Every time your AI coding agent starts a new task, Freestyle launches a dedicated VM for it. Helicone (a tool that tracks AI API usage and costs) logs how many tokens (units of AI processing) each agent uses. You see exactly what each task costs before your bill surprises you.
Set up Freestyle to tag each VM with a task ID when it launches
Route all AI model calls from your VMs through Helicone's proxy (a middleman that records traffic)
Add the task ID as a custom property in Helicone so costs group by task
Set up Helicone cost alerts to notify you when a single task exceeds your budget threshold
Review the Helicone dashboard weekly to spot which agent tasks cost the most
Create a free account to get the steps written out for your tools, click by click.
Create a free accountReduce unexpected AI infrastructure costs and spend less time on manual cost tracking.
Grab a 15-minute chat. We don't sell software, so we have no stake in which one you use.
Run this in your main platform instead? Check how it connects first: its API, native apps, Zapier or Make, and the plan each one needs.
Open the Integration CheckerWe build the missing piece next to the software you already run.
Get it built
