Muse Image now available on AI Gateway
By Steven Van ·
Muse Image from Meta Superintelligence Labs is now available on AI Gateway.
Vercel's AI Gateway now supports Muse Image, the first image model from Meta Superintelligence Labs and a separate family from Muse Spark. Unlike Muse Spark, it returns images rather than text, and the same model handles both generating and editing, so there's no need to switch models to go from one to the other.
- To generate an image, set the model to meta/muse-image-1.0 and call generateImage from the AI SDK with a text prompt.
- Reference images can be passed in prompt.images alongside text, and the model blends them into what it draws.
- To edit an existing image, pass it in prompt.images with an instruction; the model changes what was asked and leaves the rest untouched.
Muse Image can be tried in the model playground. AI Gateway reflects provider pricing with no markup and charges no platform fee on inference, including on Bring Your Own Key requests. See the full announcement for code examples.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →