Muse Image is the first image model from Meta Superintelligence Labs. Write a prompt, add up to 9 reference images if you have them, and Muse Image returns one picture in the aspect ratio you pick, at one flat price per image.
Required · must not be empty
1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · default auto
Try one of these prompts
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
One sample at the cheapest tier (1 image).
Muse Image is the image generation model from Meta Superintelligence Labs, launched on July 7, 2026 as the lab's first media model. Meta describes it as following instructions faithfully, editing with precision and composing from multiple references. On reAPI, Muse Image is the model id muse-image on /api/v1/images/generations: a prompt, up to 9 reference images and one of seven aspect ratios in, one WebP image out, billed at a single per-image price.
Real-world workflows and production use cases you can build and ship with this model.
Send a product photo as a reference and tell Muse Image where it belongs: a flat lay, a shelf, a sunlit table. Name what must not change, such as color or shape, and Muse Image builds the new scene around it.
Try a reference
Pick 9:16 for Stories, 16:9 for banners or 1:1 for feeds, and keep the same prompt. Every Muse Image ratio costs the same, so cropping for each channel never changes the bill.
Muse Image charges one price per image whether you send text alone or nine references. A batch of twenty variations costs twenty images, with no resolution tiers to work out.
Text to image and reference images share one Muse Image request on /api/v1/images/generations. Add image_urls when you have references and leave them out when you don't.
The same reAPI key runs Muse Image, Muse Video, Nano Banana 2, GPT Image 2 and the rest of the catalog. You don't need a separate Meta developer account for Muse Image.
Muse Image bills one flat price per generated image. Credits never expire, and failed tasks are refunded automatically.
Both models run on reAPI under the same key. Muse Image keeps the request small and the price flat; Nano Banana 2 adds resolution tiers, more ratios, more references and search grounding. Pick Muse Image when one flat-priced picture per request is what you need.
Values reflect each model's parameters on reAPI on October 29, 2026. Current rates are in each model's pricing table.
Sign up and create a key in the dashboard. New accounts get a small test credit, enough for several Muse Image test images.
OpenWrite a prompt, add references if you have them, pick a ratio and generate. Copy the request from the API tab when you like the result.
OpenPOST to /api/v1/images/generations with model muse-image, then poll the Muse Image task until it completes and download the image.
Opencurl -X POST https://reapi.ai/api/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-image",
"prompt": "A travel poster for a seaside town called Porto Azul: pastel houses stacked on a cliff above a turquoise bay, the headline PORTO AZUL in bold serif letters at the top, flat retro illustration style.",
"aspect_ratio": "3:4"
}'Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.
401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.
Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.
A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.
Common questions about this model.
Explore more models in the same category.
Meta
From $0.024 per clip
Alibaba
From $0.005 per image
SpaceXAI
From $0.005 per image
—
From $0.013 per image
Try it in the playground or grab an API key to integrate now.