API Documentation

Authentication and Base URL

Start by updating your client configuration with your unique API key and our specific base URL. You do not need to change your code logic, only the connection string. The endpoint is https://api.gatewayllm.cc/v1 and requires the Authorization: Bearer <key> header. This setup works with any standard OpenAI-compatible SDK you already have installed.

First Request

Send a standard chat completion request to verify your connection and receive an immediate response. Use the model ID uncensored to access our specific large language model. The following example demonstrates a simple text interaction using the cURL command-line tool.

Copycurl https://api.gatewayllm.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check server health status"}]
  }'

Your response will arrive as JSON containing the generated text. If you receive a valid response, your integration is working correctly.

Python SDK Integration

Use the official OpenAI Python library to interact with our endpoint by overriding the base URL. This allows you to keep your existing Python code structure while switching the underlying provider. The following snippet shows how to initialize the client and send a message.

Copyfrom openai import OpenAI

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

The library handles serialization and deserialization automatically. You can now use standard methods like chat.completions.create with our backend.

Node.js SDK Setup

Initialize the OpenAI Node.js package with your key and our base URL to start generating content. This approach ensures compatibility with existing Node applications without requiring major refactoring. The following code demonstrates the initialization process.

Copyimport OpenAI from "openai";

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

Call the completion method with your desired model ID. The response object will contain the generated text in the content field.

Streaming and SSE

Enable streaming to receive tokens as they are generated, reducing perceived latency for long outputs. Set stream: true in your request parameters to activate Server-Sent Events. The following example shows how to consume the stream in chunks.

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)

Each chunk contains partial data. The final chunk includes the total token usage statistics. This method is ideal for real-time user interfaces.

Limits, Errors, and Context

Monitor your request rate and handle errors gracefully to maintain a stable application. Our API enforces a limit of 300 requests per minute per key. You will receive a 401 error if your key is invalid, a 402 error if your prepaid credit is exhausted, and a 429 error if you exceed the rate limit. Each request supports a context window of 100,000 tokens. Ensure your prompt plus completion stays within this limit to avoid truncation.