HomeDocumentation

Introduction

Menatic provides a unified Platform to access AI models. Backed by community and customer requests for additional model requests. Integration to your databases, datastores, Enterprise systems via MCP.

Air Gap Secure Data

When running your models on Menatic on Prem

50+ Models

Access GPT-4, Claude, Llama, and more

One API Key

Single key for all model providers

Quickstart

Get started with Menatic in under 5 minutes. Install our SDK and make your first API call.

1. Install the SDK

npm install @menatic/sdk

2. Initialize the client

import { Menatic } from '@menatic/sdk'

const menatic = new Menatic({
  apiKey: 'YOUR_API_KEY'
})

3. Make your first request

const response = await menatic.chat.completions.create({
  model: 'gpt-4-turbo',
  messages: [
    { role: 'user', content: 'Hello, how are you?' }
  ]
})

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

Authentication

All API requests require an API key. You can create and manage API keys in your dashboard.

Using your API key

Include your API key in the Authorization header:

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

Chat Completions

Create chat completions using any supported model. The API is compatible with the OpenAI format.

Request

const response = await menatic.chat.completions.create({
  model: 'claude-3-opus',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain quantum computing.' }
  ],
  temperature: 0.7,
  max_tokens: 1000
})

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1703654321,
  "model": "claude-3-opus",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing is..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Embeddings

Generate vector embeddings for text using models like text-embedding-3-large.

const embedding = await menatic.embeddings.create({
  model: 'text-embedding-3-large',
  input: 'The quick brown fox jumps over the lazy dog'
})

console.log(embedding.data[0].embedding) // [0.0023, -0.0045, ...]

Models

List available models and retrieve model information.

// List all available models
const models = await menatic.models.list()

// Get specific model info
const model = await menatic.models.retrieve('gpt-4-turbo')
console.log(model.context_length) // 128000

View all available models

Model Routing

Let Menatic automatically select the best model for your request based on cost, latency, and capability.

const response = await menatic.chat.completions.create({
  model: 'auto', // Menatic selects the best model
  messages: [
    { role: 'user', content: 'Write a haiku about coding' }
  ],
  routing: {
    optimize: 'cost', // 'cost' | 'latency' | 'quality'
    fallback: ['gpt-4-turbo', 'claude-3-opus']
  }
})

Streaming

Stream responses token by token for real-time user experiences.

const stream = await menatic.chat.completions.create({
  model: 'gpt-4-turbo',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '')
}

Function Calling

Enable models to call functions and interact with external tools.

const response = await menatic.chat.completions.create({
  model: 'gpt-4-turbo',
  messages: [{ role: 'user', content: 'What is the weather in Tokyo?' }],
  tools: [
    {
      type: 'function',
      function: {
        name: 'get_weather',
        description: 'Get current weather for a location',
        parameters: {
          type: 'object',
          properties: {
            location: { type: 'string', description: 'City name' }
          },
          required: ['location']
        }
      }
    }
  ]
})

API Keys

Manage your API keys securely. Never expose keys in client-side code.

Security Warning: Keep your API keys secure. Do not share them or expose them in browser code.

# Store your API key in environment variables
export MENATIC_API_KEY="mnt_sk_..."

Rate Limits

Rate limits vary by plan. Check response headers for your current usage.

Plan	Requests/min	Tokens/min
Developer	60	40,000
Pro	500	200,000
Enterprise	Unlimited	Custom

Rate limit headers

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 45
X-RateLimit-Reset: 1703654400

Questions?

Contact our team