Home / Models / Nano Banana 2.1

Nano Banana 2.1

Google · Image model

Google's newest Flash-tier image model, a generally available update to Nano Banana 2 (Gemini 3.1 Flash Image). Google says it improves visual quality, prompt adherence, multi-turn character consistency and text rendering at Flash-tier speed and cost. Google now recommends migrating…

Current
ReleasedOct 6, 2026
Context window—
Input → outputtext, image → image, text
API pricegemini-nano-banana-2.1 (Standard): $1.50 / 1M text/image input tokens; $30.00 / 1M image output tokens (approx. $0.0336 per 1K image, $0.0504 per 2K, $0.113 per 4K). Batch roughly half.
Consumer accessReported rollout to Google AI Mode, Flow, Google AI Studio and Stitch on launch day; Gemini app status not verified.

Best for

Fast, low-cost image generation and conversational editing with good text rendering, including 4K and very wide/tall formats.

Overview

Google's newest Flash-tier image model, a generally available update to Nano Banana 2 (Gemini 3.1 Flash Image). Google says it improves visual quality, prompt adherence, multi-turn character consistency and text rendering at Flash-tier speed and cost. Google now recommends migrating from gemini-3.1-flash-image to this model.

Strengths and limits

  • Highest-ranked Google image model on Artificial Analysis (Oct 2026)
  • 1K, 2K and 4K output; panoramic ratios up to 8:1 and 1:8
  • Lower per-image price than Nano Banana 2 and Nano Banana Pro
  • No free tier on the Gemini API (reported)
  • 512px fast-draft size from Nano Banana 2 was dropped (reported)

Published benchmark scores

Artificial Analysis Text to Image Arena Elo1173 (rank 4) Source: artificialanalysis.ai

Scores are as published by the source; settings (reasoning effort, tools, attempts) differ between labs, so compare with care. How to read benchmarks →