#cost

CloudMetric — Cost-as-you-type

cloudmetric

Real-time cloud and AI cost annotations inline in your editor

PromptRouter

madhavanand

Ultra-Intelligent, Cost-Slashing AI Prompt Router for VS Code Copilot Chat

Copilot Insights (Local)

RajatJaiswal

Automatically indexes your Copilot chat history into a private local SQLite database so you can search past sessions and analyze token usage and cost — all stored on your machine.

Claude & Copilot Token Optimizer

ai-token-optimizer

Automatically reduces token consumption for Claude Code, GitHub Copilot, and Codex by injecting optimized instructions, installing compression tools, and configuring MCP servers.

ClearBurn: LLM Token & Cost Estimator

artcllick-apps

See the token count and $ cost of any prompt or file before you call the API. Supports Claude, GPT, and Gemini pricing.

Copilot Inspector

SebastianGross

Deep visibility into GitHub Copilot prompt execution sessions — tools, files, commands, context, tokens, and estimated cost — in a local-first Activity Bar UI.

Agent Context Trail

VectorMind

See how one agent conversation's context evolves, prompt by prompt: tokens, cache reuse, and cost for Claude Code, Codex, and GitHub Copilot.

Tokoscope — LLM Token Optimizer

tokoscope

Audit, compress, and monitor LLM token usage directly in VS Code. See token counts, waste scores, and cost estimates as you write.

LLM Token Surgeon 🔪

ashishjsharda

Cut your LLM API bill by 30–70%. Inline token counts, one-click optimization, and savings projections.

Lens by corteX

questo

Lens observability for VS Code, Cursor, Windsurf and other VS Code-family editors. Ships token, cost, and tool-call telemetry into the Lens dashboard so teams see SavingsCounter, Brain Advisor whisper, and Claude-Code-in-terminal de-duplication in real time.

OpenRouter Insights

RLAlpha49

Display OpenRouter API pricing and track your OpenRouter account usage in VS Code

ACIL — AI Credit Intelligence Layer

imKrisK

Pre-execution LLM cost governor for VS Code. Predicts cost before tokens are spent, compresses prompts, routes to cheaper models, enforces budgets, and learns your session patterns. Patent Pending.