Quickstart: Integrate Uncensored AI API
Integrate our Uncensored AI API in minutes: Use the OpenAI-compatible interface for immediate results with the "uncensored" model and without complex contracts.
https://api.kiohnezensurapi.com/v1uncensored
Base URL and Authentication
Integration starts by configuring your base URL. For all requests to our uncensored AI API, use https://api.kiohnezensurapi.com/v1. This ensures compatibility with existing OpenAI SDKs and clients. For authentication, pass your personal API key in the Authorization header. The value must be provided in the format Bearer DEIN_API_KEY. Get your key after registration on the "Get API key" page. One key per account is sufficient; you can regenerate it at any time if needed, which invalidates the old key. Authentication is required to track your requests and debit your prepaid credit.
First request with cURL
Test the interface directly via the command line to verify how it works. Send a POST request to the endpoint /v1/chat/completions. The model is addressed with the ID uncensored. You can set the response type to json_object if you need structured data. The response contains the generated text under message.content. This method is great for quick tests before you choose a programming language. Make sure to keep an eye on your prepaid credit, as each request incurs a cost.
curl https://api.kiohnezensurapi.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."}]
}'
Integration with Python
For Python users, the official openai SDK is available. Initialize the client with the custom base_url and your api_key. This allows direct use of our uncensored AI without changing the logic. Send the request via client.chat.completions.create(). The context window is 100,000 tokens, which is sufficient for extensive documents. Error handling should catch HTTP errors to detect any limits or authentication issues. Python is ideal for data-intensive applications and scripting.
from openai import OpenAI
client = OpenAI(base_url="https://api.kiohnezensurapi.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)
Integration with Node.js
Developers working in JavaScript or TypeScript also use the standard SDK. Configure the client as described above with our base URL. The asynchronous nature of Node.js works well with API requests. You can use Promises or async/await to retrieve the response text. Make sure to pass the correct model name uncensored. Response speed depends on server load, but the interface is designed to work fast and reliably. This is the recommended method for web applications and microservices.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.kiohnezensurapi.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);
Enable streaming
If you need low latency for the user interface, enable streaming mode. Set the stream argument to true. The API then sends Server-Sent Events (SSE), which you can parse line by line. This enables step-by-step display of the response instead of waiting for full generation. The data structure changes slightly; you receive chunk objects instead of a complete JSON object. This is particularly useful for chat interfaces that need to provide real-time feedback.
stream = client.chat.completions.create(
model="uncensored",
messages=[{"role": "user", "content": "Tell the story in second person."}],
stream=True,
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
Limits, errors and models
Note the technical limits: you have 300 requests per minute per key. The maximum allowed request body is limited to 8 MB. On errors, the API returns standard HTTP codes. A 401 error means your API key is invalid. A 402 error indicates insufficient credit. A 429 error signals that you have exceeded the rate limit. Use the GET endpoint /v1/models to query available models. Our model supports function calling and streaming. There are no other models to choose from; we offer a specialized, open-weight solution without censorship for adults and creative purposes.
Capabilities and limits
Use this table to decide whether the API fits your project before you buy credit.
| Feature | Support |
|---|---|
| API format | OpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key |
| Base URL | https://api.kiohnezensurapi.com/v1 |
| Model | uncensored |
| API key | Authorization: Bearer YOUR_KEY |
| Methods | POST /v1/chat/completions · GET /v1/models |
| Context window | 100,000 tokens, input and output combined |
| Structured output | response_format: {"type": "json_object"} |
| Max output | prompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap |
| Function calling | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| SSE streaming | Yes — server-sent events; the last chunk carries token usage |
| Other parameters | temperature, top_p, stop, seed, presence_penalty, frequency_penalty |
| Requests per minute | 300/min per key |
| Parallel requests | up to 8 in parallel per key |
| Response headers | X-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency |
| Request size | 8 MB request body |
| Top-up | crypto: USDT on TRON or USDC on Base, $20–$500, any whole sum |
| Bonus credit | +5% on $50+, +10% on $100+, +15% on $200+ |
| Trial credit | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| Token prices | $0.15 per 1M input tokens · $0.50 per 1M output tokens |
| Billing | pay as you go from prepaid credit; nothing is charged for failed or refused requests |
| Credit expiry | paid credit never expires, no subscription |
| Content policy | uncensored for adults; the only hard rule: no sexual content involving minors |
| Key management | one key per account, regenerate any time (the old one stops working) |
| Sign-in | sign in with Google or with e-mail + password |
Error reference
Errors come back as JSON with a stable type; failed and refused requests are not billed.
| Code | Type | Meaning |
|---|---|---|
400 | bad_request | invalid JSON, empty messages, bad parameter, or a prompt longer than the window — fix and resend |
401 | missing_key · invalid_key · key_revoked | no key, wrong key, or a key replaced by a newer one |
402 | no_credit | out of credit; add credit and retry |
403 | content_blocked | refused by the content policy |
404 | not_found | unknown endpoint |
413 | request_too_large | body over 8 MB |
429 | rate_limited · concurrency | slow down: rate or parallel limit reached |
503 | upstream_busy | model busy — retry in a few seconds |
Frequently Asked Questions
What exactly does "uncensored" mean for this model?
The model does not automatically reject topics like adult content, controversial opinions or creative freedom as long as they are legally permitted. There are no predefined filters for political or social topics. The only exceptions are sexually explicit content involving minors, which is always blocked.
How much does it cost to use the API?
You pay only for what you consume. The price is $0.15 per 1 million input tokens and $0.50 per 1 million output tokens. There are no monthly base fees. You top up your account with deposits starting from $20, and credits never expire.
Is my chat history used for training?
No. The API stores your requests solely for billing and context management during the session. Your prompts are not used to train or improve the model. Your data privacy is ensured by the simple registration with email and password.