Enterprise DNAEnterprise DNA
Google logo

Models · Best vision

Nano Banana 2.1

by Google

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

Our verdict

Not reviewed yet

We have not reviewed Nano Banana 2.1 yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

Best for

Conversational image iteration

Notes

Nano Banana 2.1 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Generating an image from a visual direction
  • image, text input; image, text output on the listed OpenRouter route

Cons

  • Assuming every Gemini model can generate images
  • Ignoring image-output charges in a token estimate
  • This route produces non-text output or rerank results. Listed text-token rates are not a complete workload price; zero text-token rates do not mean free generation. Verify the route-specific billing unit before estimating cost.

Key facts

What we have checked

Input price
$1.50 per million tokens
Checked OpenRouter models API
Output price
$7.50 per million tokens
Checked OpenRouter models API
Price on google-ai-studio
$1.50 per million input tokens
Checked OpenRouter models API
Price on google-ai-studio
$7.50 per million output tokens
Checked OpenRouter models API
Latest version
google/gemini-nano-banana-2.1-20261006
Checked OpenRouter models API
Time to first token (ms) on google-ai-studio
16,994
Checked OpenRouter models API
Tokens served on OpenRouter in a day
521.2M (for 28 Oct 2026)
Checked OpenRouter model activity (728 of 728 series)
Tool calls on OpenRouter in a day
77 (for 28 Oct 2026)
Checked OpenRouter model activity (728 of 728 series)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `google/gemini-nano-banana-2.1`.

  • openrouter · google/gemini-nano-banana-2.1 · Docs

OpenRouter id: google/gemini-nano-banana-2.1

Price

What Nano Banana 2.1 costs, over time

Input price

$1.50 to $1.50

US dollars per million input tokens. 7 Oct 2026 to 28 Oct 2026, 19 days.

Source: OpenRouter models API. Checked .

Output price

$7.50 to $7.50

US dollars per million output tokens. 7 Oct 2026 to 28 Oct 2026, 19 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
google-ai-studioInput$1.50 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-ai-studioOutput$7.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Nano Banana 2.1 is used

Tokens served a day

67.4M to 521.2M

tokens a day on OpenRouter. 6 Oct 2026 to 28 Oct 2026, 23 readings.

Source: OpenRouter model activity (728 of 728 series). Checked .

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

USAGE / OPENROUTER

How much Nano Banana 2.1 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
2B ▲46.8%
Requests, last 7 days
558K
Tool calls, last 7 days
822
Price per million tokens
$1.5 in · $7.5 out
0500M1B6 Oct: 67.4M tokens, 19.6K requests7 Oct: 264M tokens, 65.8K requests8 Oct: 165M tokens, 51.2K requests9 Oct: 197M tokens, 54.7K requests10 Oct: 193M tokens, 53.3K requests11 Oct: 201M tokens, 52.1K requests12 Oct: 201M tokens, 56.7K requests13 Oct: 205M tokens, 59.2K requests14 Oct: 210M tokens, 61.6K requests15 Oct: 216M tokens, 60.5K requests16 Oct: 201M tokens, 59.3K requests17 Oct: 160M tokens, 52.3K requests18 Oct: 161M tokens, 54.7K requests19 Oct: 198M tokens, 61.2K requests20 Oct: 197M tokens, 60K requests21 Oct: 209M tokens, 62.6K requests22 Oct: 216M tokens, 61.4K requests23 Oct: 216M tokens, 62.8K requests24 Oct: 171M tokens, 51.7K requests25 Oct: 173M tokens, 52.5K requests26 Oct: 204M tokens, 58.3K requests27 Oct: 467M tokens, 129K requests28 Oct: 521M tokens, 142K requests6 Oct20 Oct28 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Nano Banana 2.1.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-24. Hosting routes and app features can differ.

DeveloperGoogle
Exact model identifiergoogle/gemini-nano-banana-2.1
Inputimage, text
Outputimage, text
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
image
Licence verification
Check the developer licence; the model name is insufficient
Context length
66K tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
6 Oct 2026
Listed retirement date
Not established

This route produces non-text output or rerank results. Listed text-token rates are not a complete workload price; zero text-token rates do not mean free generation. Verify the route-specific billing unit before estimating cost.

Consider it for

  • Generating an image from a visual direction
  • Revising an owned product scene while retaining the subject

Watch for

  • Assuming every Gemini model can generate images
  • Ignoring image-output charges in a token estimate

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Using an owned reference image of a chair, place the same chair in a bright reading corner. Preserve the chair shape and fabric colour; add no writing.

Check the result: Compare reference and output for chair identity, colour preservation and absence of added text.

Inspect the sources and their scope
catalogue source ↗

google/gemini-nano-banana-2.1: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-24
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-10-24
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

This route uses image pricing. A token calculator is not a quote for this model. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.