At a cent per image with web search included, it suits developers generating images in bulk; country availability is unclear.
Kenning's take
What it does
Muse Image is Meta's image generation and editing model. It reasons about a prompt and plans the layout before drawing, can search the web for references, and keeps characters and style consistent across a series using reference images. It has powered image features in Meta AI since July 2026 and became available to developers through the Meta Model API on 25 August 2026.
- Generates and edits images from text and reference images
- Plans layout before rendering
- Built-in web and image search for references
- Consistent characters and style across a series
- Output up to 1600 pixels
Who it suits. Meta AI users making images, and developers who want low-cost image generation through an API.
Key facts
- Category
- AI models
- Part of
- Meta AI
- Made by
- Meta
- Launched
- 2026
- How to get it
- in Meta AI, and through the Meta Model API (muse-image-1.0) at dev.meta.ai
- Works on
- Web, iOS, Android, API
- API price
- $0.01 per generated image
FAQ
How much does Muse Image cost?
Through the Meta Model API it costs a flat $0.01 per generated image.
Where can I use Muse Image?
In Meta AI, and for developers through the Meta Model API.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Meta Llama models
Meta's family of downloadable large language models, from Llama 2 to the multimodal Llama 4
Muse Glimmer
Meta's open-weight 30B model for running AI agents locally on a Mac or PC with one consumer GPU
Muse Spark
The first model from Meta Superintelligence Labs, a multimodal reasoning model behind the Meta AI app
Muse Spark 1.1
Meta's July 2026 update to Muse Spark with a 1M-token context, computer use and the first public API