OpenAI Compatible API: Switch your client in three lines

Prerequisites: Install OpenAI SDK

Before making requests, ensure your development environment has the official OpenAI SDK installed for your preferred language. This is the standard way developers interact with an openai compatible api, ensuring you get consistent typing and error handling. For Python, use pip install openai. For Node.js, run npm install openai. These libraries handle the underlying HTTP details, so you can focus on passing prompts and receiving text outputs.

Configure Base URL and API Key

The core advantage of our service is that you only need to update two configuration values. Point your client to our base URL: https://api.openaicompatibleapi.com/v1. Then, generate your API key on the signup page; it is shown immediately after registration with no credit card required. Set the base_url and api_key in your client initialization. This makes us a direct gpt api alternative for your existing projects without rewriting logic.

Make Your First Request

Send a standard chat completion request using the model ID uncensored. This model is an open-weight large language model tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model. You can test connectivity immediately with a simple text prompt. The response will return the generated text in the content field.

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

Enable Streaming Responses

For better user experience, enable streaming to receive tokens as they are generated. Set stream=True in your request. The SDK will yield chunks as they arrive, allowing you to display partial results instantly. This is particularly useful for long context windows up to 64,000 tokens. Streaming works identically to standard OpenAI clients, maintaining compatibility with your existing error-handling logic.

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)

Use Tool Calling (Function Calling)

Our API supports structured tool calling. Define your functions in the tools parameter, and the model will return tool calls in the response. You can then execute those tools and send the results back to the model for further reasoning. This feature works with any OpenAI-compatible client that supports the standard tool calling format. It is ideal for building agents or automating workflows without managing a complex llm proxy.

Copyfrom openai import OpenAI

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

Check Available Models

Query the GET /v1/models endpoint to verify available models. You will see the uncensored model listed. This confirms your API key and base URL are configured correctly. You can also use this endpoint to debug authentication issues. If the endpoint returns a list, your connection to the ai api for developers is active. No other models are offered, keeping the configuration simple.

Node.js

Copyimport OpenAI from "openai";

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