Native compatibility, extreme stability
Unfiltered LLM API Gateway
A single-model API gateway built for developers, providing uncensored LLM services. Based on self-built GPU servers, ensuring low latency and high availability, making integration easier.
- OpenAI-compatible interface
- 100k context window
- Pay as you go, no monthly fee
Try it in one click
curl https://api.llmzhongzhuan.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.llmzhongzhuan.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.llmzhongzhuan.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);- Input token price per 1M
- $0.25
- Output token / 1M
- $1.00
- Token context
- 100,000
- Free trial credit
- $0.50
- Requests per minute
- 300
Features
Single model, no aggregation latency
We do not aggregate multiple models; we focus on a single high-performance uncensored model. This eliminates routing unpredictability and ensures consistent, low-latency responses for every request.
Native OpenAI compatibility
Fully compatible with the /v1/chat/completions interface, supporting streaming and tool calling. No code changes needed; just replace the base_url to connect to existing OpenAI SDKs.
Transparent pay as you go
Input $0.25/1M tokens, output $1.00/1M tokens. No subscription fees, no hidden costs. Prepaid credit never expires and is used up as consumed.
100k long context support
Supports a 100,000 token context window (including prompt and completion), meeting the needs of long document processing and complex logical reasoning.
Clear privacy and limits
Prompts are not used for training. The only hard limit is child sexual abuse material. All other legal adult, fictional, or controversial topics are uncensored.
Minimalist developer experience
Register with just an email, no card required. Get $0.50 free trial credit upon registration, valid for 7 days. API key is generated instantly and can be reset at any time.
Usage process
Register account
Register on the "Get API Key" page using your email and password. No credit card binding required.
Get Key
Immediately receive your API key after successful registration, ready for code configuration or third-party tools.
Make a request
Point the base_url to https://api.llmzhongzhuan.com/v1，使用 model id "uncensored" to send a request.
Application scenarios
LLM application integration
Developers can seamlessly integrate this API into existing LLM applications, leveraging its uncensored nature for more free-form answers. Compatible with standard OpenAI protocols, with very low switching costs.
Content generation and creation
Suitable for scenarios requiring adult content, controversial topics, or breaking common AI hallucinations. A single model ensures consistent output style, ideal for batch content generation tasks.
Long text context processing
Use the 100k context window to process long documents, codebases, or complex conversation histories. Ideal for RAG or summarization tasks requiring full context understanding.
Development and testing environments
New users get $0.50 free trial credit, perfect for quickly verifying API integration logic. Test streaming and tool calling without any upfront payment.
Why choose our API gateway service
Many API aggregation services offer diversity by routing multiple models, but this often leads to latency fluctuations and unpredictable output quality. Our API gateway takes the opposite approach: focusing on a single, fine-tuned uncensored LLM. This means you don't need to switch between models; instead, you get consistent, low-latency responses. For developers needing stability, this single-model architecture eliminates the complexity of an aggregation layer.
We self-host the model on our own GPU servers, ensuring efficient data transmission. Whether generating creative content or performing logical reasoning, you get the raw, unfiltered model output. This transparency lets you know exactly what you are calling, rather than relying on black-box routing.
Native OpenAI-compatible interface
Our API fully follows the OpenAI /v1/chat/completions standard. This means you can use any OpenAI-compatible SDK (such as Python, Node.js, or curl) to connect directly. Just point the base_url to https://api.llmzhongzhuan.com/v1 and set the model ID to uncensored.
Supports streaming (SSE) and function calling to meet the needs of modern AI applications. Note that we provide text generation only; we do not support images, audio, video, or embedding vectors. This is a pure, efficient text API proxy.
Flexible pay as you go model
We ditched expensive monthly subscriptions for a transparent pay as you go model. Input tokens are $0.25/1M, output tokens are $1.00/1M. Prepaid credit never expires. The top up threshold is low, starting at $10 with cryptocurrency (USDT, USDC) payments; top up $50 for a 5% bonus, $100 for a 10% bonus.
New users get $0.50 free trial credit upon registration, no card required, valid for 7 days. This allows you to test API stability and response time at zero cost. All credit is used to offset token consumption with no hidden fees.
Who it is for, who it is not for
Our uncensored AI API is for developers who need free output, do not mind a single model, and value latency stability. If you need multi-model routing, image generation, or embedding vectors, this is not for you. We are also not for scenarios requiring enterprise-grade SLA guarantees (such as a 99.99% availability commitment) or specific industry compliance certifications (such as HIPAA). We are an independent service, not affiliated with any major tech company.
Additionally, we support text generation only; we do not support OCR, search, or fine-tuning. If your application relies on these features, evaluate whether you need to combine them with other specialized APIs. We focus on providing pure, unrestricted text generation capabilities.
Frequently asked questions
Is this API a proxy for GPT or Claude?
No. We run a self-hosted open-weight model, fine-tuned to be uncensored. It is not a GPT, Claude, Gemini, or any third-party vendor model. We provide an independent API proxy service that does not rely on any external vendor model instances.
What are the API rate limits?
Each API key is limited to 300 requests per minute, with a request body size of no more than 8 MB. Each account can have only one key, but it can be reset at any time, and the old key will become invalid immediately. This is sufficient for most developers and small to medium-sized applications.
How do I top up after the free trial credit is used up?
You can top up starting from $10 via cryptocurrency (USDT, USDC). The top-up amount is credited to your account and never expires. Top up $50 to get a 5% bonus, top up $100 to get a 10% bonus. No monthly subscription fees.
Will my conversation data be used for training?
No. We only collect necessary account information (email and password) to manage your account. Your prompts and responses are not used to train the model. We respect user privacy and do not use data for other purposes.
What does 'uncensored' mean? What are the exceptions?
'Uncensored' means the model will not reject legal adult content, fictional stories, controversial topics, or safety research. The only hard limit is child sexual abuse material, which will be blocked. We encourage legal use but do not restrict other adult content.
Just fill out the form to get your key
Create an account, copy the key, and modify the Base URL. Configuration is that simple.
