AionLabs: Aion-RP 1.0 (8B)

aion-labs/aion-rp-llama-3.1-8b · Aion LabsNot yet established

Declared family: Unknown
Entered catalogue: 4 February 2025
Last tested: 3 September 2026
Measured signature: tk_559886c2

Identity statement

AionLabs: Aion-RP 1.0 (8B) has a clean measured fingerprint that currently sits alone: no other measured model shares its signature.

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 cleanly, and no other model in the catalogue counts the same way	tk_559886c2
How its API is set up	A combination of settings no other listing in the catalogue uses	api_a52f44e9
How much it can read and write	Reads up to 32,768 tokens at onceOpenRouter's listing shows 29,491 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Who served our requests	AionLabs	we measured it, 3 September 2026

Closest measured models

Agreement across the mutually clean test strings

Union Alphastealth/union-alpha29/47 · 62%Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct30/50 · 60%Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct30/50 · 60%Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct30/50 · 60%Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct30/50 · 60%Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b30/50 · 60%

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent AionLabs: Aion-RP 1.0 (8B) 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-prose13

en-long14

spaces-203

spaces-603

tabs-203

newlines-204

mixed-ws5

Digits

digits-94

digits-125

digits-3011

digits-sep8

float-long10

CJK

zh-common12

zh-long18

zh-rare18

ja-kana12

ja-kanji12

ko14

Other scripts

ru14

ar12

he24

hi14

th14

el13

Emoji

emoji-basic9

emoji-skin29

emoji-zwj-family14

emoji-zwj-x344

emoji-flags24

emoji-prof25

Rare Unicode

math30

boxdraw23

combining11

cjk-ext-b13

surrogates40

zalgo35

rtl-mix8

Code

py-code24

py-indent15

json19

html16

regex44

camel5

snake6

Repetition and encodings

rare-word-x530

repeat-tok20

base6434

hex11

url17

uuid28

Overhead subtracted: 9 prompt tokens.

Declared record

What the catalogue claims about this model

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

Modalities: text->text
Declared tokenizer: Other
Prompt price: $0.80 / M tokens
Completion price: $1.60 / M tokens

Supported parameters

max_tokenstemperaturetop_p

defaults: {}

Catalogue entry

History

Every observation, kept as taken

4 February 2025Enters the OpenRouter catalogue with no declared family.
3 September 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.