OpenAI Compatible API Quickstart

Base URL and Authentication Setup

Start by pointing your client at our dedicated endpoint. We use standard headers so your existing logic works immediately.

• Base URL: https://api.openaicompatibleapis.com/v1
• Auth: Bearer token via Authorization header

Generate a key on the dashboard. No phone number required.

Chat Completions Endpoint (POST /v1/chat/completions)

Send prompts and receive text responses through the standard chat interface. This is the core of our uncensored API.

The model ID is uncensored. It handles 100,000 token context windows efficiently.

List Models Endpoint (GET /v1/models)

Verify connectivity by checking available models. This endpoint returns the single uncensored LLM we host.

Use this for quick health checks before sending heavy payloads.

Streaming Responses and Token Usage

Receive data in real-time via Server-Sent Events (SSE). Token usage details appear in the final chunk.

Great for UIs that need instant feedback without waiting for full completion.

Function Calling and JSON Mode

Structure your outputs precisely using response_format: json_object. Tool definitions work exactly like the OpenAI spec.

Set tool_choice to force specific behaviors. Ideal for automated workflows.

Rate Limits and Token Constraints

Enforce strict limits to ensure stability. Each key allows 300 requests per minute and 8 concurrent connections.

Max output is 16,000 tokens. Errors are free. Context is 100k tokens total.

cURL

Copycurl https://api.openaicompatibleapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current system time"}]
  }'

Python

Copyfrom openai import OpenAI

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