AI Gateway: Switch your client in three lines

Prerequisites: Install Your Preferred SDK

Before making requests, ensure your development environment has the appropriate SDK installed. Since our endpoint follows the openai compatible api standard, you can use the official library or any compatible client. For Python, run pip install openai. For Node.js, use npm install openai. No additional configuration files are required beyond the environment variables you will set in the next step.

Step 1: Configure Base URL and API Key

Our ai gateway endpoint operates at a distinct base URL. You need to retrieve your API key from the dashboard and configure your SDK client to point to https://api.openaigatewayapi.com/v1. This ensures all requests bypass standard OpenAI infrastructure and route directly to our uncensored model servers. You do not need to change the model name; simply set the base URL and provide your key.

Step 2: Send a Standard Chat Completion Request

With the client configured, you can send a standard chat completion request. The model ID is uncensored. This request demonstrates the basic text-in, text-out capability. The system will process your prompt and return a completion without the typical content filters applied by major providers, provided the content is not sexually explicit involving minors. Use the following command to verify connectivity.

Step 3: Enable Streaming with Server-Sent Events

For lower latency and better user experience, enable streaming by setting stream=true. The endpoint supports Server-Sent Events (SSE), allowing you to receive tokens as they are generated. This is particularly useful for long-form generation or interactive applications. The response stream will emit partial chunks until the completion is finished, providing real-time feedback without waiting for the entire context window to be processed.

Step 4: Use Function Calling for Tool Integration

The endpoint supports tool calling, allowing you to define functions and let the model decide when to invoke them. This enables complex workflows by integrating external APIs or data sources directly into your LLM logic. Define your tools in the tools parameter, and the model will return structured JSON output when appropriate. This feature works identically to the standard OpenAI format, making it easy to swap providers without rewriting your tool integration logic.

Step 5: Handle Errors and Rate Limits

Monitor your API key usage and handle potential errors gracefully. If the key is invalid, you will receive a 401 error. If your prepaid credits are exhausted, a 402 error indicates you need to top up. The system enforces a limit of 300 requests per minute per key; exceeding this will trigger a 429 rate limit error. Additionally, keep your request body under 8 MB to avoid rejection. The context window supports up to 100,000 tokens for both prompt and completion combined.

cURL

Copycurl https://api.openaigatewayapi.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."}]
  }'

Python

Copyfrom openai import OpenAI

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