Connect to the LLMPort API

Prepare your account and key

Sign in, create an API key in your account, and check that you have available credit. Keep the key in server environment variables; never include it in browser code.

Set environment variables

Replace the placeholders with your key and an exact chat model ID from the catalog, rather than a display name.

export LLMPORT_API_KEY="your-llmport-api-key"
export LLMPORT_MODEL="exact-chat-model-id-from-pricing"

Python example

Run pip install openai, then run this Python code.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://llmport.si/v1",
    api_key=os.environ["LLMPORT_API_KEY"],
)
response = client.chat.completions.create(
    model=os.environ["LLMPORT_MODEL"],
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Node.js example

Run npm install openai, save the code as quickstart.mjs, then run node quickstart.mjs.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://llmport.si/v1",
  apiKey: process.env.LLMPORT_API_KEY,
});
const response = await client.chat.completions.create({
  model: process.env.LLMPORT_MODEL,
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

curl example

Test the connection from your terminal. This makes a real request and is billed according to your account settings.

curl https://llmport.si/v1/chat/completions \
  -H "Authorization: Bearer $LLMPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d "$(printf '{"model":"%s","messages":[{"role":"user","content":"Hello!"}]}' "$LLMPORT_MODEL")"

Streaming and common errors

For models that support streaming, set stream=true and read the response chunks. For 401, check your key; for 403, check model and group access; for 429, check rate limits and credit. If a model is unavailable, check its exact ID and supported endpoint. Image, video and model-specific parameters differ.