Show HN: Frugal Tokens – explore costs and usage across coding agents
Sentiment Mix
Geography
Expert Signals
dpc94
author • 1 mention
Hacker News
source • 1 mention
AI-Generated Claims
Generated from linked receipts; click sources for full context.
I originally built it because I was curious to see how much all of my sessions cost and how much cache misses affected that spend.
Supported by 1 story
I'd noticed people had widely different spend profiles and wanted to better understand what might contribute to that.As I've worked on this, the tool has grown to show more usage patterns across all of your sessions.
Supported by 1 story
It shows overall usage, estimated working time and overlapping sessions, and where your spend is coming from across models and cache misses.
Supported by 1 story
I also have a few session level metrics with percentile breakdowns, along with a list of your sessions and high level info.Clicking into a session opens an explorer where you can see individual model calls and tool inputs and outputs.
Supported by 1 story
There's also a rough cost comparison that shows what the recorded session would have cost with another model's pricing, or for Anthropic, with 5m...
Supported by 1 story
Paper to Product Links
Related Events
I use Claude Code without paying a dime to Anthropic - makeuseof.com
LLMs • 8/20/2026
Claude AI E-Degree Bundle: $20 for Lifetime Access - The Inventory
LLMs • 8/20/2026
Claude, ChatGPT, Gemini, and more are all included in this lifetime subscription, now just $99.99 - Mashable
LLMs • 8/19/2026
Lifetime access to Claude, GPT, and dozens of other AI models is only $60 this week - KING5.com
LLMs • 8/19/2026
OpenAI’s Latest Bid to Fight Anthropic: A Promise Not to Keep Customer Data - WSJ
LLMs • 8/19/2026
Causality Chain
Preceded By