OpenAI Compatible
Use existing SDKs with our base URL and API key.
Uncensored LLM API
Unfilter gpt API: Uncensored & OpenAI Compatible
Get an open-weight uncensored GPT model with a 100,000 token context window via a drop-in OpenAI compatible API.
- 100k context window
- No data training
- Crypto top-up
Test with one request
curl https://api.unfiltergpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "What is the current weather in Seattle"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.unfiltergpt.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.unfiltergpt.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
Features
Streaming Support
Receive real-time token updates via Server-Sent Events.
Function Calling
Execute tools with structured JSON response formats.
Transparent Pricing
Pay only for input and output tokens used.
Privacy First
Prompts are never used to train the model.
Simple Limits
300 requests per minute per API key.
Getting started
Create Account
Sign up with Google or email to get your key.
Add Credit
Top up via crypto to start using the API.
Make Request
Send POST requests to the chat completions endpoint.
Use cases
Content Creation
Generate uncensored stories without standard content filters.
Research Analysis
Analyze large documents with a 100k token window.
Dev Tools
Integrate AI into applications using standard OpenAI code.
Data Processing
Extract structured JSON from unstructured text inputs.
Cost Examples: 100k Context Window Arithmetic
Predictable billing relies on exact token counts. A 100k context window uses 100,000 input tokens and up to 16,000 output tokens. Input costs $15. Output costs $8. Total is $23 per request. Errors are free. Streaming returns usage in the final chunk. Check the usage field for precise accounting. No hidden fees apply.
How This Uncensored Model Differs from Standard LLMs
How This Uncensored Model Differs from Standard LLMs
Our API delivers uncensored responses by removing restrictive safety filters, allowing direct access to raw model outputs without refusal logic.
| Feature | Standard LLMs | Our API |
|---|---|---|
| Content Filtering | Strict refusal on adult topics | None for lawful use |
| Training Data | Prompts often used for training | Prompts never used |
| Infrastructure | Aggregated or vendor-locked | Own servers, no lock-in |
Why Developers Choose unfilter GPT for NSFW and Creative Work
Developers choose unfilter GPT because the model answers without refusals for lawful adult, fictional, or controversial topics, ensuring your prompts drive the output.
Uncensored Creative Writing
Generate mature themes without artificial softening. The model preserves nuance in tone and context.
NSFW Roleplay Systems
Run adult chatbots without sudden content blocks. Context window retains character details accurately.
Security Research
Probe model behavior without guardrails. Get raw, unfiltered responses for analysis.
Real Questions: Is It Safe and How Does It Handle Context?
Is it safe without safeguards?
The model answers without content refusals, so you must handle downstream filtering for your specific use case. A hard limit always applies: sexual content involving minors is refused.
How does it handle long contexts?
We support a 100,000-token context window. You can generate up to 16,000 tokens per request, ensuring your entire prompt and response fit within our limits.
Provider Selection Checklist for Uncensored LLMs
Verify infrastructure ownership and data isolation before integrating.
- Confirm you use a dedicated provider, not a proxy aggregating multiple vendors.
- Check that prompts are not used for model training.
- Ensure transparent token pricing with no hidden subscription fees.
- Validate OpenAI compatibility for drop-in SDK replacement.
- Review strict content limits and request rate caps.
- Confirm crypto-only top-up flexibility without card requirements.
Setup Guide: From Signup to First API Call
Get Your Key
Click "Get API key" and sign in with Google or email. Your key appears instantly. No phone number is required.
- Top up: Add crypto like USDT (TRC20) or USDC (Base). Start with $20 to receive a 5% bonus.
- Configure: Set your base URL to
https://api.unfiltergpt.com/v1in your OpenAI SDK. - Call: Send a POST request to
/v1/chat/completionsusing the model ID "uncensored".
You now have an uncensored LLM ready for your prompts.
Frequently asked questions
What is unfilter GPT and how does it work?
It is a hosted API serving one uncensored model. You send text, you get text back. Use the standard OpenAI SDK by changing the base URL to our endpoint and providing your unique API key for direct access.
Does this API refuse adult content?
No. It answers without content refusals for lawful adult use. It allows controversial topics but always blocks sexual content involving minors. You get direct, unfiltered responses for creative and adult applications without standard guardrails interfering.
How much does it cost per token?
Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. Errors and refusals are free. You pay only for real usage with prepaid credit that never expires, ensuring transparent pricing without hidden fees.
Can I use my existing OpenAI code?
Yes. It is an openai compatible API that works with standard clients. Just update your base URL to api.unfiltergpt.com/v1 and swap your key. Your existing Python or Node.js SDK integrations will work immediately with minimal changes.
What is the maximum context window size?
The context window supports 100,000 tokens for prompt and completion together. You can generate up to 16,000 tokens per request. This allows processing large documents while maintaining coherence across long conversations and complex data structures effectively.
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.
Get your API key instantly
Sign up, copy the key, update your base URL. Setup takes seconds.
