Uncensored LLM API

Sans Censure API for NSFW and Unrestricted AI

Get an uncensored LLM via our OpenAI-compatible API, featuring a 100,000 token context window and zero corporate filters for unrestricted NSFW roleplay.

Prepaid crypto, no monthly fees
100,000 token context window
Standard OpenAI-compatible endpoints

Start now View documentation

Test with one request

curl https://api.sanscensure.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fix the null pointer in the async handler"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.sanscensure.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.sanscensure.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);

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Capabilities

No Corporate Guardrails

We do not refuse lawful adult, fictional, or controversial topics based on corporate regulations.

Standard OpenAI Interface

Use your existing SDKs with our /v1/chat/completions endpoint and simple base URL change.

Crypto Prepaid Only

Top up with USDT or USDC; credit never expires and errors cost nothing.

Streaming and Tools

Supports SSE streaming, function calling, and JSON mode for complex application logic.

Privacy First

Prompts are not used for training, and signup requires only an email address.

Single Uncensored Model

We serve one tuned model, eliminating routing complexity and ensuring consistent behavior.

Setup guide

Get Your Key

Sign up with Google or email and receive your API key instantly.

Add Crypto Credit

Top up with USDT or USDC to start using the uncensored API immediately.

Update Base URL

Point your OpenAI SDK to our endpoint and send your first request.

Integrations & builds

Unrestricted Roleplay

Generate extreme scenarios without getting blocked by standard corporate content filters.

Security Research

Probe model boundaries and get direct answers without unnecessary refusals or lectures.

Creative Writing

Produce adult or controversial narratives without worrying about arbitrary content restrictions.

Data Annotation

Get consistent outputs for labeling tasks without model-specific variations or routing issues.

Get Your Uncensored API Key in Seconds

Get Your Uncensored API Key in Seconds by visiting the Get API key page.

Instant Access

Sign up with Google or email. Receive your key immediately. No phone number required. Start sending requests now.

Crypto Only

Top up with USDT or USDC. Add $20 to $500. Get bonus credit. Just crypto.

Zero Restrictions

Our model answers without refusals. Perfect for NSFW chatbot scenarios. Unfiltered content generation. Reliable text output.

What Developers Ask About Uncensored APIs

Our API accepts lawful adult content without arbitrary refusals. It serves a single uncensored model via the standard OpenAI-compatible interface. You get streaming, JSON mode, and function calling. Context supports 100,000 tokens, with a 16,000 token output limit. There are no embeddings or image generation capabilities. Pricing is $0.15 per million input tokens and $0.50 per million output tokens. Top-ups require crypto, starting at $20.

Common Pitfalls in the Uncensored AI Niche

Most users confuse government censorship with corporate content moderation. Our uncensored LLM removes corporate guardrails, not legal limits like minor sexual content. Avoid assuming unlimited generation; we cap outputs at 16,000 tokens per request. Many expect image or embedding capabilities, but we serve text-only chat-completions. Our API is strictly pay-as-you-go via crypto, with no monthly subscriptions or hidden fees.

Who Should Use Our API and Who Shouldn't

Use this API for high-volume NSFW roleplay and unrestricted content generation. It serves developers needing a single, uncensored model without corporate guardrails or complex routing. It is not for teams requiring image, audio, or embedding capabilities. Do not use it if you need a specific vendor’s proprietary model or require formal SLA guarantees. Our uncensored LLM handles diverse topics efficiently, but it lacks fine-tuning and multi-modal features. Developers seeking a straightforward, pay-as-you-go solution for text-heavy applications will find it ideal.

Migrate Your OpenAI Code in Three Steps

Switch to our uncensored LLM by updating your base URL to HTTPS://api.sanscensure.com/v1 and setting the model ID to "uncensored". First, change the base_url in your OpenAI SDK configuration. Second, ensure your API key is active. Third, test a request to /v1/chat/completions. This single model replaces complex routing, eliminating corporate restrictions while maintaining standard compatibility for your existing NSFW chatbot scripts.

Calculate Your Costs: Real Token Examples

Costs depend strictly on token volume. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. A 10k input and 2k output exchange costs $0.0016. Errors incur zero charges. Streaming via SSE reports usage in the final chunk. Crypto top-ups apply bonuses. Prepaid credit never expires. Track usage via the dashboard to avoid surprises.

Common questions

What is the sans censure API?

It is a hosted chat-completions API serving one uncensored large language model. You get text in, text out via an OpenAI-compatible interface without corporate guardrails.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Is this API free?

No, but you get a free trial. Usage costs $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals do not consume your prepaid credit.

What payment methods do you accept?

We accept crypto only: USDT (TRC20) or USDC (Base). Top-ups range from $20 to $500, with bonus credits starting at $50.

How many tokens can the model handle?

The context window supports 100,000 tokens for prompt and completion combined. You can request up to 16,000 output tokens per request, or 2,048 if you omit the max_tokens parameter.

Is the model uncensored?

Yes, the model answers without refusals for lawful adult, fictional, or controversial topics. The only hard limit is that sexual content involving minors is always refused.

Access in two steps

Register, retrieve your key, update the endpoint URL. That is the entire configuration.

Start now View documentation