LLM API Quickstart Guide | LLM API Source

Base URL and Authentication

To use the llm api, point your client to https://api.llmapisource.com/v1. Authentication uses a standard API key passed in the Authorization: Bearer <key> header. You can generate or rotate keys on the dashboard; revoking a key immediately invalidates the old one.

• No phone number or credit card is required for the trial.
• Each account holds exactly one active key at a time.
• Prompts are not used for training.

First Request

Send a simple chat completion to verify connectivity. The endpoint supports standard OpenAI JSON structures. Replace the placeholder with your actual key.

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

If the key is invalid, you receive a 401 error. If you have no prepaid credit, you receive a 402 error. The model identifier is always uncensored.

Python SDK

Install the official OpenAI package and configure the base URL to route requests to our infrastructure. This works with any OpenAI-compatible Python client.

Copyfrom openai import OpenAI

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

Ensure the base_url includes the full path to /v1. The model name must be set to uncensored to access the dedicated instance.

Node SDK

For Node.js environments, configure the client similarly. The structure mirrors the standard OpenAI interface, making migration straightforward.

Copyimport OpenAI from "openai";

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

Pass the apiKey and set the basePath to https://api.llmapisource.com/v1. This ensures all completions are routed to our uncensored model.

Enable Streaming

Set stream: true in your request to receive Server-Sent Events (SSE). This allows you to process tokens as they generate, reducing perceived latency for long responses.

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 the stream events to update your UI in real-time. Each chunk contains a partial delta of the completion.

Limits, Errors, and Context

Our infrastructure enforces specific limits to ensure stability. The context window supports up to 100,000 tokens for prompt plus completion combined.

• Rate Limit: 300 requests per minute per key (returns 429).
• Body Size: Maximum 8 MB per request.
• Pricing: $0.25/1M input tokens, $1.00/1M output tokens.

Requests involving sexual content with minors are blocked. All other lawful adult content is permitted.