Google: Nano Banana 2 (Gemini 3.1 Flash Image)

google/gemini-3.1-flash-image · GoogleNot yet established

Tokenizer lineage (measured): Gemini
Declared tokenizer tag: Gemini
Entered catalogue: 18 June 2026
Last tested: 22 August 2026
Evidence confidence: Moderate

Why moderate: near-exact agreement (44 of 44 strings) with google/gemini-3.7-flash, short of a full exact signature.

Evidence

✓ near-exact agreement (44/44) with google/gemini-3.7-flash

Compare with Google: Gemini 3.7 Flash

Report a correction

Identity statement

Google: Nano Banana 2 (Gemini 3.1 Flash Image) is Google's model. Its measured tokenizer sits with the Gemini group, which is evidence that it builds on the Gemini tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Google's authorship of the model itself.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Counted, using the 44 strings that came back reliably	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_b8f53431
How much it can read and write	Reads up to 131,072 tokens at once, writes up to 32,768	its own listing
Whether it thinks before answering	Reasons when asked to, at high, minimal, minimal by default	its own listing
Who served our requests	Google, Google AI Studio	we measured it, 22 August 2026

Closest measured models

Agreement across the mutually clean test strings

Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash44/44 · 100%Google: Gemma 3 4Bgoogle/gemma-3-4b-it44/44 · 100%Google: Gemma 3 12Bgoogle/gemma-3-12b-it44/44 · 100%Google: Gemma 3 27Bgoogle/gemma-3-27b-it44/44 · 100%Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite44/44 · 100%Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite44/44 · 100%

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent Google: Nano Banana 2 (Gemini 3.1 Flash Image) fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.

All 50 rows, 6 excluded as corrupt

English and whitespace

en-prosex

en-long16

spaces-20x

spaces-60x

tabs-203

newlines-203

mixed-ws9

Digits

digits-99

digits-1212

digits-3030

digits-sep12

float-long22

CJK

zh-common10

zh-long12

zh-rare25

ja-kana7

ja-kanji9

ko11

Other scripts

ru12

ar10

he13

hi8

th10

el13

Emoji

emoji-basic5

emoji-skin10

emoji-zwj-familyx

emoji-zwj-x3x

emoji-flags8

emoji-profx

Rare Unicode

math26

boxdraw17

combining10

cjk-ext-b16

surrogates27

zalgo22

rtl-mix5

Code

py-code28

py-indent18

json28

html14

regex44

camel6

snake11

Repetition and encodings

rare-word-x525

repeat-tok21

base6434

hex16

url23

uuid36

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 0 prompt tokens.

Declared record

What the catalogue claims about this model

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

Modalities: text+image->text+image
Declared tokenizer: Gemini
Prompt price: $0.50 / M tokens
Completion price: $3.00 / M tokens

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken

18 June 2026Enters the OpenRouter catalogue declared as Gemini.
22 August 2026Fingerprinted in the YFarmX catalogue sweep · 44 of 50 strings measured clean.
22 August 2026YFarmX assessment: consistent with the Gemini family, moderate confidence.