Skip to content
effecthub
Verified Oct 15, 2026

Nano Banana

Verified Oct 15, 2026 Active
Use tool
Share

Google DeepMind's image generation and editing models, built on Gemini and sold per image through the Gemini API

text to imageimage generationimage apiprompt adherenceFreemium · from $0.0336/image

Listed on EffectHub ·

InputsTTextOutputsImagesWeb · iOS · Android · API
Screenshot of the Nano Banana website
#1050
deepmind.google as we captured it — our own screenshot, not the vendor’s press image.

Pricing

Pricing model
Freemium
Paid options from
$0.0336/image
Billing
Metered · per image

Free in the Gemini app and Google AI Studio within plan limits; the Gemini API bills per output image with no free tier for image models: Nano Banana 2 Lite and Nano Banana 2.1 from $0.0336 at 1K, Nano Banana 2 from $0.045 at 0.5K and $0.067 at 1K, Nano Banana Pro $0.134 at 1K or 2K and $0.24 at 4K, batch mode at half those rates.

Use tool ↗
Overview

About Nano Banana

Nano Banana is the current name for Google DeepMind's image generation and editing family, which has replaced Imagen: the model page now lists Nano Banana Pro (Gemini 3 Pro Image), Nano Banana 2 (Gemini 3.1 Flash Image) and Nano Banana 2 Lite, all built on Gemini rather than the diffusion-era Imagen line. The models generate from text, edit existing pictures, keep characters consistent across shots and render legible text, and they are reachable in the Gemini app and Google AI Studio for free, and through the Gemini API and Google Cloud's agent platform per image. Imagen itself has been shut down in the Gemini API and its Vertex AI endpoints are listed as discontinued with a migration path to the Gemini image models.

Platforms
Web · iOS · Android · API
API
Yes
Last verified
Oct 15, 2026

Verified sources

  • The old Imagen model page redirects to the Nano Banana page, which lists Nano Banana Pro (Gemini 3 Pro Image), Nano Banana 2 (Gemini 3.1 Flash Image) and Nano Banana 2 Lite, available in the Gemini app, Google AI Studio, the Gemini API and the Gemini Enterprise Agent Platform; the word Imagen does not appear (15 October 2026)deepmind.google ↗
  • Gemini API pricing: Nano Banana 2 Lite and Nano Banana 2.1 $0.0336 per 1K image, Nano Banana 2 $0.045 at 0.5K and $0.067 at 1K, Nano Banana Pro $0.134 at 1K/2K and $0.24 at 4K, batch at half price; free tier marked not available for image models (15 October 2026)ai.google.dev ↗
  • Gemini API Imagen page states the Imagen models are shut down and no longer available, and tells developers to use Nano Banana with generate_content instead of generate_images; page last updated 17 September 2026 (read 15 October 2026)ai.google.dev ↗
  • Vertex AI image overview lists every Imagen 3 and Imagen 4 endpoint as discontinued, maps each to gemini-2.5-flash-image and recommends updating endpoints before 30 June 2026; last updated 13 October 2026 (read 15 October 2026)docs.cloud.google.com ↗
Fact check

Is Nano Banana legit?

We don’t label tools safe or unsafe. Below are the records we checked ourselves, each with the date we read it.

Domain registered
Sep 7, 2023 (3 years ago)Registry record (RDAP), registrar MarkMonitor Inc., looked up Sep 6, 2026
TLS certificate
Issued by Google Trust Services, valid until Jan 9, 2027Seen in our own connection to the site on Oct 15, 2026
Last checked
Oct 15, 2026The site answered
Operated by
Google DeepMind, United StatesOur research, card verified Oct 15, 2026

How we collect these records

Editorial verdict

Pros & cons of Nano Banana

high confidence

If you came here for Imagen, it is gone: the Gemini API has shut the Imagen models down, Vertex AI lists their endpoints as discontinued, and the DeepMind page redirects to Nano Banana. What replaced it is a stronger editing-first family that keeps characters consistent, follows layout instructions and renders text, priced by the image at rates that undercut most rivals at the Lite tier. Pick it when you need editing and consistency inside a Google stack; look elsewhere if you need an open-weights model you can run yourself.

Pros

  • Three tiers from a cheap Lite model to a 4K Pro model, all under one API
  • Editing, multi-image reference and character consistency are first-class rather than bolted on
  • Readable in-image text, a weak spot of earlier generators
  • Free access in the Gemini app and AI Studio before any API spend

Cons

  • The Imagen name, SDK method and response format are retired, so existing integrations break
  • No free tier in the API for image models — every generated image is billed
  • Output carries Google's SynthID watermark and usage sits under Google's content policies
  • Pro-tier 4K images cost about seven times a Lite image

Best for

  • Product and marketing teams editing existing images with text instructions at scale
  • Developers already on the Gemini API who want image generation on the same key and bill
  • Casual users, since the Gemini app and AI Studio expose the models for free

Not for

  • Teams that need open weights or on-premises inference — nothing here is downloadable
  • Pipelines hard-wired to the Imagen endpoints, which now need a code migration rather than a version bump

Watch out: Code written against Imagen (generate_images) must move to generate_content on a Gemini image model; Vertex AI asked customers to switch endpoints before 30 June 2026 and the Gemini API has already shut Imagen down.

Nano Banana head-to-head

Side-by-side fact sheets against the competitors our research or their makers name — pricing, platforms, API and both verdicts on one page.

Tasks

Also used for

Professions

AI tools by profession

Text-to-Image Generators is one of the jobs on these pages:

Be the first to review Nano Banana

Ask a question about Nano Banana