Gemini Nano Banana 2.1

Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) is the latest high-efficiency image generation and conversational editing model. An update to Nano Banana 2 (Gemini 3.1 Flash Image), it maintains Flash-level speed and cost efficiency while delivering significant improvements in visual quality, prompt adherence, multi-turn character consistency, and text rendering. It serves as the more efficient counterpart to Gemini 3 Pro Image (Nano Banana Pro).

Key updates:

  • Improved visual quality and realism across 1K, 2K, and 4K output resolutions (default 1K)
  • Fixed tiling artifacts on wide and panoramic aspect ratios (1:4, 4:1, 1:8, 8:1) at 2K and 4K resolutions
  • Enhanced text rendering and infographic layout accuracy
  • Multi-image fusion supporting up to 14 reference images (character consistency for up to 4 characters and object fidelity for up to 10 objects)
  • Grounding with Google Web and Image Search
  • Configurable Thinking levels (minimal, medium default, and high)

Documentation

Visit the Image generation page for full coverage of features and capabilities.

gemini-nano-banana-2.1

Property Description
Model code gemini-nano-banana-2.1
Supported data types

Inputs

Text, Image, Video, and PDF

Output

Image and Text
Token limits[*]

Input token limit

131,072

Output token limit

32,768
Capabilities

Audio generation

Not supported

Caching

Not supported

Code execution

Not supported

File search

Not supported

Function calling

Not supported

Grounding with Google Maps

Not supported

Image generation

Supported

Live API

Not supported

Search grounding

Supported

Structured outputs

Not supported

Thinking

Supported

URL context

Not supported
Consumption options

Batch API

Supported

Flex inference

Not supported

Priority inference

Not supported
Versions
Read the model version patterns for more details.
  • Stable: gemini-nano-banana-2.1
Latest update October 2026