Private LLM API

The Private Uncensored LLM API for Developers

A single, uncensored model on dedicated infrastructure. No content filters, no training data scraping, and no monthly subscriptions.

Get API key Read the docs

OpenAI compatible endpoints
Pay-as-you-go pricing
No training on prompts

per 1M input tokens: $0.25
Output tokens / 1M: $1.00
token context: 64,000
trial credit: $0.50
requests per minute: 300

Try it in one request

https://api.anonymousllmapi.com/v1uncensored

curl https://api.anonymousllmapi.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.anonymousllmapi.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.anonymousllmapi.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

Use the official OpenAI SDKs by simply pointing to our base URL. Supports streaming via SSE and tool/function calling for complex workflows.

Dedicated Infrastructure

We run our own uncensored model on private GPU servers, avoiding the rate limits and filtering of third-party aggregators.

True Privacy

Your prompts are not used for training. We collect only an email and password to create your account and issue your key.

No Subscription Friction

Prepaid credit never expires. Top up from $10 via card or crypto, or start with a free trial requiring no payment method.

Large Context Window

Supports 64,000 tokens for both prompt and completion, allowing for extensive conversations and long document processing.

Simple Key Management

One API key per account. Regenerate it anytime to instantly revoke access without losing your prepaid credit balance.

How it works

Get Your Key
Sign up with an email and password to receive your API key instantly.
Add Credits
Purchase prepaid credit via card or crypto, or start with the $0.50 free trial.
Make Requests
Point your OpenAI-compatible client to our base URL and send text to the uncensored model.

What people build with it

NSFW Content Generation

Generate unrestricted adult fiction or roleplay without hitting artificial content filters or refusal walls common in standard models.

Unfiltered Chatbots

Build chatbot interfaces that allow users to discuss controversial, political, or explicit topics without the bot getting 'stuck' in safety mode.

Privacy-Sensitive Analysis

Process sensitive data where you need to ensure the provider isn't training on your input to improve their public models.

Research & Exploration

Use the model for security research or creative writing where standard corporate guidelines would block specific outputs.

Why Go Uncensored?

Standard LLMs are optimized for broad corporate appeal, which means they often refuse lawful adult content, creative interpretations, or nuanced opinions. Our API serves a dedicated open-weight model tuned to answer without these artificial constraints. This is not about removing all intelligence; it is about removing the filter that blocks specific types of output.

Unlike local runners, you don't need to manage hardware or handle version upgrades. Unlike aggregators, we don't route your request through a chain of vendors that might add their own filters or latency. We provide a direct path from your code to an uncensored inference engine.

OpenAI Compatible, Drop-in Replacement

Our API follows the OpenAI chat-completions standard. You can use the official OpenAI SDKs for Python, Node.js, and other languages by simply changing the base URL to https://api.anonymousllmapi.com/v1 and updating your API key. The model identifier is uncensored.

Supports streaming responses via Server-Sent Events (SSE) and structured tool/function calling. If you are building an application that currently uses OpenAI, you can switch to us with minimal code changes.

Privacy First: No Training, No Tracking

When you use a free or shared API, your data often becomes part of the training set. We operate on a private infrastructure model where your prompts are not used for training. We require only an email and password to create your account. No phone number, no address, no payment method for the trial.

Your API key is the only identifier. You can regenerate it at any time, instantly revoking the old key. This ensures that even if a key is compromised, your history remains secure under the new key.

Simple Pay-As-You-Go Pricing

We do not charge monthly fees. You buy credits and spend them as needed. Credits never expire. If you top up $50, you get a 5% bonus. Top up $100, and you get 10% bonus. This model favors heavy users who want predictable costs without committing to a subscription.

New accounts get $0.50 in trial credit valid for 7 days. No card required. This allows you to test the model's behavior and performance before spending real money. The model charges $0.25 per 1M input tokens and $1.00 per 1M output tokens.

Questions and answers

Is this the OpenAI API?

No. We are an independent service running our own uncensored model. We are compatible with the OpenAI API format, but we do not serve GPT-4, GPT-3.5, or any other OpenAI model. We host our own open-weight model on our own servers.

Do you use my prompts for training?

No. Our privacy-first approach means your prompts are not used to train our model. We only collect the email and password necessary to manage your account and API key.

What happens if I run out of credits?

Your API key remains active, but you will receive a 402 Payment Required error when you try to make requests. You can top up your account at any time to resume service. Credits never expire.

Can I use this for commercial projects?

Yes. Once you have purchased credits, you can use the API for any lawful purpose, including commercial applications. There are no restrictions on how you use the output, provided the input does not violate our single hard limit.

What is the content limit?

The model is uncensored for most adult and controversial topics. However, we do block sexual content involving minors. This is a hard limit that always applies.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.