "auto",
"resolution": "1k"
}
}),
})).json();
while (task.status === "queued" || task.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));Parameters
| Parameter | Type | Allowed | Default |
|---|---|---|---|
prompt * | string | ≤ 10000 chars | |
aspect_ratio | string | 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 | auto |
resolution | string | 1k 2k | 1k |
quality | string | standard high | standard |
num_images | integer | 1-4 | 1 |
image_urls | array | max 1 |
The same schema is available from GET /v1/models/grok-imagine.
