API Documentation - StudioAICore

Authentication

All API requests require authentication via a Bearer token in the Authorization header.

Authorization: Bearer YOUR_API_KEY

Generate your API key from the StudioAICore Dashboard (available after launch). Keep your key secure and never expose it in client-side code.

Chat API

Send messages and receive AI-generated responses.

Endpoint

POST https://api.studioaicore.com/v1/chat

Request Body

                            {
  "model": "studiocore-1",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "max_tokens": 1024,
  "temperature": 0.7
}
                        

Response

                            {
  "id": "chat-abc123",
  "object": "chat.completion",
  "created": 1709900000,
  "model": "studiocore-1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 256,
    "total_tokens": 270
  }
}
                        

Examples

cURL

                            curl -X POST https://api.studioaicore.com/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "studiocore-1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
                        

Python

                            import requests

response = requests.post(
    "https://api.studioaicore.com/v1/chat",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "studiocore-1",
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)

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

JavaScript

                            const response = await fetch('https://api.studioaicore.com/v1/chat', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'studiocore-1',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);
                        

Available Models

StudioAICore offers multiple models optimized for different use cases:

studiocore-1 — General-purpose model. Balanced performance and cost. Best for most use cases.
studiocore-1-turbo — Optimized for speed. Lower latency with slightly reduced accuracy. Great for real-time applications.
studiocore-1-pro — Maximum accuracy and reasoning. Higher cost per token. Ideal for complex analysis and code generation.

Rate Limits

Rate limits vary by plan:

Essentials: 30 requests/minute, 500K tokens/month
Professional: 120 requests/minute, 5M tokens/month
Enterprise: Custom limits based on agreement

Rate limit headers are included in every response:

                            X-RateLimit-Limit: 120
X-RateLimit-Remaining: 115
X-RateLimit-Reset: 1709900060
                        

Error Handling

The API uses standard HTTP status codes:

400 — Bad request. Check your request body.
401 — Unauthorized. Invalid or missing API key.
429 — Rate limit exceeded. Slow down requests.
500 — Server error. Retry with exponential backoff.

                            {
  "error": {
    "type": "rate_limit_exceeded",
    "message": "You've exceeded your rate limit. Please wait before retrying.",
    "code": 429
  }
}
                        

Official SDKs

We're building official SDKs for popular languages. All are coming soon:

🐍

Python

Coming Soon

✍

JavaScript

Coming Soon

🐜

PHP

Coming Soon