Uncensored LLM Inference
Uncensored Inference API for Developers
A drop-in OpenAI-compatible inference API serving a single uncensored open-weight model. Change your base_url and key, keep the code.
- One uncensored model
- No monthly fees
- Credits never expire
Try it in one request
curl https://api.llminferenceapi.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.llminferenceapi.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.llminferenceapi.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
Drop-in Compatibility
Works with official OpenAI SDKs and any compatible client. Just update your base_url to https://api.llminferenceapi.com/v1 and swap your API key.
Uncensored Output
The model answers without content refusals for lawful adult, fictional, or controversial topics. Only sexual content involving minors is blocked.
Direct GPU Hosting
We run the model on our own servers, not as a reseller. No vendor routing, no hidden layers, just direct inference.
Transparent Pricing
Pay only for what you use. Input tokens are $0.15/1M, output tokens are $0.50/1M. No subscriptions or expiration dates on credits.
Streaming & Tools
Supports server-sent events (SSE) for streaming responses and standard tool/function calling endpoints.
Privacy First
Prompts are not used for training your model. Account creation requires only an email and password.
How it works
Create Account
Sign up with an email and password to get your API key instantly.
Add Credit
Top up by crypto (USDT on TRC20, USDC on Base) to start using the service.
Start Inference
Point your existing client code to our base_url and send requests.
What people build with it
Creative Writing
Generate stories and scripts without unwanted moralizing or content filters restricting your narrative choices. Perfect for adult fiction or edgy humor.
Data Extraction
Parse large documents using the 100k context window to extract structured data from long texts without losing context.
Research & Analysis
Get unfiltered answers to controversial or niche topics without the model refusing to engage due to standard safety guidelines.
Chat Applications
Build chat interfaces that feel natural and responsive, supporting streaming responses for a better user experience.
Drop-in OpenAI Compatibility
Stop rewriting your integration code for every new model. Our API implements the standard /v1/chat/completions endpoint, meaning you can switch to our uncensored model by simply changing the base_url and api_key in your existing OpenAI SDK clients. We support streaming via Server-Sent Events (SSE) and function calling, so your existing logic for handling tool outputs or real-time text generation works out of the box.
This is not a multi-model gateway or a complex proxy that adds latency. It is a direct connection to our GPU servers running a single, optimized open-weight model. You get the performance of a dedicated endpoint with the familiarity of the OpenAI format.
Uncensored & Unfiltered
Our model is tuned to answer without content refusals for lawful adult use, fictional narratives, security research, or controversial topics. While most standard models will politely decline to discuss sensitive subjects or generate mature content, our model will provide a direct answer.
There is one hard limit that always applies: requests containing sexual content involving minors are blocked. Everything else is fair game. This makes it ideal for applications where you want full creative control over the output without the model acting as a gatekeeper for your users' legitimate requests.
Transparent Pay-As-You-Go Pricing
We do not lock you into monthly subscriptions or tiered plans. You pay exactly for the tokens you consume. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. When you add funds, those credits never expire, so you can top up when it makes sense for your budget.
We offer bonuses for larger deposits: +5% from $50, +10% from $100, +15% from $200. New accounts start with $0.50 in trial credit valid for 7 days, requiring no credit card. This structure ensures you only spend what you use, with no hidden fees for streaming or tool usage. Claim this credit with one click on your API key page.
Who This Is NOT For
If you need image generation, audio processing, or embeddings, this API is not for you. We serve text only. If you require model routing across multiple vendors (like GPT-4, Claude, and Llama in one call), we do not offer that. We focus on delivering the best possible experience for one specific uncensored model. If you need strict SLA guarantees, SOC2 certifications, or HIPAA compliance out of the box, you should look at enterprise-grade providers. We are a straightforward, developer-first inference endpoint.
Questions and answers
Is this an OpenAI proxy?
No. We are not reselling OpenAI's models. We host our own open-weight model on our own GPU servers. It is OpenAI-compatible in format, meaning it accepts the same JSON structures and SDK commands, but the underlying model is ours.
What is the context window size?
Our model supports a 100,000 token context window, counting both the prompt and the completion. This allows for processing large documents or maintaining long conversation histories.
Do my prompts get used for training?
No. We do not use your prompt data to train our model. Your data remains private to your inference requests.
How do I get started?
Sign up with an email and password on the Get API Key page. You will receive an API key immediately. You can start using the free $0.50 trial credit without adding a credit card. Claim this credit with one click on your API key page.
What happens if I hit the rate limit?
We allow 300 requests per minute per API key. If you exceed this, you will receive a 429 error. You can regenerate your API key at any time to reset the counter if needed.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Get API keyGuides
Practical articles on setup, pricing and integration.
LLM API Cost per Month: Four Realistic ScenariosLLM API cost per month for a hobby bot, a Discord server, an app with 1,000 users and a batch job, priced at $0.15 and $0.50 per 1M tokens with…
Cheapest LLM Inference API: How to Judge Real CostHow to find the cheapest LLM inference API for your workload: input vs output tokens, context, top-ups and failures, with exact worked costs at…
LLM Inference Framework Comparison vs Hosted APIAn llm inference framework comparison of vLLM, llama.cpp, Ollama, TensorRT-LLM and a hosted API, with the trade-offs and when each one is the…
LLM Inference API: Streaming, Tools and JSON ModeSet up an LLM inference API with an OpenAI-compatible endpoint: working Python, Node and curl code for chat, streaming, tool calling, JSON mode…
What Is LLM Inference? Tokens, Latency and CostWhat is LLM inference? A plain explanation of prefill, decoding, tokens, the KV cache, latency and cost, with worked per-request price examples…
Troubleshooting Common AI Chat API MistakesFix context limits, streaming errors, and token counting in your uncensored LLM API integration. Optimize your pay as you go setup today.