NewHow we catch a seller listing the wrong model, and refund you if one does.

What API can I use for uncensored roleplay in SillyTavern or Janitor AI?

MartLLM works in both: SillyTavern through Chat Completion → Custom (OpenAI-compatible) with base URL https://api.martllm.com/v1, and Janitor AI through a proxy configuration with https://api.martllm.com/v1/chat/completions. On November 20, 2026, 12 uncensored text models were taking requests, billed per token with no subscription. The lowest-priced is GLM 4.7 Flash Heretic at $0.049 per million input tokens and $0.2797 per million output tokens. There is no ID or KYC check: sign up with an email code or with Google, then add prepaid credit by card or PayPal, from $5.

Prices as of November 20, 2026, 11:00 UTC. This page is rebuilt every hour.

ModelInput / 1M tokensOutput / 1M tokensBelow list price
DeepSeek V4.1 Flash 1017 Uncensored$0.2145$0.85835%
DeepSeek V4.1 Flash Uncensored$0.2244$0.897632%
Abliterated Large V2$1.74$2.9042%
Venice Role Play Uncensored$0.2747$1.098945.1%
Venice Uncensored 1.2$0.1111$0.499944.5%
Abliterated Large Flash$0.6985$1.396944.1%
GLM 4.7 Flash Heretic$0.049$0.279730.1%
Gemma 4 26B A4B Uncensored (E2EE)$0.1055$0.488744.5%
Qwen 3.6 Plus Uncensored$0.5125$3.07518%
Venice Uncensored 1.1$0.19$0.8555%
Qwen 3.6 35B A3B Uncensored (E2EE)$0.20$0.60
OrcaCyber: GLM 5.3 Flash Abliterated / Uncensored$0.736$1.4728%

MartLLM adds no fee to these prices · every model and price →

More questions

Which model name do I enter?

The model id from the table, for example deepseek/deepseek-v4.1-flash-uncensored. SillyTavern can also fetch the list after you connect.

What is still not allowed?

Uncensored means the model does not refuse legal adult or sensitive topics; MartLLM’s terms still ban breaking the law and sexual content involving minors.