Nano Banana 2.1
gemini-nano-banana-2.1
Google · chat · api
Context
65.5K
Max output
65.5K
Input $/1M
$1.50
Output $/1M
$30.00
Modalities
text
Released
06 Oct 2026
AI summary
● machine-written
Google releases Nano Banana 2.1 image generation model
Nano Banana 2.1 is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It accepts text and image inputs and returns images with optional text, supporting 1K, 2K, and 4K output resolutions. The model offers improved visual quality, multi-turn character consistency, accurate text rendering, and search-grounded generation at reduced pricing compared to its predecessor.
What's new
- Improved visual quality and realism for 1K, 2K, and 4K output resolutions
- Corrected mosaic artifacts on wide-angle and panoramic formats
- Enhanced text rendering and layout precision for infographics
- Multi-image fusion support for up to 14 reference images with character and object consistency
- Configurable reasoning levels (minimal, medium, high) and Web Search grounding
Best for
High-efficiency image generation and conversational editingMulti-turn character consistency and object fidelity tasksText rendering and infographic design generationProduct recontextualization and mask- or ink-based editing
Source: https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1