LLM Hosting: LLM API Quickstart Guide

Authentication & Keys

To use the llm hosting API, you need an API key from your account dashboard. The key authenticates all requests. Keep it secure; anyone with the key can use your prepaid credit. You can regenerate the key at any time, which immediately invalidates the previous one. Each account supports one active key. No phone number or credit card is required to start, as new accounts receive trial credit.

Base URL Configuration

Our API is fully OpenAI-compatible. To switch, update your client's base URL to https://api.llmhostingapi.com/v1 and set your API key in the authorization header. This works with the official OpenAI SDKs and any compatible client library. You do not need to change your code logic, just the endpoint and credentials. The model identifier to use is uncensored.

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

Chat Completions Endpoint

Send text to the model via POST /v1/chat/completions. The API accepts messages and returns text responses. We support a 100,000 token context window for both input and output. Function calling is supported for structured data extraction. The model is tuned to answer without content refusals for lawful adult use, making it ideal for creative, research, or adult content generation without extra configuration.

Copyfrom openai import OpenAI

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

Streaming Responses (SSE)

For lower latency and real-time user experiences, enable streaming by setting stream: true. The API returns Server-Sent Events (SSE) chunks. This allows you to display partial responses as they are generated. Streaming does not affect pricing or token counts. It is recommended for chat interfaces where users expect immediate feedback. Ensure your client handles SSE parsing correctly.

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)

Function Calling Support

Define functions in your request body using the tools parameter. The model will respond with function calls instead of plain text when appropriate. You must execute the function on your side and send the result back in the next conversation turn. This enables complex workflows like database queries or API integrations. The model handles tool selection automatically based on the user's prompt and available function definitions.

Model Listing Endpoint

Query GET /v1/models to list available models. You will see the uncensored model with its ID, created date, and owned by field. This endpoint helps verify connectivity and model availability. It returns standard OpenAI-format JSON. Use this to debug authentication issues before sending chat requests. The endpoint is lightweight and returns immediately.

Node.js

Copyimport OpenAI from "openai";

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