Developer-First API
Uncensored AI API for Developers
Integrate a true uncensored LLM into your stack with a standard OpenAI-compatible endpoint. No infrastructure, no guardrails, just raw text generation.
- OpenAI protocol compatible
- $0.15 per 1M input tokens
- 100k token context window
Try it in one request
curl https://api.unfilteredaimodels.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.unfilteredaimodels.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.unfilteredaimodels.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);The Uncensored API Standard
Most API providers offer a wrapper around proprietary models with built-in refusal layers. We offer a direct path to an uncensored large language model via the standard OpenAI protocol. This means you get the convenience of a hosted service with the freedom of an unfiltered model. You do not need to manage GPUs, handle scaling, or deal with complex infrastructure. Simply point your existing client to our base URL and start generating text. The model is tuned to answer without content refusals for lawful adult use, making it ideal for developers who need raw output.
One Model, Zero Compromises
We do not route between vendors or offer a marketplace of models. We run a single open-weight model on our own GPU servers, tuned specifically for unrestricted behavior. This focus ensures consistency and performance. You get a 100,000 token context window for both prompt and completion. This allows for long-context tasks without losing coherence. Unlike aggregation platforms, we do not hide behind multiple model choices. You get one powerful, abliterated llm that does exactly what you ask.
Built for Developers
Our API is designed for engineers who value simplicity. We support streaming via Server-Sent Events (SSE) and tool/function calling, matching the behavior of the official OpenAI SDK. You can use any OpenAI-compatible client by simply changing the base URL and API key. We do not offer embeddings, image generation, or audio processing. If you need those, look elsewhere. For text generation, we provide a high-performance endpoint that handles up to 300 requests per minute. Your prompts are not used for training, ensuring your data remains private.
Who This Is Not For
This API is not for users who need a general-purpose assistant with corporate safety filters. It is not for teams requiring SLA guarantees, SOC2 certifications, or on-prem deployment. We do not offer model routing, fine-tuning, or multimodal capabilities like image or video generation. If you need a specific vendor's model like GPT or Claude, this is not the right choice. We are an independent service providing one uncensored model. We also block sexual content involving minors, so if you need absolute zero restrictions on that specific category, this may not fit your needs.
Questions and answers
Is this API compatible with the official OpenAI SDK?
Yes. Our endpoint follows the OpenAI chat completions protocol. You can use the official OpenAI SDK for Python, Node.js, or any other language by simply setting the base URL to https://api.unfilteredaimodels.com/v1 and providing your API key.
What is the context window size?
The model supports a 100,000 token context window for both input and output. This allows you to process long documents or maintain extensive conversation histories without truncation.
Do you offer embeddings or image generation?
No. We focus exclusively on text generation via the chat completions endpoint. We do not offer embeddings, image, audio, or video generation. If you need multimodal capabilities, you will need to use a different provider for those specific tasks.
How does pricing work?
We use a pay-as-you-go prepaid credit model. There are no monthly fees or subscriptions. Credits never expire. You can top up starting at $20 by crypto (USDT on TRC20, USDC on Base). You get a +5% bonus for $50 top-ups, +10% for $100 top-ups, and +15% for $200 or more.
Is my data used for training?
No. We do not use your prompts to train our model. Your data remains private. You only need an email and password to sign up, and we do not require a phone number or credit card for the trial period.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Guides
Practical articles on setup, pricing and integration.
Unfiltered AI Models for Ollama vs a Hosted APIWeigh unfiltered AI models for Ollama against a hosted endpoint: hardware, speed, privacy, cost math, and how to switch your tools between the two…
Unfiltered LLM API: Call It in Five MinutesUse a hosted unfiltered LLM API with any OpenAI SDK: get a key, set the base URL, send a first request, stream tokens, and check your balance.…
OpenAI-Style API with cURL and a Bearer TokenCall an OpenAI-compatible chat API with cURL and a bearer token: list models, send a chat request, stream, use JSON mode and tools, read headers,…
Unfiltered AI Model: Myths vs FactsIs the unfiltered AI model right for you? We debunk myths about censorship, context windows, and API compatibility for uncensored LLMs used in…