ToolsThe story, in brief

Muse Image now available on AI Gateway

Meta's Muse Image now available on Vercel's AI Gateway—unified API for both generation and editing, no provider markup.

Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
New tools for building and creating with AI.AI illustration by KeyNews
The KeyNews take

Why it matters

Meta's first image model (Muse Image) ships on a major developer platform (Vercel's AI Gateway), expanding multi-modal tooling available to practitioners building with unified APIs. Single model handles both generation and editing, reducing workflow complexity.

The key facts

16 to know
  1. Meta Superintelligence Labs released Muse Image—first image model from Meta

  2. Muse Image available on Vercel's AI Gateway (unified API platform)

  3. Single model handles both image generation and image-to-image editing

  4. Reference image blending supported (pass images to steer generation)

  5. AI Gateway offers no platform fee on inference, reflects provider pricing with no markup

  6. AI Gateway includes usage tracking, cost tracking, failover, routing rules, custom reporting, budgets for API keys

  7. Model identifier: meta/muse-image-1.0

  8. Integration via Vercel's AI SDK (generateImage method)

  9. Test available in model playground

  10. Meta Superintelligence Labs releases Muse Image — first image model from the family

  11. Single model handles both image generation from text and image editing from instructions

  12. Available via Vercel AI Gateway with model ID: meta/muse-image-1.0

  13. Supports reference images to steer generation toward existing art (style transfer capability)

  14. AI Gateway provides unified API, usage tracking, cost monitoring, failover, and performance optimization

  15. No platform fee on inference; reflects provider pricing with no markup

  16. Published: August 26, 2026

Go to the source

Vercel Blogvercel.com

Publisher excerpt: from Meta Superintelligence Labs is now available on AI Gateway. It is their first image model and a separate family from Muse Spark, returning images rather than text. Send a prompt and get an image back, or send an image with an instruction and get it changed. One model does both, so you don't…
Read original report
Back to today's editionMore tools news

Keep reading

Related stories

More from Tools