Decision Models
Lumoz Decision
High-speed probabilistic decision model returning simplex-calibrated confidence scores across custom or preset rubrics at $0.035 / 1M tokens.
API Endpoint
POST https://lumozai.com/api/v4/run
Use this endpoint to run the model with your parameters. Authentication is required using your API key.
Sample Code (PHP cURL)
<?php
// API endpoint URL
$apiUrl = 'https://lumozai.com/api/v4/run';
// Your API key
$apiKey = 'YOUR_API_KEY';
// Model parameters
$params = [
'model_id' => 'lumoz-decision',
'prompt' => 'Customer account verified 3 years, requested withdrawal of $850 within daily limit of $2,000, 2FA passed, IP matches home device.',
'decision_mode' => 'approval',
'choices' => '',
'reasoning_depth' => 'fast',
];
// Initialize cURL session
$curl = curl_init();
// Set cURL options
curl_setopt_array($curl, [
CURLOPT_URL => $apiUrl,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POST => true,
CURLOPT_POSTFIELDS => $params,
CURLOPT_HTTPHEADER => [
'Accept: application/json',
'Authorization: Bearer ' . $apiKey
]
]);
// Execute the request
$response = curl_exec($curl);
$httpCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
// Check for errors
if (curl_errno($curl)) {
echo 'cURL Error: ' . curl_error($curl);
} else {
// Process the response
$result = json_decode($response, true);
if ($httpCode == 200 && isset($result['success']) && $result['success']) {
// Handle successful response
echo "Model output: ";
print_r($result['data']['output']);
} else {
// Handle error response
echo "Error: " . ($result['message'] ?? 'Unknown error');
}
}
// Close cURL session
curl_close($curl);
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| model_id | string | Required | The ID of the model to run (lumoz-decision) |
| api_key | string | Required | Your API key for authentication (sent via Bearer token in the Authorization header) |
| prompt | string | Required | Provide plain text or structured JSON state for calibrated probabilistic evaluation. |
| decision_mode | string | Optional | Select a built-in decision rubric or choose Custom Choices to define your own candidate labels. |
| choices | string | Optional | Comma-separated decision labels when using Custom Choices mode. |
| reasoning_depth | string | Optional | Select the Lumoz Decision evaluation depth and token rate ($0.035/1M for Fast, $0.055/1M for Balanced, $0.080/1M for Deep). |
Response Format
{
"success": true,
"data": {
"output": "This is the text output from the model based on your input parameters."
}
}
Model Pricing
Pay only for what you run. Charges are deducted directly from your account balance with zero recurring commitments.
Reasoning Depth & Token Tier Rates
Select a tier to estimate volume costs
Fast (Ultra-Low Latency — $0.035 / 1M tokens)
Default
$0.035 / 1M tokens
$0.000035 / 1K tokens
Balanced (Standard Calibrated — $0.055 / 1M tokens)
$0.055 / 1M tokens
$0.000055 / 1K tokens
Deep (Multi-Factor Analysis — $0.080 / 1M tokens)
$0.08 / 1M tokens
$0.00008 / 1K tokens
Cost Estimator
fast ($0.035/1M tok)
1,000 K tokens
Estimated Total
$0.03
Automatic instant refund if any run fails • Credits valid for 1 year