Quickstart: Connect your app

Prerequisites: SDK Installation

Install the official client library for your language before making requests. Our endpoint works with any standard openai API alternative SDK because we follow the same JSON schema. You do not need special drivers or extra dependencies to start generating text immediately.

Configure Base URL and Key

Point your SDK client to our specific endpoint to route traffic through our proxy. You must set the base URL to HTTPS://api.llmapiproxy.com/v1 and provide the key you generated on the dashboard. This simple configuration change allows your existing application to use an uncensored AI backend without rewriting your core logic.

Send Your First Chat Completion

Make a standard POST request to the chat completions endpoint with your model ID. Our server processes the input and returns text without filtering lawful adult or controversial topics. The response structure matches the standard output format you already know.

Copycurl https://api.llmapiproxy.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fetch the current temperature in Tokyo"}]
  }'

Enable Streaming and Token Counts

Add stream=true to your request payload to receive text tokens as they are generated. Each chunk includes usage data, allowing you to track costs in real-time as the model writes. This approach reduces perceived latency for end-users while giving you precise visibility into token consumption.

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)

Handle Function Calling and JSON Mode

Use the tools parameter to enable function calling or set response_format to json_object for structured outputs. The model follows your instructions precisely without refusing complex logical tasks. This capability makes our proxy ideal for automated agents that require reliable data extraction.

Copyimport OpenAI from "openai";

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

Limits, Errors, and Context Window

We enforce a 100,000 token context window and a 429 rate limit of 300 requests per minute. If you receive a 401 error, your API key is invalid, while a 402 error indicates you need to top up your crypto credit. Keep request bodies under 8 MB to ensure smooth processing.

Copyfrom openai import OpenAI

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