Model directory

Models under test

Thirteen text models are in the launch protocol. Filter the roster, inspect provider facts, and see exactly which evidence is still missing.

ProviderPrivacyUse case

Score 67.4

Aion 3.0

AionLabs · 131,072 token context

openrouterprivacy unverifiedroleplaystorytelling

Score 40.0

MiniMax M2-her

MiniMax · 65,536 token context

openrouterprivacy unverifiedroleplaydialogue

Live tested — review incomplete

Cydonia 24B V4.1

TheDrummer · 131,072 token context

openrouterprivacy unverifieduncensoredcreative-writing

Score 50.0

Llama 3.3 Euryale 70B

Sao10K · 131,072 token context

openrouterprivacy unverifiedroleplaycreative-writing

Score 85.4

Dolphin Mistral 24B Venice Edition

Cognitive Computations / Venice · 128,000 token context

openrouterprivacy unverifieduncensoredinstruct

Score 77.8

Hermes 3 405B

Nous Research · 131,072 token context

openrouterprivacy unverifiedsteerableroleplay

Score 85.7

UnslopNemo 12B

TheDrummer · 1,024,000 token context

openrouterprivacy unverifiedroleplaylow-cost

Score 76.0

MythoMax 13B

Gryphe · 8,192 token context

openrouterprivacy unverifiedroleplaylegacy

Score 40.0

Magnum V4 72B

Anthracite · 16,384 token context

openrouterprivacy unverifiedroleplayprose

Score 76.7

Venice Uncensored 1.2

Venice / Cognitive Computations · 128,000 token context

veniceprivate routeuncensoredprivate

Score 75.6

Venice Role Play Uncensored

Venice / dphnAI · 128,000 token context

veniceprivate routeuncensoredroleplay

Score 87.7

Gemma 4 Uncensored

Community / Venice · 256,000 token context

veniceprivate routeuncensoredprivate

Live tested — no textual output

Qwen3.6 35B A3B Uncensored E2EE

Community / Venice · 128,000 token context

veniceE2EE routeuncensorede2ee