Monitor your project
What you can watch, and where
| You want to see | Console | API, with a virtual key |
|---|---|---|
| The spend of today, 7 or 30 days | Overview › Spent, Spend over time | GET /usage/me: the spend of this month |
| The spend of each app, key and model | Overview › Per-app burn, Per-key burn, Model split | GET /usage/me: by_model, by_task |
| The calls that failed, and why | Requests › What failed, Attempt log | — |
| The vendors that fail often | Requests › Who is unreliable, Model health | GET /status/peek: the state of each vendor |
| If the next call will be refused | — | GET /status/peek: tenant_capped |
| What to change to spend less | Improve › What to change | — |
The console pages are explained in Console screens.
Get an alert
Proxium sends an alert to Slack, Discord, Telegram or a webhook when the spend of the project or of one app passes a level. See Get spend alerts.
Watch the spend from your own system
To alert from your own system, read the spend on a schedule.
Example: a script that a scheduler runs each hour. It exits with an error when the spend of the month passes $50.
check-spend.sh
#!/bin/sh
used=$(curl -s https://proxium.tech/usage/me \
-H "Authorization: Bearer $PROXIUM_KEY" | jq '.credits.used_usd')
echo "Proxium spend this month: \$$used"
awk -v u="$used" 'BEGIN { exit (u > 50) ? 1 : 0 }'
To stop an app at a limit, do not wait for an alert. Set a limit, and Proxium refuses its calls above it. See Set budgets and limits.
What is not available yet
| Feature | State today |
|---|---|
| Spend alerts by email | Not available. Use Slack, Discord, Telegram or a webhook |
| Sending call records, logs or traces to your own tools | Not available. You read your traffic in the console |