API Documentation

1. Introduction

This documentation describes the technical specification and usage of the Logicc AI API.

The API provides a central and unified access point (endpoint) to a variety of leading language models (LLMs). All requests are handled through a single OpenAI-compatible v1/chat/completions endpoint.

This approach significantly reduces implementation complexity because developers can use models from different providers, including OpenAI, Google, Anthropic, and Mistral, through a consistent and standardized API structure without having to develop a separate integration for each model.

2. Authentication

An API key is required to use the Logicc AI API.

Obtaining the API key:
A personal API key is issued by customer support to customers with an active subscription.

Using the API key:
The API key must be sent as a Bearer token in the Authorization header with every request.

Header example:Authorization: Bearer YOUR_LOGICC_API_KEY

Replace YOUR_LOGICC_API_KEY with your provided key.

---

3. Endpoint: Chat completion

The primary endpoint is used to generate text responses and is fully compatible with the OpenAI Chat Completions API standard.

POST https://api.logicc.io/v1/chat/completions

Headers:

• Content-Type: application/json
• Authorization: Bearer YOUR_LOGICC_API_KEY

4. Request body

The body of the POST request must be a JSON object containing the following parameters:

Example for messages:

"messages": [
  {
    "role": "system",
    "content": "You are a helpful assistant for technical questions."
  },
  {
    "role": "user",
    "content": "Explain the difference between `REST` and `GraphQL`."
  }
]

---

4a. Endpoint: Models (/models)

This endpoint provides an overview of all models enabled for the respective account. The response follows the OpenAI schema for GET /v1/models.

Method: GET

Path: /models

Headers:

• Authorization: Bearer YOUR_LOGICC_API_KEY

Description:

• Returns only the models enabled for the respective customer.
• Suitable for filling UI dropdowns or validating model IDs server-side.

Example response:

{
  "data": [
    {
      "id": "gpt-5-nano",
      "object": "model",
      "created": 1677610602,
      "owned_by": "openai"
    },
    {
      "id": "o3-mini",
      "object": "model",
      "created": 1677610602,
      "owned_by": "openai"
    },
    ...
  ],
  "object": "list"
}

cURL

curl -X GET \
  -H "Authorization: Bearer YOUR_LOGICC_API_KEY" \
  https://api.logicc.io/v1/models

---

5. Available models / price list

The following model identifiers can be specified in the model parameter:
Additional models on request.

---

6. Response object

A successful request returns a JSON object with the following structure:

---

7. Code examples

cURL

curl <https://api.logicc.io/v1/chat/completions> \\
  -H "Content-Type: application/json" \\
  -H "Authorization: Bearer YOUR_LOGICC_API_KEY" \\
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [
      {
        "role": "user",
        "content": "What is Earth's escape velocity in km/h?"
      }
    ]
  }'

Python (with requests)

import requests
import json

api_key = "YOUR_LOGICC_API_KEY"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {api_key}"
}

data = {
    "model": "claude-3-7-sonnet",
    "messages": [
        {"role": "user", "content": "Write a Python function that finds prime numbers."}
    ]
}

try:
    response = requests.post("<https://api.logicc.io/v1/chat/completions>", headers=headers, data=json.dumps(data))
    response.raise_for_status() # Raises an HTTPError for bad responses (4xx or 5xx)

    result = response.json()
    print(result['choices'][0]['message']['content'])
except requests.exceptions.RequestException as e:
    print(f"An error occurred: {e}")
    if hasattr(e, 'response') and e.response is not None:
        print(f"Response from server: {e.response.text}")

Node.js (with axios)

const axios = require('axios');

const apiKey = 'YOUR_LOGICC_API_KEY';
const url = '<https://api.logicc.io/v1/chat/completions>';

const data = {
  model: 'gpt-4o',
  messages: [
    { role: 'user', content: 'How does a neural network work? Explain it for a beginner.' }
  ]
};

const headers = {
  'Content-Type': 'application/json',
  'Authorization': `Bearer ${apiKey}`
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.data.choices[0].message.content);
  })
  .catch(error => {
    console.error('Error during API request:', error.response ? error.response.data : error.message);
  });