Muse Image is Meta's image model, shown in July 2026. Each request returns one WebP image. Input is a prompt plus up to 9 optional reference images - a character, a product, a style. There are seven aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 and 2:3. There is no resolution or quality setting, but the single price is one of the lowest in the catalog.
The video model from the same family is Muse Video.
Best for
- Fast graphic and thumbnail variants in bulk
- Posters and flat-style illustrations
- Character or product scenes from several reference photos
- First frames to animate in a video model
How to write prompts
- Start with the style (e.g. flat retro illustration, 35 mm photo), then the scene.
- Name each reference in the prompt: "the person from the first image", "the mug from the second".
- Put in-image text in quotes and keep it short.
FAQ
How much does Muse Image cost?
$0.02 per image. Failed generations are not charged.
What file format do I get?
WebP, one image per request.
How many reference images can I add?
Up to 9 per request.
How to call Muse Image via API
curl https://jantaris.com/v1/generate?wait=60 \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-image",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "1:1"
}
}'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": "muse-image",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "1:1"
}
}).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": "muse-image",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "1:1"
}
}),
})).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 | ||
aspect_ratio | string | 1:1 16:9 9:16 4:3 3:4 3:2 2:3 | 1:1 |
image_urls | array | max 9 |
The same schema is available from GET /v1/models/muse-image.