Zero Config
Swap base_url and key to use existing OpenAI clients without code changes.
Uncensored API
Not filter API: Uncensored LLM Integration
Integrate our uncensored LLM via one base_url change and start generating text with a 100,000 token context window immediately.
- No subscription required
- OpenAI SDK compatible
- Crypto top-ups only
Test with one calluncensored
curl https://api.notfilter.cc/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "what is the capital of france"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.notfilter.cc/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.notfilter.cc/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
Core capabilities
No Refusals
The uncensored model answers adult and controversial topics without standard content filters.
Streaming Data
Get real-time token usage details in the final SSE chunk for accurate billing.
JSON Mode
Enforce strict object responses with response_format json_object for reliable parsing.
Tool Support
Call functions dynamically using standard tool_choice and tools parameters.
No Expiry
Your prepaid credit never expires so you pay only for what you use.
Setup process
1/3
Get Key
Sign up with Google or email and receive your API key instantly.
2/3
Add Funds
Top up with USDT or USDC to start sending requests immediately.
3/3
Send Request
Point your SDK to the new base_url and model id uncensored.
Moving from another OpenAI-compatible provider in three steps
Switch your LLM provider in three steps. First, replace your base URL with https://api.notfilter.cc/v1. Second, update your API key in the environment variables. Third, send requests to the same /v1/chat/completions endpoint. This uncensored LLM works with existing OpenAI SDKs without code changes. You get transparent per-token pricing and no subscription baggage. Integrate unrestricted AI capabilities instantly.
Why developers choose not filter for NSFW generation
Developers choose not filter for NSFW generation because it offers a straightforward, uncensored LLM API with transparent pricing and zero configuration overhead.
Zero Configuration
Drop in your existing OpenAI SDK client and swap the base URL. The API responds instantly without complex setup steps.
Transparent Pricing
Pay strictly per token with no hidden subscription fees. Errors and refusals cost nothing, so you only pay for real output.
Uncensored Model
The model answers without filtering lawful adult content. It handles controversial topics smoothly while maintaining strict safety for minors.
What developers actually ask about this topic
Does the API refuse NSFW content?
No. The uncensored model answers without refusals for lawful adult topics. Only one hard limit applies: sexual content involving minors is always refused.
- No subscription fees.
- Prepaid credit never expires.
- Errors are free.
Streaming via SSE works with standard OpenAI SDKs. Change the base URL to HTTPS://api.notfilter.cc/v1. Input costs $0.15 per 1M tokens. Output is $0.50 per 1M. Start with $0.50 trial credit. Use Google or email to sign up immediately. Get your key in seconds.
Common mistakes people make in this niche and how to avoid them
Developers often assume uncensored means unlimited context, but we cap completion at 16,000 tokens. Many also forget that streaming via SSE is required to access token usage data in the final chunk. You must set the base_url to api.notfilter.cc, not the default OpenAI endpoint. Another error is ignoring the 8 MB request body limit. Ensure your payload fits within these constraints to avoid silent failures.
How this differs from a typical alternative on 4-6 concrete signs
Our API skips subscription baggage, charging strictly per token usage with prepaid crypto credit that never expires. Unlike services using third-party models, we run one uncensored open-weight model that answers without refusals. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. This transparent, code-first approach ensures you only pay for actual generation.
A checklist for choosing a provider in this niche
Verify the base URL matches standard OpenAI compatibility. Check that pricing uses per-token rates, not subscriptions. Confirm crypto-only top-ups match your workflow. Test that streaming via SSE works reliably. Validate that the uncensored model allows adult content without arbitrary refusals. Confirm context windows support your data size. Ensure API keys are generated instantly.
Common use cases
NSFW Chatbot
Build unrestricted conversational agents that handle adult themes without blocking.
Content Generation
Create fictional stories or articles without encountering standard safety refusals.
Roleplay Apps
Develop immersive character bots that maintain context over long conversations.
Data Extraction
Parse complex text into JSON objects with high precision and reliability.
Frequently asked questions
What is not filter and how does it differ from standard models?
It is an uncensored LLM API serving one open-weight model. It removes refusals for lawful adult topics. Standard models often block these. Our API allows direct content generation without extra configuration steps or complex parameter tuning.
Does the API support streaming responses for real-time chatbots?
Yes. It supports streaming via Server-Sent Events. Token usage details appear in the final chunk. This enables low-latency interfaces. You can integrate this easily using standard SDKs without managing connection state manually.
How much does the uncensored API cost per million tokens?
Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors are free. This transparent pricing eliminates hidden fees. You only pay for actual usage without monthly subscription baggage or surprise overages.
Can I use standard OpenAI SDKs with this uncensored AI endpoint?
Yes. It follows the OpenAI compatible standard. You just change the base URL. The official SDKs work directly. This simplifies integration significantly. You avoid writing custom HTTP clients for basic chat completions.
What is the maximum context window for a single request?
The window is 100,000 tokens. This includes both prompt and completion. You can set max_tokens up to 16,000. This allows long conversations. Shorter defaults apply if you omit the parameter explicitly.
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.
Obtain your key now
Register, copy the key, and update the endpoint. That is all.
