Standard Interface
POST /v1/chat/completions works with existing OpenAI SDKs and clients.
Uncensored LLM API
Uncensor Chat API for Developers
Get an open-weight uncensored chat API that returns 100,000-token context without content refusals for lawful adult use.
- $0.15 per 1M input tokens
- Crypto billing, no card
- OpenAI compatible endpoint
Try it in one request
curl https://api.chatuncensor.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Send me the current UTC timestamp."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.chatuncensor.com/v1", api_key="YOUR_KEY")
resp = client.chat.completions.create(
model="uncensored",
messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.chatuncensor.com/v1", apiKey: process.env.API_KEY });
const resp = await client.chat.completions.create({
model: "uncensored",
messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute
What you get
No Content Refusals
The model answers controversial topics without blocking lawful adult content.
Streaming Support
Receive tokens via SSE with usage metrics included in the final chunk.
JSON Mode
Force structured outputs using response_format json_object for reliable parsing.
Tool Calling
Execute functions with tools and tool_choice parameters exactly as defined.
Privacy First
Prompts are never used for training your data or model tuning.
How it works
Create Account
Sign up with Google or email to get your API key instantly.
Top Up Crypto
Add credits via USDT or USDC with bonus incentives for larger amounts.
Send Requests
Point your client to our base URL and start generating text.
What people build with it
Uncensored Roleplay
Generate unrestricted fictional narratives without arbitrary word filters blocking your story.
Security Research
Test prompt injection techniques without the model refusing dangerous but legal queries.
Adult Content Generation
Produce mature text content for applications requiring NSFW tolerance without extra flags.
Data Annotation
Label data or classify text without the model refusing based on tone.
From Signup to First Token: How It Works
Create an account with Google or email and receive your API key instantly.
- Visit the
Get API keypage and complete signup. - Claim $0.50 trial credit; no card required.
- Configure your client to point at
https://api.chatuncensor.com/v1. - Send a request to
/v1/chat/completionswith modeluncensored. - Receive unrestricted text responses immediately.
Uncensor Chat: Concrete Use Cases for NSFW Tolerant Generation
Our API delivers direct, unfiltered responses without hiding adult themes behind polite refusals.
Roleplay Stories
Generate explicit fictional narratives where the model follows your lead without censoring mature vocabulary or actions.
Medical Data
Process raw clinical notes containing sensitive terminology without artificial filtering distorting the actual medical context.
Security Research
Extract detailed vulnerability descriptions from technical logs without unnecessary moderation blocks interfering with your parsing logic.
Token Arithmetic: Real Cost Examples for Your Budget
Costs are calculated strictly from token counts at $0.15 per million input and $0.50 per million output tokens.
A 50k prompt with 500 output tokens costs exactly $0.0075.
Errors consume no credits, ensuring you pay only for actual text generated.
| Input Tokens | Output Tokens | Total Cost |
|---|---|---|
| 100,000 | 10,000 | $0.020 |
| 50,000 | 500 | $0.0075 |
Use prepaid crypto to cover these precise, transparent rates.
Three Steps to Migrate from Your Current OpenAI-Compatible Provider
Switch your integration in minutes by updating two configuration values. First, replace your existing base URL with our endpoint: HTTPS://api.chatuncensor.com/v1. Second, swap your current API key for the one issued on your dashboard. Third, change the model ID from "gpt-4" to "uncensored" in your SDK settings. Our interface is fully openai compatible, so your existing code runs without modification. Streaming and function calling work immediately with no extra setup required.
The Provider Checklist: 7 Checks for Choosing an Uncensored LLM
Verify that the model itself lacks hard refusals, not just the frontend wrapper. Ensure your prompts are never used for training your data. Confirm you can pay via crypto without linking a bank account. Check that error responses do not consume your prepaid credit. Ensure the API follows standard OpenAI-compatible patterns for easy integration. Verify privacy claims match the actual data retention policy.
Who This Is For (And Who Should Look Elsewhere)
Who This Is For (And Who Should Look Elsewhere)
Developers needing an uncensored LLM for adult content get reliable text generation without refusal. Our 100k context window handles long chats.
- Use cases: NSFW chatbot interfaces, unrestricted creative writing, and unfiltered research where model bias matters.
- Not for: Apps requiring image generation, embeddings, or fine-tuning. We only offer text completions via the standard API.
Questions and answers
What is uncensor chat and how does it work?
It is an open-weight model endpoint that returns text without content refusals for lawful adult use. You send POST requests to our standard chat-completions interface and receive direct text responses.
Does it cost money to use the API?
Yes, you pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals incur zero charge, and prepaid credit never expires.
How do I get started with a free trial?
Every new account receives $0.50 of trial credit valid for 7 days.
Can I uncensor chat in settings like a consumer app?
No, this is a raw API for developers, not a consumer interface with toggle settings. You receive unfiltered model output directly as structured JSON or text.
What payment methods are accepted for top-ups?
We accept crypto only: USDT on TRC20 or USDC on Base. You can top up any whole amount from $20 to $500 to receive bonus credit.
Is there a limit on how many tokens I can generate?
You can generate up to 16,000 tokens per request. The total context window supports 100,000 tokens for both the prompt and the completion combined.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
