UncensoredLLM

Uncensored LLM API,
on one prepaid key.

98 abliterated and uncensored open-weight models through one OpenAI-compatible key and the SDK you already use.

https://api.uncensoredllm.ai/v1 · 98 models and prices

OpenAI SDK · Python
from openai import OpenAI
client = OpenAI(
  base_url="https://api.uncensoredllm.ai/v1",
  api_key="sk-ullm-live-...",
)

Try it.

curl https://api.uncensoredllm.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-ullm-live-..." \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-uncensored", "messages": [{"role": "user", "content": "Say hello in five words."}]}'

GLM-5.3 Uncensored: $0.30 in · $0.873 out per million tokens.

Run it in the console

Every build, one price list.

Google (community tune)

29 models · from $1.25 per M output

Qwen (community tune)

16 models · from $1.53 per M output

UncensoredLLM

13 models · from $3.00 per M output

Z.ai

11 models · from $0.3802 per M output

90 of 90 checked models answered today's real-model check.

Prepaid credit, priced per token.

$10
Minimum top-up
No expiry
On the balance
98
Models on one key
$10 credit$25 credit$50 credit$100 credit$250 credit$500 credit

Common questions.

What does abliterated mean?

An abliterated model is an open-weight model whose refusal direction has been removed from the weights, so it answers instead of declining. It is not a jailbreak prompt: there is nothing to paste and nothing to maintain.

Which clients work with it?

Anything that speaks the OpenAI API: the official OpenAI SDKs, SillyTavern, Janitor AI proxies, OpenCode, Cline, Open WebUI and plain curl. Set the base URL and the key; the model ids are on the Models page.

What does it cost?

Each model has an input and an output price per million tokens on the Models page. You pay exactly those, from a prepaid balance that starts at $10 and never expires. No subscription, no seat fee.

Do you store my prompts?

No. Request and response bodies are not retained unless a key opts in to seven days of replay. The usage log keeps the model, the token counts and the charge.

Something else? Contact us.

Get a key in two minutes.

Sign in, top up from $10, paste the base URL into your client.

Open the console →