API Documentation

Base URL and Authentication

The API follows standard OpenAI conventions. Use HTTPS://api.chatkiohnezensur.com/v1 as your base URL. Retrieve your key from the dashboard after signing up with Google or email. Keep this key secure. Pass it in the Authorization header as a bearer token.

Authentication is straightforward. No complex routing or vendor-specific quirks apply here. Your requests go directly to our dedicated uncensored model. Errors like 401 indicate an invalid key. Check your account settings if access fails.

Each account allows one active key. Generating a new key replaces the old one immediately. This ensures you always control access. No phone number verification is required for signup.

Copycurl https://api.chatkiohnezensur.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the three main points of the provided text"}]
  }'

First Request with Python

Send text to the model using the official SDK. Install the package and configure your key. The model ID is uncensored. Requests return text responses directly. This works for roleplay or unrestricted creative writing.

Set the temperature for creativity. Use top_p for nucleus sampling. Adjust max_tokens to control output length. The default max is 2,048 tokens unless you specify otherwise. Errors and refusals do not consume credits.

Response formatting is standard JSON. Handle exceptions gracefully. The API supports streaming for real-time output. Use the stream parameter for better user experience in apps.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatkiohnezensur.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)

Node SDK Implementation

Integrate the API into Node.js applications easily. Configure the base URL correctly. Pass your API key in the headers. The SDK handles serialization automatically. This reduces boilerplate code significantly.

Stream responses to update the UI in real time. Process chunks as they arrive. This provides a smoother experience for users waiting for long outputs. Context window supports 100,000 tokens total.

Function calling is available via the tools parameter. Define schemas for structured data extraction. The model respects the format constraints. JSON mode ensures consistent outputs for parsing.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatkiohnezensur.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);

Streaming and SSE

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Each chunk contains partial text. The final chunk includes token usage statistics.

Process data as it arrives. This reduces perceived latency for long responses. Buffer chunks to reconstruct the full message. Handle network interruptions gracefully.

Streaming works with function calling too. Receive tool calls incrementally. Update the UI dynamically. This approach scales well for high-traffic applications.

Copystream = 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)

Rate Limits and Constraints

Each API key allows 300 requests per minute. Concurrency is limited to 8 simultaneous requests. Request bodies cannot exceed 8 MB. These limits prevent abuse during peak usage.

Rate limits reset every minute. Exceeding them returns a 429 error. Wait before retrying. Premium tiers might offer higher limits in the future.

Context window supports 100,000 tokens. This includes both prompt and completion. Monitor usage to stay within bounds. Large inputs consume more credits.

Token Counting and Costs

Pay only for what you use. Input tokens cost $0.15 per 1M. Output tokens cost $0.50 per 1M. Credits never expire. Errors are free.

Top up with crypto. USDT on TRC20 or USDC on Base. Minimum deposit is $20. Bonus credit applies for larger amounts. +5% from $50, +10% from $100, +15% from $200.

New accounts get $0.50 trial credit. Valid for 7 days. Check usage in the dashboard. Refunds are not issued for credit.