API Documentation

Authentication and Base URL

The lite llm API requires a bearer token. Send your API key in the Authorization header. Use the base URL provided below for all requests. This works with any OpenAI compatible client.

Base URL: https://api.llmlite.cc/v1

Get your key by signing up with Google or email. The key appears immediately. Use it in every request.

Chat Completions Endpoint

Send messages to the /v1/chat/completions endpoint. The model ID is uncensored. It outputs text directly without blocking lawful adult content.

Here is a basic request structure:

Copycurl https://api.llmlite.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list available models via get request"}]
  }'

Receive a JSON response with the generated text. Check the usage object for token counts.

Python SDK Integration

Use the official OpenAI Python SDK. Set the base URL to our endpoint. Set the API key. Call chat.completions.create. The library handles the request.

Copyfrom openai import OpenAI

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

Install the SDK via pip. Run your script. The model responds with the completion.

Node.js SDK Setup

Initialize the OpenAI client in Node. Provide the base URL and API key. Call the chat completions method. This works for server-side scripts or APIs.

Copyimport OpenAI from "openai";

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

Handle the response object. Access the generated text from the first choice.

Streaming and Token Usage

Enable streaming by setting stream: true. Receive Server-Sent Events (SSE). Each chunk contains partial text. Token usage appears in the final chunk.

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)

Process each event as it arrives. This reduces perceived latency for long outputs. Monitor the last chunk for accurate token counts.

Limits, Errors, and Context

The context window is 100,000 tokens. Max output is 16,000 tokens per request. You get 300 requests per minute. Concurrent requests are limited to 8.

Handle errors appropriately. A 401 status means your key is invalid. A 402 status indicates no credit remains. A 429 status means you hit the rate limit. Credit never expires. Errors are free.