Drop-in Uncensored API
The Uncensored LLM Proxy API
Swap your base URL and API key to access a high-performance, uncensored LLM proxy with exact OpenAI compatibility. No complex routing, no vendor lock-in, just text generation.
- One uncensored model, no routing
- Exact OpenAI SDK compatibility
- Prepaid credit, no subscriptions
Try it in one request
curl https://api.llmproxyapi.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.llmproxyapi.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.llmproxyapi.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);What you get
Uncensored Inference
The model answers without content refusals for lawful adult use, making it ideal for creative writing, roleplay, and security research where standard models might hold back.
Zero Code Changes
Use the official OpenAI SDKs by simply changing the base_url and API key. Your existing code works immediately with our endpoint.
Large Context Window
Process up to 100,000 tokens per request. Handle long documents, codebases, or extended conversations without complex chunking strategies.
Simple Prepaid Pricing
Pay only for what you use with no monthly fees. Credits never expire, and you can top up by crypto (USDT on TRC20, USDC on Base) starting at $20.
Streaming & Tools
Supports streaming responses via SSE and tool/function calling for building agentic workflows or real-time chat interfaces.
Transparent Limits
300 requests per minute per key with an 8 MB request body limit. One key per account, revocable and regenerable anytime.
How it works
Create Account
Sign up with an email and password to receive your API key immediately, no card required for the trial.
Configure SDK
Update your client's base_url to https://api.llmproxyapi.com/v1 and set your new API key.
Send Requests
Make POST requests to /v1/chat/completions using the standard OpenAI payload structure.
What people build with it
Creative Writing & Roleplay
Generate stories, scripts, or character dialogues without the model refusing to explore mature or unconventional themes. Ideal for immersive narrative experiences.
Security Research
Test LLMs for jailbreaks or prompt injection vulnerabilities by using a model that doesn't apply standard safety filters. Analyze raw model behavior.
Content Generation Pipelines
Feed large documents into the API for summarization or extraction. The 100k context window handles extensive inputs without needing complex preprocessing.
Agentic Workflows
Integrate tool calling into your automation scripts. The API supports function definitions, allowing agents to interact with external systems effectively.
Why an Uncensored LLM Proxy?
Standard LLM providers often apply safety filters that block lawful adult content, niche topics, or specific reasoning patterns. Our uncensored LLM API serves a single open-weight model tuned to answer without these refusals. This is not about removing all quality; it is about removing arbitrary gates. You get consistent, direct inference for creative and research use cases where standard models might refuse to generate valid text.
The model is NOT GPT, Claude, Gemini, Grok, or DeepSeek. It is an independent model run on our own GPU servers. We focus on text generation only, ensuring high performance for the tasks that matter most to developers who need raw output.
Drop-in OpenAI Compatibility
Our API is designed to be a drop-in replacement for OpenAI. You can use the official OpenAI SDKs for Python, Node.js, and other languages without rewriting your logic. The endpoint structure mirrors OpenAI's chat-completions API, supporting streaming via Server-Sent Events (SSE) and tool/function calling.
To integrate, you only need to change two variables: the base_url to https://api.llmproxyapi.com/v1 and your API key. Everything else remains the same. This simplicity reduces integration time from hours to minutes, allowing you to test uncensored inference in your existing pipelines immediately.
Performance & Context Window
We provide a 100,000-token context window for both prompt and completion. This allows you to process large codebases, long documents, or extended conversation histories in a single request. For most use cases, this reduces the need for complex chunking strategies and preserves context coherence.
Our infrastructure is optimized for speed. You can send up to 300 requests per minute with an 8 MB request body limit. This capacity is sufficient for most production applications, from chat interfaces to batch processing jobs. If you need higher throughput or multi-model routing, this proxy is not the right fit; we offer a single, focused model.
Simple Prepaid Pricing
Our pricing is transparent and straightforward. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly subscriptions, no hidden fees, and no enterprise bloat. You preload credit, and it never expires. You can top up starting at $20 by crypto (USDT on TRC20, USDC on Base).
We also offer bonus credits: +5% on deposits of $50 or more, +10% on deposits of $100 or more, and +15% on deposits of $200 or more. New accounts receive a $0.50 trial credit valid for 7 days, no card required. This allows you to test the model's quality and performance before committing funds. Claim this credit with one click on your API key page.
Questions and answers
Is this API exactly like OpenAI?
Yes, it follows the OpenAI chat-completions schema. You can use the official OpenAI SDKs by changing the base URL and API key. However, the underlying model is not GPT-4 or GPT-3.5; it is an independent uncensored model with its own capabilities and limitations.
What content is blocked?
The model is uncensored for lawful adult content, but we enforce a hard limit: sexual content involving minors is always blocked. This is the only strict content filter applied. All other topics, including controversial or mature themes, are generally allowed.
Can I use this for embeddings or image generation?
No. Our API only supports text generation via chat-completions. We do not offer embeddings, image, audio, or video generation. If you need those capabilities, you will need a different service or to call multiple APIs.
How does the prepaid credit work?
You pay in advance. Credits are deducted as you use the API. Unused credits do not expire. You can top up your balance at any time, and we offer bonuses for larger deposits. There are no monthly fees or subscriptions.
Do you use my prompts for training?
No. Your prompts and completions are not used to train our model. We value privacy for developers who send sensitive data or proprietary content through the API. Your account requires only an email and password.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
LangChain with Local LLM or a Hosted Endpoint
The Claude API Proxy: A Production Checklist