Content Generation
Produce raw text without unexpected refusals for creative apps.
Crypto API Access
Uncensored open ai API for developers
Get uncensored open AI API access with a 100,000 token context window and prepaid crypto credits that never expire for your projects.
- 100k token context window
- Crypto only payments
- No monthly fees
per 1M input tokens$0.15
Output tokens / 1M$0.50
token context100,000
trial credit$0.50
requests per minute300
Test with one call
curl https://api.aiopenuncensored.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Check if port 8080 is open"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.aiopenuncensored.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.aiopenuncensored.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);Base URLhttps://api.aiopenuncensored.com/v1
Modeluncensored
Core features
OpenAI Compatible
Drop-in replacement for existing clients using standard endpoints.
Uncensored Output
Answers without filtering lawful adult or controversial topics.
Streaming Support
SSE streaming with token usage in the final chunk.
JSON Mode
Enforce structured outputs with response_format json_object easily.
Tool Calling
Native support for tools and tool_choice parameters.
No Expiry
Prepaid credit never expires after you top up.
Setup steps
Create Account
Sign up with Google or email to get your key.
Top Up Credit
Add crypto funds starting from twenty dollars minimum.
Start Requesting
Send prompts to the chat completions endpoint immediately.
Common use cases
Data Extraction
Parse large documents using the extended context window effectively.
Chatbots
Build conversational agents that handle diverse user inputs freely.
Research Tools
Analyze sensitive topics without standard corporate content filters blocking.
uncensored open AI: The API that answers everything
We provide a single, dedicated uncensored model via a standard OpenAI-compatible interface, eliminating the complexity and variable quality of routing through multiple vendors.
NSFW LLM for Adult Content
Generate raw text without refusals for lawful adult material.
Unfiltered Chatbot Logic
Build conversational agents that answer directly, avoiding generic politeness filters that truncate useful context.
Security Research Data
Extract precise technical details without the model hedging its answers due to controversial topics.
The uncensored provider checklist: 7 points to verify
Verify these seven points to ensure your uncensored API provider delivers raw, unfiltered outputs.
- Base URL compatibility: Confirm the endpoint is OpenAI-compatible (e.g., /v1/chat/completions).
- Model identity: Check if the service runs its own uncensored model or routes third-party models.
- Refusal behavior: Test for refusals on lawful adult or controversial topics.
- Pricing transparency: Ensure prepaid credits cover errors and refusals are free.
- Privacy policy: Verify prompts are not used for training.
- Access method: Confirm crypto-only or flexible payment options.
- Rate limits: Check requests per minute and concurrent connection limits.
Migrate from your current OpenAI provider in three steps
Switch to our uncensored AI API by updating two variables in your client configuration. First, replace your base URL with HTTPS://api.aiopenuncensored.com/v1. Second, swap in your new API key. Third, set the model ID to "uncensored". This single model handles all your text requests without complex routing. You can now generate content freely. Use our standard OpenAI-compatible SDKs to integrate instantly. Your existing code structure remains valid.
From signup to first token: 4 quick steps
Get your first uncensored response in minutes by following these four steps.
- Sign up with Google or email to receive an API key instantly.
- Load your account with crypto credit to start making requests.
- Configure your client to use the
https://api.aiopenuncensored.com/v1base URL. - Send a
POST /v1/chat/completionsrequest with the model IDuncensored.
Is it truly uncensored? 5 signs you are getting filtered output
Filtering hides your raw data. Verify your uncensored AI API by checking for these six signs in the response stream.
| Sign | Filtered Output | Uncensored Output | |||
|---|---|---|---|---|---|
| Refusal Logic | Includes refusal reason text | Direct answer without preamble | |||
| Content Limits | Blocks lawful adult topics | Answers controversial queries directly | Keywords | Adds "Sure, here is..." | Starts immediately with the answer |
| JSON Mode | Alters structure to avoid tags | Preserves raw JSON object | |||
| Streaming | Stops abruptly on sensitive words | Streams continuous tokens | |||
| Model ID | Uses standard commercial IDs | Returns "uncensored" | |||
| Privacy | Prompts used for training | No training on your data |
Common uncensored API mistakes and how to avoid them
Common uncensored API mistakes and how to avoid them
Developers often assume a single API key handles unlimited traffic, but we enforce a 300 requests per minute limit per key.
- Set
max_tokensexplicitly to avoid unexpected $0.50 per 1M output charges. - Use the correct base URL:
https://api.aiopenuncensored.com/v1. - Remember that errors are free, so retry logic is safe.
Always verify your model id is uncensored to ensure you are using our dedicated open-weight model, not a generic endpoint.
FAQ
What is uncensored open AI and how does it differ from standard models?
It is a hosted API serving one model that answers without refusing lawful adult topics. Unlike filtered alternatives, it allows controversial outputs. Our specific endpoint is POST /v1/chat/completions, ensuring direct access to the unfiltered model via standard OpenAI-compatible clients.
Is the uncensored AI model open source?
No. It is an open-weight model run on our servers, not a fully open-source repository you can download. You interact with it via our API endpoint. The model is tuned to answer without content refusals for lawful adult use.
How much does the uncensored LLM API cost per token?
It costs $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. You pay only for real usage via prepaid credit, which never expires and is topped up exclusively with crypto.
Does the uncensored API support streaming responses?
Yes. You can enable streaming via Server-Sent Events (SSE) to receive tokens progressively. Token usage details are included in the last chunk. This ensures low latency for your application while maintaining the standard OpenAI-compatible response format.
What is the maximum context window for requests?
The context window supports 100,000 tokens for both prompt and completion combined. You can request up to 16,000 tokens per response. If you do not set max_tokens, the limit defaults to 2,048 tokens for the output.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Get your API key
Sign up, copy the key, update the endpoint URL. Setup is done.
