Meta: Llama 3.1 70B Instruct

meta-llama/llama-3.1-70b-instruct · MetaDeclared and measured agree

Tokenizer lineage (measured): Llama3
Evidence confidence: Very high
Declared tokenizer tag: Llama3
Entered catalogue: 23 July 2024
Last tested: 21 August 2026
Measurement: Measured

Evidence

exact tokenizer signature shared with 5 models
API-surface contract identical to a group member

Compare with Sao10K: Llama 3.3 Euryale 70B

Download JSON Report a correction

Identity statement

Meta: Llama 3.1 70B Instruct is Meta's model. Its measured tokenizer sits with the Llama3 group, which is evidence that it builds on the Llama3 tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Meta's authorship of the model itself.

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Exact match with 5 other models	tk_6588ed5b
API surface	Identical contract to 1 other entry	api_607fdf1c
Context and output	131,072 context · 16,384 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	DeepInfra	measured 21 August 2026

Shares this fingerprint

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

Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instructexact · 50/50 Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructexact · 50/50 Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructexact · 50/50 Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70bexact · 50/50 Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70bexact · 50/50 Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instructsame tokenizer · template shift Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405bsame tokenizer · template shift Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70bsame tokenizer · template shift Nous: Hermes 4 70Bnousresearch/hermes-4-70bsame tokenizer · template shift Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8bsame tokenizer · template shift

Closest measured models

Agreement across the mutually clean test strings

Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct50/50 · 100%Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct50/50 · 100%Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct50/50 · 100%Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b50/50 · 100%Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b50/50 · 100%Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct48/50 · 96%

Click a row to open the full comparison.

The measured fingerprint

Marginal prompt-token cost of each test string, grouped by script

All 50 rows

English and whitespace

en-prose14

en-long16

spaces-203

spaces-603

tabs-203

newlines-204

mixed-ws5

Digits

digits-93

digits-124

digits-3010

digits-sep7

float-long9

CJK

zh-common12

zh-long18

zh-rare18

ja-kana11

ja-kanji12

ko14

Other scripts

ru14

ar12

he24

hi15

th14

el13

Emoji

emoji-basic10

emoji-skin30

emoji-zwj-family15

emoji-zwj-x345

emoji-flags24

emoji-prof26

Rare Unicode

math31

boxdraw23

combining11

cjk-ext-b13

surrogates40

zalgo35

rtl-mix8

Code

py-code25

py-indent15

json20

html16

regex44

camel5

snake6

Repetition and encodings

rare-word-x530

repeat-tok21

base6435

hex11

url17

uuid27

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 10 prompt tokens.

Declared record

What the catalogue claims about this model

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

Modalities: text->text
Declared tokenizer: Llama3
Prompt price: $0.40 / M tokens
Completion price: $0.40 / M tokens

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

defaults: {}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

23 July 2024Enters the OpenRouter catalogue declared as Llama3.
21 August 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
21 August 2026YFarmX assessment: consistent with the Llama3 family, very high confidence.

Cite this page as the evidence record for Meta: Llama 3.1 70B Instruct: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.