OpenAI compatible endpoint quickstart guide

Prerequisites: Python or Node.js

Install the official openai package for your runtime environment before proceeding.

Python users need version 1.0.0 or later. Node developers require version 4.0.0 or newer. Both versions support the standard chat-completions structure.

No extra dependencies are required. The SDK handles JSON serialization and HTTP transport automatically.

Configure base_url and API key

Point your SDK client to our base URL and supply your generated key.

Use https://api.openaicompatibleendpoint.com/v1 as the base URL. Set the API key to the value shown on your dashboard.

• Python: base_url="https://api.openaicompatibleendpoint.com/v1"
• Node: baseURL: "https://api.openaicompatibleendpoint.com/v1"

This configuration works with any OpenAI SDK compatible client. No code changes are needed for the rest of your logic.

Send your first chat completion

Make a POST request to /v1/chat/completions with your system and user messages.

The model ID is uncensored. This model answers without refusing lawful adult or controversial topics.

• Context window: 100,000 tokens total.
• Max output: 16,000 tokens.

Send your prompt and receive text output immediately. Errors and refusals are free. Only real token usage counts against your prepaid credit.

Enable streaming and function calling

Enable streaming by setting stream: true in your request parameters.

Token usage is included in the last chunk of the stream. This allows you to track costs in real-time.

Function calling is fully supported. Use the tools parameter to define your schema. The model returns structured tool calls that you can execute in your application logic. JSON mode is also available via response_format.

Handle errors and token limits

The API returns standard HTTP status codes for common issues.

• 401: Invalid API key. Check your dashboard.
• 402: Insufficient credit. Top up with USDT or USDC.
• 429: Rate limit exceeded. You are allowed 300 requests per minute.

If you exceed the 16,000 token output limit, the response will be truncated. The context window includes both prompt and completion tokens.

Pricing and limits

Pay only for what you use. Input tokens cost $0.15 per 1M. Output tokens cost $0.50 per 1M.

Prepaid credit never expires. Refunds are not issued, but double charges are fixed via Support.

Top up with crypto only. Acceptable currencies are USDT (TRC20) and USDC (Base). Minimum top-up is $20. Bonus credit ranges from +5% to +15% depending on amount.

cURL

Copycurl https://api.openaicompatibleendpoint.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return list of supported file formats"}]
  }'

Python

Copyfrom openai import OpenAI

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