Free Daily Requests

Lunos offers free daily token requests for select AI models. This feature allows you to use certain models without incurring costs, up to a specified token limit each day. This guide explains how free daily requests work and how to make the most of them.

How It Works

Free daily requests allow you to use certain AI models up to a specified token limit each day without being charged. Here's how the feature works:

• Daily Reset: Your free token allowance resets every 24 hours at midnight UTC
• Token Counting: Both input and output tokens count toward your daily limit
• Automatic Tracking: The system automatically tracks your usage and applies the free allowance
• Seamless Transition: Once you exceed your free daily limit, requests will automatically be billed at the standard rate

Eligible Models

The following models currently offer free daily token allowances. The specific token limits may change over time as we adjust our offerings.

For the most up-to-date list of models with free daily tokens, visit the Models page and look for models with the 🎁 gift icon.

Using Free Daily Requests

Using models with free daily requests is no different from using any other model through the Lunos API. Simply specify the model in your API request as you normally would:

1import OpenAI from 'openai';
2
3const client = new OpenAI({
4  apiKey: 'your_api_key_here',
5  baseURL: 'https://api.lunos.tech/v1',
6});
7
8async function generateText() {
9  const completion = await client.chat.completions.create({
10    model: "gemma-3-12b", // Model with free daily tokens
11    messages: [
12      { role: "system", content: "You are a helpful assistant." },
13      { role: "user", content: "Tell me about free daily requests on Lunos." }
14    ],
15  });
16
17  console.log(completion.choices[0].message.content);
18}
19
20generateText();

Tracking Your Usage

You can monitor your free daily token usage in the Usage Statistics section of your dashboard. The dashboard provides:

• Current free token usage for each eligible model
• Remaining free tokens available for the day
• Historical usage patterns to help you optimize your requests

Best Practices

To make the most of your free daily tokens, consider these best practices:

• Optimize Prompts: Write clear, concise prompts to minimize token usage
• Set Maximum Tokens: Limit the maximum output tokens to prevent unexpectedly large responses
• Batch Requests: Combine related queries into a single request when possible
• Monitor Usage: Regularly check your usage statistics to avoid unexpected charges
• Test with Free Models: Use models with free tokens for development and testing before deploying with premium models

1// Example of setting maximum tokens to control usage
2const completion = await client.chat.completions.create({
3  model: "meta-llama/llama-4-scout",
4  messages: [
5    { role: "system", content: "You are a helpful assistant." },
6    { role: "user", content: "Summarize the concept of free daily tokens." }
7  ],
8  max_tokens: 100, // Limit the response to 100 tokens
9});

Frequently Asked Questions