inclusionAI: Ling 3.1 Flash

inclusionai/ling-3.1-flash · InclusionAITokenizer lineage measured

Tokenizer group (measured): InclusionAI
Entered catalogue: 2 October 2026
Last tested: 17 October 2026
Evidence confidence: Very high

Why very high: an exact fingerprint shared with 7 models and an identical API contract inside the same group: two signals of different kinds agree.

Evidence

✓ exact tokenizer signature shared with 7 models
✓ API-surface contract identical to a group member

Compare with inclusionAI: Ling 3.0 Flash VL

Report a correction

Identity statement

inclusionAI: Ling 3.1 Flash is InclusionAI's model, and its measured tokenizer sits in InclusionAI's own signature group alongside its sibling models. No other maker's measured model shares it so far.

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 7 other models	tk_fc5a4585
How its API is set up	Set up identically to 3 other listings, field for field	api_386688aa
How much it can read and write	Reads up to 262,144 tokens at once, writes up to 32,768	its own listing
Whether it thinks before answering	Reasons when asked to	its own listing
Who served our requests	Novita	we measured it, 17 October 2026

Shares this fingerprint

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

inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1texact · 50/50 inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flashexact · 50/50 inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flashexact · 50/50 inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-finexact · 50/50 inclusionAI: Ling 3.0 Flash Sante (free)inclusionai/ling-3.0-flash-sante:freeexact · 50/50 inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vlexact · 50/50 inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1texact · 50/50

Closest measured models

Agreement across the mutually clean test strings

inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash50/50 · 100%inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash50/50 · 100%inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1t50/50 · 100%inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1t50/50 · 100%inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin50/50 · 100%inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl50/50 · 100%

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent inclusionAI: Ling 3.1 Flash 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-603

tabs-205

newlines-2022

mixed-ws9

Digits

digits-99

digits-1212

digits-3030

digits-sep12

float-long22

CJK

zh-common9

zh-long10

zh-rare18

ja-kana10

ja-kanji13

ko12

Other scripts

ru15

ar14

he19

hi25

th15

el21

Emoji

emoji-basic10

emoji-skin20

emoji-zwj-family11

emoji-zwj-x333

emoji-flags16

emoji-prof20

Rare Unicode

math28

boxdraw30

combining5

cjk-ext-b16

surrogates40

zalgo36

rtl-mix9

Code

py-code26

py-indent18

json25

html16

regex45

camel5

snake6

Repetition and encodings

rare-word-x531

repeat-tok41

base6436

hex18

url19

uuid36

Overhead subtracted: 20 prompt tokens.

Declared record

What the catalogue claims about this model

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

Modalities: text->text
Declared tokenizer: Other
Prompt price: $0 / M tokens
Completion price: $0 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_logprobstop_p

Default settings

No values declared

Catalogue entry

History

Every observation, kept as taken

2 October 2026Enters the OpenRouter catalogue with no declared family.
17 October 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
17 October 2026YFarmX assessment: consistent with the InclusionAI family, very high confidence.