Cost Python Packages

caliper-ai

Per-PR cost for your AI coding tools. Reads local Codex, Claude Code, Cursor, and Aider logs. Offline. No login. No SaaS. No telemetry.

git-fame

:star: Pretty-print `git` repository collaborators sorted by contributions

gammarer-aws-daily-cost-usage-reporter

This library deploys an AWS Cost and Usage reporter that runs daily and posts a cost summary to Slack.

llm-registry

A centralized registry for discovering and managing LLM model capabilities. Track model features, costs, and limitations across providers like OpenAI, Anthropic and other open source models. Supports both verified model definitions and user-managed entries with local storage.

gammarers-aws-daily-cost-usage-report-stack

This library deploys an AWS Cost and Usage reporter that runs daily and posts a cost summary to Slack.

llm-toll

A lightweight, drop-in Python decorator to track costs, monitor token usage, and enforce budget and rate limits for LLM API calls.

ccexplorer

Cost Explorer for Claude Code

cost-monitoring-construct

A CDK construct that helps track applications' costs separately and receive alerts in case of unpredicted resource usage

awscost

table console view cost of aws.

kicost-digikey-api-v3

KiCost plugin for the Digikey PartSearch API

parsimony-cli

Know where your Claude Code tokens go - usage tracking for subscribers

azurecost

Simple and easy command line to view azure costs.

trackly

Zero-overhead AI cost and usage tracking for Python. Import the library, wrap your LangChain model, and every LLM call is automatically logged - tokens, cost, latency, and your own metadata.

aws-finops-mcp-server

An MCP (Model Context Protocol) server that brings powerful AWS FinOps capabilities directly into your AI assistant. Analyze cloud costs, audit for waste, and get budget insights using natural language, all while keeping your credentials secure on your local machine.

paddlets

PaddleTS (Paddle Time Series Tool), PaddlePaddle-based Time Series Modeling in Python

stacksense

Open-source Python SDK that monitors every AI API call — tokens, cost, latency, errors. Drop it in. Zero config

tokonomix

Universal LLM token counting and cost management. Track, compare, and optimize your LLM API spending.

rtac

Realtime Algorithm Configuration Methods

tokenmeter

calculating and tracking token usage and costs across various llms