Image-only models available in Vercel AI Gateway
By Steven Van ·
Vercel's AI Gateway adds ten image-only models from Black Forest Labs and Google, usable via generateImage with no separate provider account.
Vercel's AI Gateway now supports image-only models, so image generation works without setting up a separate account with the model's provider. These sit alongside multimodal models that already generate images in the Gateway, such as GPT-5.1 and Nano Banana Pro, but the new models are dedicated to image generation.
The additions are:
- Black Forest Labs: FLUX.2 Flex, FLUX.2 Pro, FLUX.1 Kontext Max, FLUX.1 Kontext Pro, FLUX 1.1 Pro Ultra, FLUX 1.1 Pro, and FLUX.1 Fill Pro
- Google: Imagen 4.0 Generate 001, Imagen 4.0 Fast Generate 001, and Imagen 4.0 Ultra Generate 001
Each is called by setting model to its slug (for example bfl/flux-2-flex) in the AI SDK, and all of them support generateImage. See the announcement for details.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →