API Reference

Complete reference for the ConfigureMyAI API endpoints. All endpoints use JSON for request and response bodies.

Base URL

https://configuremyai.com/api/v1

Authentication

All API requests require a valid endpoint token in the Authorization header: 

Authorization: Bearer cmai_your_token_here

Chat Completions

Create a chat completion using your configured AI.

Endpoint

POST /api/v1/[endpoint-path]

Headers

Header Required Description
Content-Type Yes Must be application/json
Authorization If required Bearer token for authentication

Request Body

{
  "messages": [
    {
      "role": "user",
      "content": "Your message here"
    }
  ]
}

Parameters

Parameter Type Required Description
messages array Yes Array of message objects
messages[].role string Yes "user" or "assistant"
messages[].content string Yes The message text

Response

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "object": "chat.completion",
  "created": 1702483200,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 12,
    "total_tokens": 27
  }
}

Response Fields

Field Type Description
id string Unique identifier for the completion
object string Always "chat.completion"
created integer Unix timestamp
model string Model used for completion
choices array Array of completion choices
usage object Token usage information

Error Responses

All errors return a JSON object with an error field:

{
  "error": {
    "message": "Human-readable error description",
    "type": "error_type"
  }
}

Error Types

HTTP Code Type Description
400 invalid_request_error Invalid request format or parameters
401 authentication_error Invalid or missing authentication token
404 not_found_error Endpoint not found or inactive
429 rate_limit_error Rate limit exceeded
500 api_error Internal server or AI provider error

Code Examples

cURL

curl -X POST https://configuremyai.com/api/v1/your-endpoint \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cmai_your_token" \
  -d '{
    "messages": [
      {"role": "user", "content": "What can you help me with?"}
    ]
  }'

JavaScript (Fetch)

const response = await fetch('https://configuremyai.com/api/v1/your-endpoint', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer cmai_your_token'
  },
  body: JSON.stringify({
    messages: [
      { role: 'user', content: 'What can you help me with?' }
    ]
  })
});

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

Python (requests)

import requests

response = requests.post(
    'https://configuremyai.com/api/v1/your-endpoint',
    headers={
        'Content-Type': 'application/json',
        'Authorization': 'Bearer cmai_your_token'
    },
    json={
        'messages': [
            {'role': 'user', 'content': 'What can you help me with?'}
        ]
    }
)

data = response.json()
print(data['choices'][0]['message']['content'])

Ruby

require 'net/http'
require 'json'

uri = URI('https://configuremyai.com/api/v1/your-endpoint')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Content-Type'] = 'application/json'
request['Authorization'] = 'Bearer cmai_your_token'
request.body = {
  messages: [
    { role: 'user', content: 'What can you help me with?' }
  ]
}.to_json

response = http.request(request)
data = JSON.parse(response.body)
puts data['choices'][0]['message']['content']

Rate Limits

Rate limits can be set at two levels:

  1. Endpoint level: Total requests allowed for all tokens
  2. Token level: Requests allowed for a specific token

When a rate limit is exceeded, the API returns a 429 status code with a rate_limit_error type.

Best Practices

  1. Handle errors gracefully
    Always check for error responses and handle them appropriately.
  2. Implement retries with backoff
    For 429 and 500 errors, implement exponential backoff.
  3. Store conversation history
    Include previous messages for context-aware responses.
  4. Monitor token usage
    Track usage to manage costs and stay within limits.