Nano Banana 2 (Gemini 3.1 Flash Image Preview)

Google· released 26 Feb 2026

google/gemini-3.1-flash-image-preview

Input / 1M tokens: $0.5
Output / 1M tokens: $3

Context window66K tokens

Longest answer: 59K tokens

reads imagereads textvisionreasoning

About

Nano Banana 2, also named Gemini 3.1 Flash Image Preview, is Google’s image generation and editing model. It accepts text and image inputs and produces image and text outputs. The listed context window is 65,536 tokens, with a maximum output of 58,982 tokens. It supports reasoning. Input costs USD 0.5 per 1M tokens and output costs USD 3 per 1M tokens. Its model identifier is google/gemini-3.1-flash-image-preview. For builders, its image generation and editing role makes it relevant to visual workflows, while accepting images as input also supports editing-oriented tasks. The listing identifies it as a preview. The facts do not specify tool support, so no tool capability is stated. It was released on 2026-02-26. The listed outputs include both image and text, distinguishing it from models that return text only.

Who it is for

Teams building image generation or editing workflows may consider Nano Banana 2. Its text and image inputs and image and text outputs are relevant to visual applications.