Generate image with Muse Image 1.0
Meta Muse Image 1.0 — agentic image generation: the model can ground your prompt with web and image search and run code for charts, tables and text layouts before rendering (all included). Excellent typography and factual accuracy, ~2K output. Text-to-image, image editing, and multi-reference composition from up to 4 input images. Flat 12 credits per image.
Asynchronous. Returns a job id (the image is not in this response). Poll GET /v1/images/{id} until status is succeeded — the generated image URLs are in that response’s images array (each { url, position }).
Examples, sample output and pricing: Muse Image 1.0
Authorizations
API key as a bearer token: Authorization: Bearer bpx_live_xxx
Body
Text description of the image to generate.
Output aspect ratio.
1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, match_input_image Number of images to generate.
1 <= x <= 4Output image format.
webp, png, jpeg Reasoning strength. "high" (default) refines the image over multiple passes and uses the model's search grounding fully — better output, slower. "low" responds faster. Both bill the same 12 credits per image.
high, low Optional input images (up to 4) for image editing and multi-reference composition. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image. An edit follows the input image's frame unless aspect_ratio forces one.
4