One API: Quickstart Guide

Base URL & Authentication

Start by pointing your client to our dedicated endpoint. This openai compatible api uses standard authentication headers, so you only need to change two values in your configuration.

The base URL is https://api.onekeyllmapi.com/v1. Generate your unique API key on the signup page. No card is required to start, and the key is shown immediately upon registration. Keep this key secure; it authenticates all requests to the service.

Basic Completion

Send a simple text prompt to receive a direct response. This is the core of our ai api for developers offering. The model returns text without content refusals for lawful adult use, making it ideal for creative or unrestricted tasks.

• Model ID: uncensored
• Endpoint: POST /v1/chat/completions
• Context: 64,000 tokens

Make your first request with this example:

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

Python SDK Integration

Use the official OpenAI Python library to interact with our service. The only changes needed are the base_url and api_key. This ensures your existing logic works without modification.

• Install via pip install openai
• Set environment variables or pass directly in the client init
• Call chat.completions.create() as usual

Configure the client like this:

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.onekeyllmapi.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 SDK Usage

Integrate with JavaScript or TypeScript projects using the standard OpenAI Node package. Point the client to our URL and provide your key. This approach maintains compatibility with any OpenAI-compatible client structure.

• Install via npm install openai
• Initialize with custom base URL
• Use standard async/await patterns

Example initialization:

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.onekeyllmapi.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 Responses

Receive responses token-by-token for lower perceived latency. Our streaming api supports Server-Sent Events (SSE), allowing you to display output as it generates. This is useful for chat interfaces or real-time applications.

• Set stream: true in your request
• Parse the SSE stream on the client
• Handle partial tokens efficiently

Enable streaming in your code:

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)

Limits, Errors & Context

Understand the constraints to build robust integrations. The API supports a 64k context api window, allowing long documents or conversations. Requests are limited to 8 MB body size.

Common errors include 401 for invalid keys, 402 when prepaid credit is exhausted, and 429 for exceeding 300 requests per minute. Pay-as-you-go credit never expires, and you can top up from $10. Tool calling is supported for function execution.