Google's Nano Banana 2.1 now available on AI Gateway

Google's Nano Banana 2.1 is now available on AI Gateway, offering improved image generation and editing over earlier Nano Banana models. The release specifically targets product recontextualization, mask- and ink-based editing, and factuality.

Key Capabilities

• Product recontextualization places an existing product in a new scene.
• Mask- and ink-based edits change only the region marked by a mask or by strokes drawn on the image.
• Factuality ensures images accurately depict real-world subjects.

The model renders photorealistic skin tones, intricate materials, sharp lighting, and coherent backgrounds at the latency and cost of a Flash-tier model.

Integration and Access

Developers can call the model using the model name google/gemini-nano-banana-2.1 via the AI SDK, the OpenAI-compatible Chat Completions API, or the AI CLI. The AI CLI is an open-source command-line tool from Vercel Labs that runs on AI Gateway, allowing any Gateway model ID to be used with the -m flag. Generated images are returned in result.files.

AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations. It reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.