OpenAI SDK

Configuration

• Install the official openai package in your application.
• Set LLMRPM_API_KEY server-side and map it to OPENAI_API_KEY if the SDK expects that variable.
• Set the SDK baseURL / base_url to https://llmrpm.com/api/v1.
• Use any public model ID returned by GET /api/v1/models.

Example

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LLMRPM_API_KEY,
  baseURL: "https://llmrpm.com/api/v1",
});

const completion = await client.chat.completions.create({
  model: "claude-sonnet-5",
  messages: [{ role: "user", content: "Write three product taglines." }],
  max_tokens: 400,
});

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LLMRPM_API_KEY"],
    base_url="https://llmrpm.com/api/v1",
)

completion = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Write three product taglines."}],
    max_tokens=400,
)

Recommended models

Any public ID from the model list works. Common picks:

• claude-sonnet-5— strong model for reasoning, refactors, and coding agents.
• claude-haiku-4.5— fast option for autocomplete, small questions, and lightweight tasks.
• deepseek-v4-pro— alternative based on your active catalog and plan.

Troubleshooting

Notes

• Streaming and tool calling behave as documented in Chat completions.
• Keep the key server-side; never ship it in a browser bundle.