Dashboard

The console home page gives an at-a-glance view of account usage and platform status, split into Overview and Model Call Analysis.

Overview

Usage overview

Monitors balance, usage, and request volume:

Card	Meaning
Last 24h spend	Amount consumed in the past 24 hours (USD)
Historical usage	Cumulative total spend (USD)
Request count	Total API requests to date

Remaining balance

The right-hand card shows your current balance and health:

• Remaining balance — available balance (USD) with a status badge (normal / low)
• Last 24h spend — mirrors the left card
• Estimated runway — how long the balance lasts at the recent burn rate; shows "no usage yet" without history
• Wallet — one-click jump to top-up

API info

Configured API routes and latency checks. Shows "no API routes configured" until set up.

Announcements

Latest platform updates and notices, newest first.

Uptime

Grouped monitor status from Uptime Kuma, reflecting upstream channel availability. Shows "no uptime monitors configured" until set up.

FAQ

Quick access to access & billing Q&A — see FAQ.

Model Call Analysis

Per-model usage analysis. Top-right corner offers Preferences and Filters (time range, model, etc.).

Stat cards

Metric	Meaning
Total count	Call count in the selected window
Total spend	Amount consumed in the window (USD)
Total tokens	Token volume in the window
Avg RPM	Requests per minute
Avg TPM	Tokens per minute

Spend distribution

Per-model spend breakdown with a bar / area chart toggle — spot cost drivers quickly.

Call analysis

Three switchable views:

• Call trend — call volume over time
• Call distribution — share of calls per model
• Call ranking — models ranked by call count