Nano Banana 2.1 now available on AI Gateway
Google’s Nano Banana 2.1 image model is now accessible via Vercel’s AI Gateway, enhancing editing and generation with improved realism and precision.
Nano Banana 2.1, developed by Google, has been added to Vercel’s AI Gateway, expanding the platform’s image generation capabilities. The update focuses on three key areas: product recontextualization, mask- and ink-based editing, and factuality. Product recontextualization allows users to place existing products into new scenes, while mask- and ink-based edits enable localized changes to specific regions of an image. Factuality ensures that generated images accurately represent real-world subjects.
The model delivers photorealistic results, including skin tones, materials, lighting, and backgrounds, while maintaining the speed and cost efficiency of a Flash-tier model. Users can integrate Nano Banana 2.1 through the AI SDK, OpenAI-compatible Chat Completions API, or the AI CLI, a command-line tool from Vercel Labs for generating text, images, video, and audio from the terminal.
AI Gateway serves as a unified interface for accessing models, tracking usage and costs, and configuring retries, failover, and performance optimizations to improve uptime. The platform includes features such as built-in custom reporting, Zero Data Retention support, budget controls for API keys, and routing rules to manage requests effectively.
AI Gateway mirrors provider pricing without additional markup and does not impose a platform fee on inference, including for Bring Your Own Key requests. Users can explore all available image models on the platform, with Nano Banana 2.1 now included among them.