Hi HN,
I just launched AI Cost Board, a small project I built to make multi-provider AI usage easier to operate in production.
It gives you a unified dashboard for:
total spend
token usage
request volume
latency and error rates
What it enables:
one proxy layer for multiple providers
request logs for debugging and visibility
budgets + alerts for cost control
workspace/project structure for teams
pricing + subscription flow for Free/Pro plans
The goal is simple: make AI costs and performance observable in real time, without stitching together multiple tools.
I’d really appreciate feedback on:
product usefulness
onboarding flow
pricing model
missing features you’d expect for production use
Thanks for checking it out.
We have found that the natural next step after tracking is automated routing. Once you see that 70% of your frontier model calls could have been handled by something much cheaper, you want a system that does that automatically.
At Komilion we route each API call to the cheapest model that fits based on benchmarks. The combination of monitoring (like this) + routing gives you both visibility and automatic savings.
One thing I would suggest adding: cost-per-quality metrics. Raw cost is not the full picture — $0.80/M tokens that fails 20% of the time is more expensive than $2/M tokens that works reliably.
reply