API Endpoints

Aqta provides OpenAI-compatible endpoints for seamless integration with existing applications.

---

Base URL

https://api.aqta.ai/v1

All endpoints are prefixed with /v1 for versioning.

---

Chat Completions

POST /v1/chat/completions

Create a chat completion with any supported model.

Supported Providers:

• OpenAI (GPT-4, GPT-3.5)
• Anthropic (Claude 3.5, Claude 3)
• Google (Gemini Pro, Gemini Ultra)
• Perplexity (Sonar, Sonar Pro)

Request

curl https://api.aqta.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorisation: Bearer sk-aqta-your-key-here" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is AI governance?"}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "AI governance refers to..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 100,
    "total_tokens": 120
  }
}

Parameters

Parameter	Type	Required	Description
model	string	Yes	Model to use (e.g., "gpt-4", "claude-3-5-sonnet")
messages	array	Yes	Array of message objects
temperature	number	No	Sampling temperature (0-2)
max_tokens	integer	No	Maximum tokens to generate
top_p	number	No	Nucleus sampling parameter
stream	boolean	No	Enable streaming responses

---

Streaming

POST /v1/chat/completions (Streaming)

Stream responses in real-time using Server-Sent Events (SSE).

Request

import openai

openai.api_base = "https://api.aqta.ai/v1"
openai.api_key = "sk-aqta-your-key-here"

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="")

Response (SSE)

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-4","choices":[{"index":0,"delta":{"content":"Once"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-4","choices":[{"index":0,"delta":{"content":" upon"},"finish_reason":null}]}

data: [DONE]

---

Models

GET /v1/models

List all available models.

Request

curl https://api.aqta.ai/v1/models \
  -H "Authorisation: Bearer sk-aqta-your-key-here"

Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1677610602,
      "owned_by": "openai",
      "provider": "openai"
    },
    {
      "id": "claude-3-5-sonnet-20241022",
      "object": "model",
      "created": 1677610602,
      "owned_by": "anthropic",
      "provider": "anthropic"
    }
  ]
}

---

Analytics

GET /v1/analytics/requests

Get analytics for your API requests.

Available in: Starter, Pro, Healthcare tiers

Request

curl https://api.aqta.ai/v1/analytics/requests \
  -H "Authorisation: Bearer sk-aqta-your-key-here" \
  -G \
  -d "start_date=2026-01-01" \
  -d "end_date=2026-01-31"

Response

{
  "total_requests": 1250,
  "total_cost": 45.67,
  "by_model": {
    "gpt-4": {
      "requests": 800,
      "cost": 38.50
    },
    "gpt-3.5-turbo": {
      "requests": 450,
      "cost": 7.17
    }
  },
  "by_date": [
    {
      "date": "2026-01-01",
      "requests": 50,
      "cost": 1.85
    }
  ]
}

---

Compliance

GET /v1/compliance/audit-trail

Get audit trail for compliance reporting.

Available in: Healthcare tier

Request

curl https://api.aqta.ai/v1/compliance/audit-trail \
  -H "Authorisation: Bearer sk-aqta-your-key-here" \
  -G \
  -d "start_date=2026-01-01" \
  -d "end_date=2026-01-31"

Response

{
  "audit_trail": [
    {
      "id": "req_123",
      "timestamp": "2026-01-15T10:30:00Z",
      "model": "gpt-4",
      "user_id": "user_456",
      "prompt_tokens": 20,
      "completion_tokens": 100,
      "cost": 0.0385,
      "metadata": {
        "patient_id": "redacted",
        "session_id": "sess_789"
      }
    }
  ]
}

---

Error Responses

All endpoints return standard error responses:

400 Bad Request

{
  "error": {
    "message": "Invalid request: missing 'model' parameter",
    "type": "invalid_request_error",
    "code": "missing_parameter"
  }
}

401 Unauthorised

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

429 Too Many Requests

{
  "error": {
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

500 Internal Server Error

{
  "error": {
    "message": "Internal server error",
    "type": "server_error",
    "code": "internal_error"
  }
}

---

Rate Limits

All endpoints are subject to rate limits based on your tier:

Tier	Rate Limit
Free	10 requests/min
Starter	100 requests/min
Pro	1,000 requests/min
Healthcare	1,000 requests/min

See Rate limits for details.

---

Next Steps

• Authentication - Get your API key
• Rate Limits - Understand rate limits
• Quick Start Guide - Get started in 5 minutes

---

Questions? Contact us at hello@aqta.ai