Direct LLM API
Uncensored AI API: Direct Responses Without Filters
An OpenAI-compatible chat API powered by an open-weight model tuned for direct responses, without systematic refusal of adult or creative content.
Try in a single request
curl https://api.apiiasanscensure.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.apiiasanscensure.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.apiiasanscensure.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);https://api.apiiasanscensure.com/v1uncensored
- Tuned open-weight model
- Compatible with native OpenAI SDK
- No card trial credit
- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
What you get
Native compatibility
Integrate our API by simply changing the base URL and API key. Your existing OpenAI clients work immediately without additional middleware.
Unfiltered responses
The model directly answers questions on adult, controversial, or creative topics without the generic refusals of commercial large models.
Streaming and Tools
Enjoy streaming via SSE and function calling for responsive and modular integrations in your applications.
Extended context window
A 100,000 token capacity allows processing long conversation contexts or documents without rapid information loss.
Pay as you go pricing
Pay proportionally to your actual consumption. No mandatory monthly subscription; paid credits never expire.
Preserved privacy
Create an account with email and password. Your prompts are not used for third-party model training.
How it works
Create your account
Sign up with an email and password to get your API key instantly.
Configure your client
Point your OpenAI SDK to our base URL and use the "uncensored" model ID.
Send requests
Start generating text via the /v1/chat/completions endpoint with your API key.
What people build with
Creative content generation
Ideal for storytelling or roleplay applications where creativity should not be stifled by excessive politeness filters. Explore rawer or specific tones without risk of arbitrary blocking.
Security research
Allows analyzing model responses on sensitive or technical topics without the usual censorship of consumer platforms. Use AI for data analysis without semantic restrictions.
NSFW chatbots
Robust solution for adult chatbots requiring direct and unvarnished responses. Fast integration thanks to the standardized structure compatible with existing tools.
Rapid prototyping
Use the free trial credit to test performance and latency before investing in paid credits. Validate model suitability for your specific use case in minutes.
Why choose an uncensored API?
Commercial models often apply generic guardrails that block legitimate responses deemed "sensitive" by their criteria. Our uncensored AI API uses an open-weight model specifically tuned to respond directly. It does not systematically reject adult, controversial, or creative topics, offering superior response freedom for your applications.
Unlike solutions that add a complex external moderation layer, our model integrates this frank response capability natively. You benefit from higher text coherence for creative writing or sensitive data analysis.
Native OpenAI Compatibility
Our API follows the standard OpenAI protocol for chat endpoints. This means you do not need to learn a new request structure. You simply change the base_url to https://api.apiiasanscensure.com/v1 and provide your unique API key.
Streaming via Server-Sent Events (SSE) and function calling are fully supported. This compatibility makes integration into frameworks like LangChain or LlamaIndex immediate, with no middleware overhead.
Tuned Open-Weight Model
The model used is a large open-weight language model, hosted on our own GPU servers. It has been specifically fine-tuned to reduce content refusals while maintaining linguistic quality. It is not GPT, Claude or Gemini, but a distinct architecture optimized for response freedom.
It supports a context window of 100,000 tokens, allowing you to maintain long conversation memory or process large documents. A strict limit always applies: sexual content involving minors is blocked, regardless of context.
Transparent Pricing and Limits
Pricing is simple and predictable: $0.15 per million input tokens and $0.50 per million output tokens. You pay for what you consume with prepaid credits that never expire. A +5% bonus applies from $50, a +10% bonus from $100, and a +15% bonus from $200.
Each key is limited to 300 requests per minute. If this API does not suit your needs, it is because you are looking for image generation, embeddings, or a service with contractual SLA guarantees. We are an independent "pay as you go" service, ideal for developers and creators, but not for companies requiring dedicated infrastructure or specific regulatory compliance such as HIPAA.
Frequently Asked Questions
What is the difference between open-weight and open-source?
Open-source means the model code is public and modifiable. Open-weight means the model weights (the result of training) are available, but the original infrastructure or training code may remain private. Our model is open-weight, ensuring its availability for inference without necessarily opening all underlying source code.
Does the trial credit expire?
Yes, the $0.50 trial credit provided upon registration is valid for 7 days. However, credits you purchase via top-up (prepaid) never expire, regardless of the time between uses.
Can I use this API for NSFW content?
Yes, the model is designed not to refuse legal adult content. However, sexual content involving minors is strictly blocked by our base filter, regardless of the prompt sent. For other types of adult content, responses are direct and without arbitrary censorship.
How does API key reset work?
You can generate a new key at any time from your dashboard. As soon as the new key is created, the old one is immediately revoked and can no longer be used to make requests, ensuring your account security.
Are my data used for training?
No. Unlike certain free or mass-market offerings, we do not use your prompts to train our models. Your privacy is preserved, as only an email and a password are required to create your account, with no superfluous data collection.
Your key is one step away
Create an account, copy the key, change the base URL. That's it.
Guides
Practical articles on setup, pricing and integration.
SillyTavern API: connect an OpenAI-compatible modelSillyTavern API: connect an OpenAI-compatible endpoint, set context and response length, estimate cost per message, and fix errors.
Uncensored text AI: first API call and limitsUncensored text AI via API: what the model accepts, a first call in curl and Python, legal adult uses and real limits.
Free AI API key: what a trial credit gets youFree AI API key: what it really offers, the $0.50 trial credit converted into request count, with exact calculations, and what comes next.
Everything about Uncensored AI: Usage, Integration, and LimitsAccess the uncensored AI API with pay per token pricing. Integrate the uncensored LLM API today.