Overview API Reference Integrations

Integration Guides

Model Router is OpenAI-compatible. Any tool that lets you set a custom API base URL will work.

Cursor

In Cursor, go to Settings → Models → OpenAI API Key:

Set API Key to your mr_sk_... key.
Set Base URL to https://api.lxg2it.com/v1.
Add a model name — use economy (free) or any tier / model ID.
Select the model when starting a chat or using Cmd+K.

Windsurf

In Windsurf, go to Settings → LLM → Custom Provider:

Set Provider to OpenAI Compatible.
Set Base URL to https://api.lxg2it.com/v1.
Set API Key to your mr_sk_... key.
Set Model to a tier name or exact model ID.

RooCode / Cline

In VS Code, open RooCode settings → API Configuration:

Set API Provider to OpenAI Compatible.
Set Base URL to https://api.lxg2it.com/v1.
Set API Key to your mr_sk_... key.
Set Model ID to economy (free) or any tier / model ID.

OpenClaw

OpenClaw supports OpenAI-compatible providers. In your OpenClaw configuration (typically ~/.openclaw/config.yaml or via environment variables):

# Environment variables
export OPENAI_API_KEY="mr_sk_..."
export OPENAI_BASE_URL="https://api.lxg2it.com/v1"
export OPENAI_MODEL="economy"  # free models (Groq/Cerebras) — upgrade to standard/premium for GPT-4o, Claude, Gemini

Or in your config file:

# config.yaml
provider:
  type: openai
  api_key: mr_sk_...
  base_url: https://api.lxg2it.com/v1
  model: economy  # free models — upgrade to standard/premium as needed

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="mr_sk_...",
    base_url="https://api.lxg2it.com/v1",
)

response = client.chat.completions.create(
    model="economy",  # free models (no cost)
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Node.js (OpenAI SDK)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'mr_sk_...',
  baseURL: 'https://api.lxg2it.com/v1',
});

const response = await client.chat.completions.create({
  model: 'economy',  // free models (no cost)
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);

curl

curl https://api.lxg2it.com/v1/chat/completions \
  -H "Authorization: Bearer mr_sk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "economy",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Replace economy with standard or premium for higher-capability models, or pin a specific model ID.

General pattern

For any OpenAI-compatible tool or library:

Set the base URL to https://api.lxg2it.com/v1
Set the API key to your mr_sk_... key
Set the model to a tier name (economy, standard, premium) or an exact model ID from /v1/models

Need help with a specific tool? Contact support@api.lxg2it.com.