Quick Start Guide

Get started with LangMart in just a few minutes. This guide walks you through signing up, getting your API key, and making your first API call.

Step 1: Sign Up or Sign In

Option A: OAuth Login (Recommended)

The fastest way to get started is with Google or GitHub:

1. Go to https://langmart.ai
2. Click Sign in with Google or Sign in with GitHub
3. Authorize LangMart to access your account
4. You're in! You'll be redirected to the dashboard.

Option B: Guest Access

Want to try LangMart without creating an account?

1. Go to https://langmart.ai
2. Click Continue as Guest
3. A temporary guest session will be created automatically

Note: Guest sessions have limited features. Sign up with OAuth to save your work and access all features.

Step 2: Get Your API Key

Once logged in, you need an API key to make API calls:

1. Go to Settings in the sidebar (or click your profile icon)
2. Navigate to the API Keys tab
3. Click Create New Key
4. Give your key a descriptive name (e.g., "Development", "Production")
5. Copy your key immediately - it won't be shown again!

Your API key looks like: sk-langmart-xxxxxxxxxxxxxxxx

Security: Treat your API key like a password. Never commit it to source control or share it publicly.

Step 3: Make Your First API Call

LangMart provides an OpenAI-compatible API. You can use it with any OpenAI client library or make direct HTTP requests.

Using cURL

curl -X POST https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "groq/llama-3.3-70b-versatile",
    "messages": [
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

Using Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.langmart.ai/v1"
)

response = client.chat.completions.create(
    model="groq/llama-3.3-70b-versatile",
    messages=[
        {"role": "user", "content": "Hello! What can you do?"}
    ]
)

print(response.choices[0].message.content)

Using JavaScript/TypeScript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.langmart.ai/v1',
});

const response = await openai.chat.completions.create({
  model: 'groq/llama-3.3-70b-versatile',
  messages: [
    { role: 'user', content: 'Hello! What can you do?' }
  ],
});

console.log(response.choices[0].message.content);

Model Name Format

LangMart uses the format provider/model-name for model selection:

Browse all available models on the Models page in the dashboard.

Step 4: Use the Chat Interface

Don't want to write code? Use the built-in chat interface:

1. Click Chat in the sidebar
2. Select a model from the dropdown
3. Type your message and press Enter
4. View the response with token usage and timing

Chat Features

• Model Selection - Switch between any available model
• System Prompts - Set custom system instructions
• Conversation History - Maintain multi-turn conversations
• Token Count - See input/output token usage
• Response Time - Track latency for each response
• Export - Export conversations for later reference

Step 5: Explore the Dashboard

Now that you're set up, explore these key sections:

What's Next?

• Add Custom Connections - Use your own provider API keys
• Set Up Alerts - Get notified about usage thresholds
• Invite Team Members - Collaborate with your team
• Explore Automation - Build automated workflows

Troubleshooting

"Invalid API key" Error

• Make sure you copied the full API key including the sk-langmart- prefix
• Check that you're using the correct header format: Authorization: Bearer YOUR_KEY

"Model not found" Error

• Verify the model name follows the provider/model-name format
• Check the Models page to ensure the model is available

Rate Limit Errors

• LangMart automatically retries on rate limits with appropriate backoff
• If you see persistent rate limits, your provider API key may have reached its quota

Connection Timeout

• Check your network connection
• Verify the API endpoint: https://api.langmart.ai
• For longer responses, ensure your client has adequate timeout settings

Need more help? Check the Troubleshooting Guide or contact support.