The Gemini API model identifier is gemini-nano-banana-2.1. Google describes it as a high-efficiency image-generation and conversational-editing model.
The release notes list improvements in visual quality, prompt adherence, multi-turn character consistency, and text rendering. They also list support for wide and panoramic aspect ratios of 1:4, 4:1, 1:8, and 8:1 at 1K, 2K, and 4K resolutions.
On the same date, Google deprecated gemini-3.1-flash-image, known as Nano Banana 2, and directs developers to migrate to Nano Banana 2.1. No shutdown date for the deprecated model has been announced.
The changelog does not provide benchmark results, pricing, rate limits, or a compatibility guarantee for existing image-generation workflows. Source: https://ai.google.dev/gemini-api/docs/changelog