Google: Nano Banana (Gemini 2.5 Flash Image)

google/gemini-2.5-flash-image · GoogleDeclared and measured agree

Tokenizer lineage (measured): Gemini
Declared tokenizer tag: Gemini
Entered catalogue: 7 October 2025
Last tested: 3 September 2026
Evidence confidence: High

Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet.

Evidence

✓ exact tokenizer signature shared with 21 models

Compare with Google: Nano Banana 2.1

Report a correction

Identity statement

Google: Nano Banana (Gemini 2.5 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	Counts every one of the 50 test strings exactly like 21 other models	tk_59ca250f
How its API is set up	A combination of settings no other listing in the catalogue uses	api_1fca876b
How much it can read and write	Reads up to 32,768 tokens at once, writes up to 8,192	its own listing
Who served our requests	Google	we measured it, 3 September 2026

Shares this fingerprint

Exact signature first; template-boundary shifts of the same signature beneath

Closest measured models

Agreement across the mutually clean test strings

Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash50/50 · 100%Google: Gemma 3 4Bgoogle/gemma-3-4b-it50/50 · 100%Google: Gemma 3 12Bgoogle/gemma-3-12b-it50/50 · 100%Google: Gemma 3 27Bgoogle/gemma-3-27b-it50/50 · 100%Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite50/50 · 100%Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite50/50 · 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 (Gemini 2.5 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

English and whitespace

en-prose14

en-long16

spaces-203

spaces-604

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-family7

emoji-zwj-x321

emoji-flags8

emoji-prof11

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

Overhead subtracted: 0 prompt tokens.

Declared record

What the catalogue claims about this model

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

Modalities: text+image->text+image
Declared tokenizer: Gemini
Prompt price: $0.30 / M tokens
Completion price: $2.50 / M tokens

Supported parameters

max_tokensresponse_formatseedstopstructured_outputstemperaturetop_p

defaults: {"temperature":null,"top_p":null,"frequency_penalty":null}

Catalogue entry

History

Every observation, kept as taken

7 October 2025Enters the OpenRouter catalogue declared as Gemini.
3 September 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
3 September 2026YFarmX assessment: consistent with the Gemini family, high confidence.