Does this skill support different LLM providers?

Yes, the usage handler captures model and provider metadata, allowing you to apply specific pricing for OpenAI, Anthropic, and other LLM providers supported by Convex Agents.

Does it handle monthly billing cycles?

Yes, it provides logic for monthly rollups and uses Convex Cron jobs to automatically generate invoices on a specific day each month.

How is the cost of LLM calls calculated?

Costs are calculated within a Convex mutation by multiplying the input and output token counts by the current rates provided by your specific LLM model provider.

Can I set up automatic spend alerts?

Yes, the skill includes implementation patterns for checking daily usage against predefined thresholds and triggering alerts via email or Slack when spending limits are exceeded.

Convex Agent Usage & Billing Tracker

Name: Convex Agent Usage & Billing Tracker
Author: Microck

byMicrock

•

Analíticas y Monitorización

Monitors LLM token consumption and manages automated billing for Convex-based AI agents.

Acerca de

This skill provides a robust framework for tracking LLM token usage and calculating real-time costs within Convex applications. It enables developers to log precise input and output metrics, attribute usage to specific users or agents, and automate the generation of monthly invoices. With built-in support for usage analytics, cost trend monitoring, and high-spend alerting, it is an essential tool for scaling production AI applications while maintaining strict control over API overhead and billing accuracy.

Características Principales

Real-time cost calculation based on provider-specific pricing
Detailed usage analytics by user, agent, and team
Automated monthly invoice generation and billing cycle management
Proactive high-usage alerts and spend monitoring systems
Automated LLM token consumption logging and attribution
81 GitHub stars

Casos de Uso

Building administrative dashboards to visualize AI resource consumption
Monitoring and optimizing multi-model API spend across development teams
Implementing a per-token usage-based billing model for AI SaaS products

Acerca de

Características Principales

Real-time cost calculation based on provider-specific pricing
Detailed usage analytics by user, agent, and team
Automated monthly invoice generation and billing cycle management
Proactive high-usage alerts and spend monitoring systems
Automated LLM token consumption logging and attribution
81 GitHub stars

Casos de Uso

Building administrative dashboards to visualize AI resource consumption
Monitoring and optimizing multi-model API spend across development teams
Implementing a per-token usage-based billing model for AI SaaS products