Frontly allows you to leverage AI in your apps, most commonly in AI requests within your live app workflows.
Each individual usage of AI within Frontly consumes a set number of AI tokens, as outlined in the chart below:
Usage Scenario | Token Cost |
AI Request Action | 1.0 |
AI Request Action (with your own API Key) | 0.05 |
AI Block Generation | 1.0 |
Each paid plan comes with a specific number of Monthly AI Tokens that measure your AI usage in the past 30 days. Usage is updated daily, so if you run out of tokens, you may only need to wait a few days rather than the entire month.
If you are regularly reaching your limit, you may need to upgrade to a higher-tier plan.
You can check your current usage level at the bottom of the Billing page:
Available AI Models
Currently we offer the following models and service providers:
OpenAI
OpenAI is one of the most popular AI model providers.
gpt-4o-mini
gpt-4o
o3-mini
Open Router
OpenRouter is a service enabling easy access to most popular AI models in a unified API. Frontly uses OpenRouter for the following AI models:
google/gemini-flash-1.5-8b
deepseek/deepseek-r1
anthropic/claude-3.5-sonnet
Decrease AI Cost by bringing your own API Keys
If you create a developer account at OpenAI or OpenRouter, you can obtain your own API Key for each service. If you add this to Frontly's Integrations settings, you will receive a large reduction in the amount of AI Tokens used when running AI actions in Frontly (as outlined in the chart at the top of the page).
To decrease the cost of OpenAI model requests, you must add an OpenAI API Key.
To decrease the cost of any other models such as Google, Deepseek or Anthropic models, you must add an OpenRouter API Key.
To purchase a higher AI token package, please contact our team directly at [email protected] or via live chat within the app.