OpenAI-Compatible API Documentation

Quickstart: Connect with OpenAI SDK

Start by authenticating with your key and pointing the client to our base URL. This setup works with the official OpenAI SDKs for Python and Node.js, ensuring you can run the same client code against our service. You need a valid API key from the dashboard and the correct endpoint configuration.

Copycurl https://api.openaiapicompatible.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the current UTC timestamp in ISO 8601 format"}]
  }'

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

Chat Completions Endpoint

Send text to our single chat endpoint for direct text output. We use POST /v1/chat/completions to process your prompts and return generated text. This is the core interaction for most LLM applications, requiring no complex routing or additional service calls.

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)

Streaming with SSE

Receive tokens in real-time using Server-Sent Events for lower latency. Enable streaming by setting the stream parameter to true in your request. The final chunk includes token usage data, allowing you to track costs accurately as the model generates text. This approach keeps your UI responsive even for long outputs.

Function Calling & JSON Mode

Integrate tools and enforce structured outputs for reliable programmatic interactions. Use the tools parameter to define function schemas and set response_format to json_object for strict JSON compliance. Our uncensored model handles complex instructions and edge cases without refusing valid functional requests.

Rate Limits & Parameters

Monitor your usage against strict per-key limits to avoid service interruptions. You are allowed 300 requests per minute and eight concurrent requests per key, with an 8 MB body limit. Errors like 401 (invalid key), 402 (no credit), and 429 (rate limit) indicate specific account states.

Context Window & Constraints

Maximize context handling with a 100,000-token window for combined input and output. Set max_tokens to control generation length, defaulting to 2,048 if unspecified. Our model runs on proprietary servers, not as a proxy for other vendors, ensuring consistent performance for your specific use case.