All models
TheDrummer

Artemis 31B

TheDrummer's Gemma 4 31B finetune for roleplay and fiction. Holds a character, writes grimdark and explicit adult scenes without refusing, and keeps the prose vivid instead of sanitised. Reads images, calls tools, 262K context. Weak at coding and hard analysis: a storyteller, not a reasoner. A community finetune on a single NanoGPT host, so it can drop out briefly. Roughly a fifth of the price of Venice Role Play Uncensored. When the story needs real logic, DeepSeek V4.1 Flash Uncensored is the smarter pick.

UncensoredTwo kinds, both answer everything. Most are mainstream models with the refusal reflex cut out: same training, same worldview, no more dodging. UncensoredLM is the other kind: its own tuning, its own worldview, political takes that run against the mainstream.
Quick
Intelligence
~0.3 credits
Estimated price per message
262K tokens
Context window
Text, Images
Reads

The facts

Made by
TheDrummer
Content tier
UncensoredTwo kinds, both answer everything. Most are mainstream models with the refusal reflex cut out: same training, same worldview, no more dodging. UncensoredLM is the other kind: its own tuning, its own worldview, political takes that run against the mainstream.
Intelligence
Quick
Estimated price per message
~0.3 credits≈ 333 messages for 1 €
Context window
262K tokens≈ 403 pages of text in one go
Reads
Text, Images
Writes
Text
Tool use
Yes - search, memory, code and more
Served via
NanoGPT
Status
Current

A typical message: 16K tokens in, 1.5K out. Short replies cost less. Models served via OpenRouter bill the real provider cost plus our markup, so actual charges vary. 1 credit = 0.01 €.

Try Artemis 31B now.

No subscription. Free credits to start. The chat opens with Artemis 31B selected and a prompt ready - just send.