OpenAI Compatible API Quickstart

Prerequisites and Environment Setup

You need an API key and the correct base URL to connect your client. Sign up with Google or email on the Get API key page to receive your credential immediately. The trial gives you $0.50 for seven days, and you can top up with USDT or USDC via crypto. Keep your key secure and verify it matches your account settings.

Ensure your environment supports standard HTTP requests. Our service runs on a single uncensored model, so you do not need to manage multiple model endpoints. Set your base URL to HTTPS://api.openaiapicompatibility.com/v1 before making any calls. This ensures all requests route correctly to our tuned inference servers.

Installing the Official OpenAI SDK

Use the official SDKs to maintain compatibility with existing OpenAI workflows. The Python and Node libraries work directly with our endpoint because we follow the standard API schema. Install the package in your project directory using your preferred package manager. This approach avoids the need for custom HTTP client code.

We support standard parameters like temperature, top_p, and stop sequences. The SDK handles the JSON serialization and request headers automatically. You can swap the base URL in the client configuration to point to our servers. This allows you to switch between providers without changing your application logic.

Configuring the Base URL and API Key

Set the base URL and API key in your client configuration object. The base URL is HTTPS://api.openaiapicompatibility.com/v1. Pass your API key in the Authorization header as a Bearer token. This configuration ensures your requests are authenticated and routed to the correct service.

Copycurl https://api.openaiapicompatibility.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all python packages for data science"}]
  }'

Verify your connection by calling the GET /v1/models endpoint. This returns a list of available models, including the uncensored model identifier. Use this step to confirm your network access and credentials are correct before sending complex prompts.

Making Your First Chat Completion Request

Send a POST request to /v1/chat/completions with your prompt messages. Define the model as uncensored to access the unfiltered inference engine. Include your system prompt to set the behavior, and add user messages for the content you want generated.

Copyfrom openai import OpenAI

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

The response contains the generated text and token usage statistics. You can adjust parameters like temperature to control creativity. The model does not refuse lawful adult or controversial topics, making it suitable for diverse use cases. Check the response object for the content field to access the output.

Streaming Responses with SSE

Enable streaming by setting the stream parameter to true in your request. This sends partial responses as Server-Sent Events (SSE). It improves the user experience by showing text as it is generated.

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 a delta of the response. Accumulate these deltas to reconstruct the full text. The final chunk includes the total token usage for the request. This method works with any standard SSE client or library. It reduces perceived latency for long-form content generation.

Handling JSON Mode and Function Calling

Use JSON mode by setting response_format to json_object. This forces the model to output valid JSON instead of free text. It is useful for structured data extraction or API responses. Combine this with function calling for tool use scenarios.

Define your tools in the tools array. Specify the function name, description, and parameters. The model will return the function call details in the response. You can then execute the function and send the result back to the model. This enables complex multi-step workflows with the uncensored model.

Node.js

Copyimport OpenAI from "openai";

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