API Reference

Complete API documentation for Aqta.

Base URLs

• Production: https://api.aqta.ai
• Staging: https://staging-api.aqta.ai
• Local: http://localhost:8000

Authentication

All API requests require an API key in the Authorisation header:

Authorisation: Bearer sk-aqta-YOUR_KEY_HERE

Get your API key from the dashboard: Settings → API Keys

See Authentication guide for detailed authentication.

OpenAI-Compatible Endpoints

Chat Completions

OpenAI-compatible chat endpoint

POST /v1/chat/completions

Supports streaming, multiple providers (OpenAI, Anthropic, Google, Perplexity).

Models

List available models

GET /v1/models

Aqta-Specific Endpoints

Authentication

User authentication and session management

POST /api/auth/login          # Email/password login
POST /api/auth/signup         # Email/password signup
POST /api/auth/oauth-signin   # OAuth signup (Google, Microsoft)
POST /api/auth/logout         # Logout
GET  /api/auth/me             # Get current user

API Keys

API key management

GET    /api/keys              # List API keys
POST   /api/keys              # Create new API key
DELETE /api/keys/{key_id}     # Delete API key

Analytics

Request history and analytics (Starter tier and above)

GET /api/analytics/requests   # Get request analytics
GET /api/analytics/costs      # Get cost analytics

Compliance

Compliance and audit trail (Healthcare tier)

GET  /api/compliance/audit-trail      # Get audit trail
GET  /api/compliance/bias-detection   # Get bias detection results
POST /api/compliance/report           # Generate compliance report

Healthcare

Medical receipt management (Healthcare tier)

GET    /api/health/receipts           # List receipts
GET    /api/health/receipts/{id}      # Get receipt details
POST   /api/health/receipts/{id}/verify  # Verify receipt
GET    /api/health/receipts/export    # Export receipts

Response Format

Success Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 8,
    "total_tokens": 18
  },
  "aqta": {
    "cost_eur": 0.00001,
    "provider": "openai",
    "cached": false,
    "loop_detected": false
  }
}

Error Response

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

Error Codes

Code	Status	Description
invalid_api_key	401	API key is invalid or expired
rate_limit_exceeded	429	Too many requests
quota_exceeded	402	Monthly quota reached
loop_detected	429	Infinite loop detected
provider_error	502	Upstream provider error
invalid_request	400	Malformed request

Rate Limits

Tier	Requests/Month	Rate Limit	Models	Price
Free	500	5/min	GPT-3.5 only	€0
Starter	100,000	100/min	All models	€49
Pro	1,000,000	1,000/min	All models	€149
Healthcare	1,000,000	1,000/min	All models	€999

See Rate limits for detailed rate limit documentation.

SDKs

Official SDKs

• Python SDK: pip install aqta (coming soon)
• JavaScript SDK: npm install aqta (coming soon)

Using OpenAI SDKs

Aqta is compatible with OpenAI SDKs. Simply change the base URL:

Python:

import openai

openai.api_base = "https://api.aqta.ai/v1"
openai.api_key = "sk-aqta-YOUR_KEY"

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

JavaScript:

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://api.aqta.ai/v1',
  apiKey: 'sk-aqta-YOUR_KEY',
});

const response = await openai.chat.completions.create({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }],
});

Examples

cURL

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

Python with Streaming

import openai

openai.api_base = "https://api.aqta.ai/v1"
openai.api_key = "sk-aqta-YOUR_KEY"

response = openai.ChatCompletion.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.get("content"):
        print(chunk.choices[0].delta.content, end="")

JavaScript with Error Handling

try {
  const response = await fetch('https://api.aqta.ai/v1/chat/completions', {
    method: 'POST',
    headers: {
      'Authorisation': 'Bearer sk-aqta-YOUR_KEY',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      model: 'gpt-4',
      messages: [{role: 'user', content: 'Hello!'}]
    })
  });

  if (!response.ok) {
    const error = await response.json();
    console.error('API Error:', error.error.message);
    return;
  }

  const data = await response.json();
  console.log(data.choices[0].message.content);
} catch (error) {
  console.error('Network Error:', error);
}

Features by Tier

Free (€0/month)

• ✅ 500 requests/month
• ✅ GPT-3.5 & cheap models only
• ✅ Loop detection
• ✅ Basic monitoring
• ✅ 5 requests/minute
• ❌ GPT-4 or expensive models
• ❌ Analytics
• ❌ Compliance features

Starter (€49/month)

• ✅ 100,000 requests/month
• ✅ All models (GPT-4, Claude 3.5, etc.)
• ✅ Loop detection
• ✅ Cost tracking
• ✅ Analytics dashboard
• ✅ Email support
• ❌ Compliance features

Pro (€149/month)

• ✅ 1,000,000 requests/month
• ✅ All models
• ✅ Advanced analytics
• ✅ Priority support
• ✅ Custom rate limits
• ❌ Healthcare compliance

Healthcare (€999/month)

• ✅ 1,000,000 requests/month
• ✅ All models
• ✅ HIPAA-ready audit trail
• ✅ Bias detection
• ✅ Compliance reporting
• ✅ Dedicated support
• ✅ SLA guarantee

Webhooks

Coming soon: Real-time notifications for events like:

• Loop detection
• Budget alerts
• High-risk healthcare decisions
• Compliance violations

Support

• Documentation: Authentication | Endpoints | Rate Limits
• Email: hello@aqta.ai
• Dashboard: app.aqta.ai

---

Questions? Contact us at hello@aqta.ai