Getting Started

Prerequisites

Before you begin, make sure you have the following ready:

• A SIMOSphere AI account — register at onboarding.simosphereai.com
• An active subscription plan (Personal tier or above)
• A terminal with curl installed, or any HTTP client of your choice

Step 1: Create an API Key

After logging into the SIMOSphere AI dashboard at app.simosphereai.com, navigate to Settings → API Keys and click Create New Key. Give the key a descriptive name (e.g., “Development” or “Production Backend”) and select the appropriate permission scope.

Your API key will be displayed exactly once. Copy it immediately and store it in a secure location such as an environment variable or a secrets manager. API keys follow the format sk_live_... for production and sk_test_... for sandbox environments.

Step 2: Send Your First Request

The SIMOSphere AI API is fully OpenAI-compatible. You can use any existing OpenAI client library or a simple HTTP request. Replace sk_live_YOUR_API_KEY with your actual key:

curl -X POST https://api.simosphereai.com/v1/chat/completions \
  -H "Authorization: Bearer sk_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-small-latest",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is data sovereignty?"}
    ],
    "temperature": 0.7,
    "max_tokens": 512
  }'

The response follows the standard OpenAI chat completions format. You will receive a JSON object containing the model's response in choices[0].message.content, along with token usage statistics in the usage field.

Step 3: Use an SDK

Since the API is OpenAI-compatible, you can use the official OpenAI SDKs directly. Simply point the base URL to https://api.simosphereai.com/v1 and provide your SIMOSphere AI key:

TypeScript / Node.js

import OpenAI from "openai";

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

const completion = await client.chat.completions.create({
  model: "mistral-small-latest",
  messages: [
    { role: "user", content: "Explain GDPR Article 25." },
  ],
});

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

Python

from openai import OpenAI

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

response = client.chat.completions.create(
    model="mistral-small-latest",
    messages=[
        {"role": "user", "content": "Explain GDPR Article 25."},
    ],
)

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

Step 4: Connect the MCP Server

The SIMOSphere AI MCP (Model Context Protocol) server enables AI agents to interact with the platform programmatically. It provides tools for model selection, completion requests, and usage monitoring — all accessible through the standardized MCP transport layer.

{
  "mcpServers": {
    "simosphere": {
      "command": "npx",
      "args": ["@simosphere/mcp-server"],
      "env": {
        "SIMOSPHERE_API_KEY": "sk_live_YOUR_API_KEY"
      }
    }
  }
}

Add this configuration to your MCP client settings (e.g., claude_desktop_config.json or your IDE's MCP configuration file). The server will automatically authenticate using the provided API key and expose all available tools.

Step 5: List Available Models

You can query the models endpoint to see which models are currently available on your plan. The response includes model IDs, context window sizes, and pricing information:

curl https://api.simosphereai.com/v1/models \
  -H "Authorization: Bearer sk_live_YOUR_API_KEY"

Use the id field from the response as the model parameter in your completion requests. Models are updated regularly — check this endpoint to discover newly available models.

Next Steps