LLM

Lumoz LLM

Lumoz LLM is our flagship multimodal intelligence model combining frontier language reasoning with high-resolution visual comprehension and OpenAI-compatible API access.

$0.002/run Popular New 217 runs

Input Parameters

Configure model parameters and run inference.

Prompt * The message, conversation query, or instruction for Lumoz LLM.

Reference Images Optional reference image(s) for visual reasoning, OCR, inspection, or multimodal question-answering.

System Prompt Custom developer instructions to guide how Lumoz LLM responds.

Temperature Controls response randomness (0.0 for deterministic/factual, 1.0 for creative).

0.7

0 1.5

Max Tokens Maximum generation length in completion tokens.

Free account • Test credits included • Sign up

Generation time: 0s

Your result will appear here

Configure parameters and press Run, or press Ctrl - ↵ Enter.

Run the model to see raw JSON response

OpenAI-Compatible Chat Completions

Use lumoz-llm as a direct drop-in replacement with the official OpenAI SDKs or any compatible client. Point your client's baseURL to Lumoz, pass your Lumoz API key, and specify model lumoz-llm. Supports streaming (SSE) and multimodal vision.

Base URL

https://lumozai.com/v1

Chat Completions Endpoint

POST https://lumozai.com/v1/chat/completions

Streaming SSE Supported Multimodal Vision (image_url) Standard OpenAI SDK Drop-in Token Billing ($0.002 / 1K tokens)

Code Examples

from openai import OpenAI

# Initialize the OpenAI client pointing to Lumoz
client = OpenAI(
    base_url="https://lumozai.com/v1",
    api_key="YOUR_LUMOZ_API_KEY",
)

# Text chat completion with streaming
response = client.chat.completions.create(
    model="lumoz-llm",
    messages=[
        {"role": "system", "content": "You are a helpful and intelligent assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.7,
    stream=True,
)

for chunk in response:
    content = chunk.choices[0].delta.content or ""
    print(content, end="", flush=True)
print()

import OpenAI from "openai";

// Initialize OpenAI client pointing to Lumoz
const client = new OpenAI({
  baseURL: "https://lumozai.com/v1",
  apiKey: "YOUR_LUMOZ_API_KEY",
});

async function main() {
  const stream = await client.chat.completions.create({
    model: "lumoz-llm",
    messages: [
      { role: "system", content: "You are a helpful and intelligent assistant." },
      { role: "user", content: "Explain quantum computing in simple terms." }
    ],
    temperature: 0.7,
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || "");
  }
}

main();

curl https://lumozai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_LUMOZ_API_KEY" \
  -d '{
    "model": "lumoz-llm",
    "messages": [
      {"role": "system", "content": "You are a helpful and intelligent assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "stream": false
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://lumozai.com/v1",
    api_key="YOUR_LUMOZ_API_KEY",
)

# Multimodal perception: Pass any image URL alongside your question
response = client.chat.completions.create(
    model="lumoz-llm",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe the scene, architecture, and lighting in this image."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/scene.jpg"
                    }
                }
            ]
        }
    ],
    temperature=0.7,
)

print(response.choices[0].message.content)

Request Parameters (OpenAI Schema)

Parameter	Type	Required	Description
model	string	Required	The model ID to run (`lumoz-llm`).
messages	array	Required	Array of message objects (`role`: system/user/assistant, `content`: string or multimodal array with `text` and `image_url`).
stream	boolean	Optional	If set to `true`, partial message deltas will be sent as Server-Sent Events (SSE). Defaults to `false`.
temperature	number	Optional	Sampling temperature between 0.0 and 2.0. Higher values make output more creative, lower values more deterministic. Defaults to `0.7`.
max_tokens	integer	Optional	The maximum number of tokens to generate in the chat completion.

Sample Response (JSON)

{
  "id": "chatcmpl-a8c7b9e1",
  "object": "chat.completion",
  "created": 1728640000,
  "model": "lumoz-llm",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing is a rapidly-emerging technology that harnesses the laws of quantum mechanics to solve problems too complex for classical computers."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 22,
    "completion_tokens": 27,
    "total_tokens": 49
  }
}

Lumoz Native Unified API

POST https://lumozai.com/api/v4/run

Use the standard Lumoz unified endpoint to run this model alongside all other models in your account. Authentication is via your Bearer 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-llm',
    'prompt' => '',
    'images[]' => 'https://example.com/image.jpg', // Example image URL
    'system_prompt' => '',
    'temperature' => 0.7,
    'max_tokens' => 2048,
];

// Initialize cURL session
$curl = curl_init();

// Set cURL options
curl_setopt_array($curl, [
    CURLOPT_URL => $apiUrl,
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_POSTFIELDS => json_encode($params),
    CURLOPT_HTTPHEADER => [
        'Content-Type: application/json',
        '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-llm)
api_key	string	Required	Your API key for authentication (sent via Bearer token in the Authorization header)
prompt	string	Required	The message, conversation query, or instruction for Lumoz LLM.
images	array	Optional	Optional reference image(s) for visual reasoning, OCR, inspection, or multimodal question-answering.
system_prompt	string	Optional	Custom developer instructions to guide how Lumoz LLM responds.
temperature	number	Optional	Controls response randomness (0.0 for deterministic/factual, 1.0 for creative).
max_tokens	array	Optional	Maximum generation length in completion tokens.

Response Format

{
  "success": true,
  "data": {
    "output": "Quantum computing is a rapidly-emerging technology that harnesses the laws of quantum mechanics to solve problems too complex for classical computers.",
    "usage": {
      "prompt_tokens": 22,
      "completion_tokens": 27,
      "total_tokens": 49
    }
  }
}

Model Pricing

Pay only for what you run. Charges are deducted directly from your account balance with zero recurring commitments.

Rate per 1K tokens

$ 0.002 / 1K tokens

$2.00 per 1,000,000 tokens

Cost Estimator

1,000 K tokens

Estimated Total $2.00

Add Balance

Automatic instant refund if any run fails • Credits never expire