Uncensored Chat Completions API

Authentication & Base URL

Use your generated API key with the base URL https://api.openrouteraisettingskeys.com/v1 to route requests. We function as an openrouter alternative for developers who want to avoid subscription layers while keeping their client code identical. The key authenticates your prepaid credit directly against the openrouter AI settings keys infrastructure. You receive one active key per account; generating a new one replaces the previous credential immediately. No phone number or bank details are required during signup, only an email or Google login. This direct key management ensures you control access without third-party billing friction. Your prompts remain private and are never used for training the underlying model.

Chat Completions Endpoint

Send POST requests to /v1/chat/completions to receive text responses from the uncensored model. The system accepts standard message arrays and returns completions without refusing lawful adult or controversial topics. You pay only for tokens actually used, with input costs at $0.15 per 1M tokens and output at $0.50 per 1M tokens. Errors and refusals incur no charge, ensuring you never pay for failed attempts. The endpoint supports a context window of 100,000 tokens for both prompt and completion combined. Max output is capped at 16,000 tokens per request unless you specify a lower limit. This straightforward structure mirrors the OpenAI format, making migration effortless.

Python SDK Integration

Install the official OpenAI package and configure the base URL to point to our uncensored LLM endpoint. The following snippet demonstrates how to initialize the client and send a simple query. You must update the base_url parameter to match our API domain. The model identifier is simply uncensored, which runs our specific open-weight model tuned for direct answers. This approach allows you to reuse existing Python codebases with minimal changes. The SDK handles JSON serialization and streaming automatically. Ensure your API key is stored securely in environment variables for production use.

Node SDK Integration

Configure the Node.js OpenAI client to direct requests to our hosted API. The base URL must be set to our domain to ensure correct routing. You can pass the model ID uncensored alongside your messages to generate text. This method works with any standard OpenAI-compatible client library in JavaScript. The request structure remains identical to the OpenAI specification, ensuring compatibility. You can manage your prepaid credit directly through the dashboard. The SDK supports both synchronous and asynchronous request patterns. Adjust the apiKey value to match your generated credential. This setup provides a reliable way to integrate uncensored generation into your Node applications.

Streaming Responses

Enable streaming by setting the stream parameter to true in your request body. The API returns Server-Sent Events (SSE) for real-time token delivery. You can track token usage within the final chunk of the stream. This feature is ideal for chat interfaces that require immediate feedback. The uncensored model maintains context throughout the stream without interruption. You can parse the SSE data using standard event listeners in your client. Streaming works with all parameters like temperature and top_p. This method reduces perceived latency for end-users significantly. It is the recommended approach for interactive applications.

Limits, Errors & Context

Your API key allows 300 requests per minute and 8 concurrent connections. The request body must not exceed 8 MB. If you receive a 401 error, your key is invalid or expired. A 402 error indicates insufficient prepaid credit; top up via USDT or USDC to resume service. A 429 error means you have hit the rate limit. The model supports a 100,000-token context window for combined input and output. Hard content limits still apply, specifically regarding sexual content involving minors. These limits ensure stable performance for high-volume developers. You can monitor your usage directly in the account dashboard. Errors are free, so you only pay for successful completions.

cURL

Copycurl https://api.openrouteraisettingskeys.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check my current key balance"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openrouteraisettingskeys.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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openrouteraisettingskeys.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

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)