LangMart API Reference

API Base URL: https://api.langmart.ai

LangMart provides a unified API for accessing AI models from multiple providers. The API is designed to be OpenAI-compatible, making it easy to integrate with existing applications.

Quick Links

API Overview

OpenAI-Compatible Endpoints (/v1/*)

These endpoints follow the OpenAI API specification, making LangMart a drop-in replacement for OpenAI:

User API Endpoints (/api/*)

Manage your account, view analytics, and configure settings:

Public Endpoints (/api/public/*)

No authentication required:

Authentication

All API requests (except public endpoints) require authentication using an API key:

curl https://api.langmart.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Getting an API Key

1. Log in to https://langmart.ai
2. Go to Settings
3. Create a new API key
4. Copy and store the key securely (it won't be shown again)

See Authentication for more details.

Quick Start

1. Make Your First Request

curl 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, how are you?"}
    ]
  }'

2. Using with OpenAI SDK

from openai import OpenAI

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

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

3. Multi-Provider Access

Use models from any provider with the same API:

# OpenAI
response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)

# Anthropic
response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet-20241022",
    messages=[{"role": "user", "content": "Hello"}]
)

# Groq (ultra-fast)
response = client.chat.completions.create(
    model="groq/llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Hello"}]
)

Model Naming Convention

LangMart uses a provider/model naming convention:

Response Format

Success Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "openai/gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}

Error Response

{
  "error": {
    "type": "authentication_error",
    "code": "invalid_api_key",
    "message": "Invalid API key provided",
    "details": {}
  }
}

Rate Limiting

API requests are rate limited based on your account tier:

Rate limit headers are included in responses:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 55
X-RateLimit-Reset: 1704067260

Pagination

List endpoints support pagination:

GET /api/models?limit=50&offset=0

Response includes pagination info:

{
  "data": [...],
  "pagination": {
    "total": 150,
    "limit": 50,
    "offset": 0,
    "hasMore": true
  }
}

Streaming

Chat completions support streaming via Server-Sent Events (SSE):

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Stream events:

data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"Hello"}}]}
data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"!"}}]}
data: [DONE]

SDK Support

LangMart works with any OpenAI-compatible SDK:

Platform Links

Next Steps

• OpenAI-Compatible API - Full /v1 API reference
• Authentication - API keys and auth methods
• Models - Browse available models
• Errors - Error handling guide