LLM Cost Tracking LLM Tools
Tools for monitoring, metering, and enforcing costs and token budgets across LLM API calls and agents. Includes cost estimation, usage tracking, quota management, and billing alerts. Does NOT include general observability/monitoring, analytics platforms, or token counting utilities without cost tracking features.
There are 80 llm cost tracking tools tracked. 2 score above 50 (established tier). The highest-rated is AgentOps-AI/tokencost at 59/100 with 1,952 stars and 811,233 monthly downloads.
Get all 80 projects as JSON
curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=llm-cost-tracking&limit=20"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
| # | Tool | Score | Tier |
|---|---|---|---|
| 1 |
AgentOps-AI/tokencost
Easy token price estimates for 400+ LLMs. TokenOps. |
|
Established |
| 2 |
jmuncor/tokentap
Intercept LLM API traffic and visualize token usage in a real-time terminal... |
|
Established |
| 3 |
Ruthwik000/tokenfirewall
Scalable LLM cost enforcement middleware for Node.js with budget protection... |
|
Emerging |
| 4 |
Merit-Systems/echo
The User Pays AI SDK |
|
Emerging |
| 5 |
azat-io/token-limit
π° Monitor how many tokens your code and configs consume in AI tools. Set... |
|
Emerging |
| 6 |
inferwise/inferwise
Like a spell checker, but for your AI costs. Scans code, estimates spend,... |
|
Emerging |
| 7 |
arieradle/shekel
LLM budget control and cost governance for AI agents. Python library for... |
|
Emerging |
| 8 |
billymaulana/ai-armor
Production AI toolkit for TypeScript -- rate limiting, cost tracking,... |
|
Emerging |
| 9 |
burn0-dev/burn0
Lightweight cost observability for every API call in your stack. Track LLM... |
|
Emerging |
| 10 |
yagil/tokmon
CLI to monitor your program's OpenAI API token usage. |
|
Emerging |
| 11 |
adarshxs/TokenTally
Estimate Your LLM's Token Toll Across Various Platforms and Configurations |
|
Emerging |
| 12 |
piyushgupta344/ai-sdk-rate-limiter
Smart rate limiting, queuing, and cost tracking middleware for AI SDK calls.... |
|
Emerging |
| 13 |
RightNow-AI/TIDE
Dynamic per-token early exit for LLM inference. Skip layers tokens don't need |
|
Emerging |
| 14 |
tokentopapp/tokentop
htop for your AI costs β real-time terminal monitoring of LLM token usage... |
|
Emerging |
| 15 |
mag123c/toktrack
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code) |
|
Emerging |
| 16 |
AlameerAshraf/tokentoll
πΎ TokenToll: is a self-hostable billing infrastructure for LLM APIs and SaaS... |
|
Emerging |
| 17 |
dillionverma/llm.report
π llm.report is an open-source logging and analytics platform for OpenAI:... |
|
Emerging |
| 18 |
Coolhand-Labs/coolhand-node
Zero-config LLM cost & quality monitoring for Node.js - automatically log AI... |
|
Emerging |
| 19 |
udaykumar-dhokia/Trackly
Zero-overhead AI cost and usage tracking for Python. Import the library,... |
|
Emerging |
| 20 |
vola-trebla/toad-eye
Auto-instrumentation, cost tracking, and observability for LLM services β... |
|
Emerging |
| 21 |
ikotun-dev/costrace
Open-source observability for LLM APIs. Track cost, token usage, and latency... |
|
Emerging |
| 22 |
mazzzystar/api-usage
Track your OpenAI API token usage & cost. |
|
Emerging |
| 23 |
fluskapp/flusk-dev
Open-source LLM cost optimization and observability |
|
Experimental |
| 24 |
djleamen/SUSTAIN
SUSTAIN is an environmentally-friendly, token-optimized AI wrapper designed... |
|
Experimental |
| 25 |
Mattbusel/Every-Other-Token
A real-time LLM stream interceptor for token-level interaction research |
|
Experimental |
| 26 |
lanesket/llm.log
Local proxy that tracks tokens, costs, prompts and responses across all your... |
|
Experimental |
| 27 |
Mattbusel/llm-budget
Autonomous cost governance primitives β hard budget enforcement across agent fleets |
|
Experimental |
| 28 |
chu2bard/tokenmeter
Token counter and LLM cost estimator CLI |
|
Experimental |
| 29 |
JingbiaoMei/Tokdash
π Token Usage Dashboard β Beautiful visualization and analytics for LLM API... |
|
Experimental |
| 30 |
subhashladumor1/laravel-ai-guard
Laravel AI Guard π‘οΈπ°π€ - Control and optimize AI costs in Laravel AI SDK... |
|
Experimental |
| 31 |
ogulcanaydogan/LLM-Cost-Guardian
Token budget enforcement and cost attribution middleware for LLM APIs.... |
|
Experimental |
| 32 |
defilantech/infercost
Kubernetes-native cost intelligence for on-premises AI inference. Computes... |
|
Experimental |
| 33 |
iBz-04/OmniLink
Monitor api key usage per compute in dollars |
|
Experimental |
| 34 |
usagepilot/usagepilot
Open-source AI usage metering for SaaS. Track tokens, calculate costs,... |
|
Experimental |
| 35 |
uucz/llmview
See what your AI is thinking. See what it costs. One binary, zero config. |
|
Experimental |
| 36 |
voska/toktap
Transparent proxy that taps LLM API traffic to extract token usage metrics.... |
|
Experimental |
| 37 |
AIMasterLabs/tokenbudget
Open source AI cost tracking. Know exactly what your AI costs β per feature,... |
|
Experimental |
| 38 |
franzos/tku
Token Usage CLI for Claude Code, Codex and others |
|
Experimental |
| 39 |
maichanks/llm-cost-optimizer
LLM cost monitoring and optimization toolkit |
|
Experimental |
| 40 |
amedinat/LLMeter
Open-source LLM cost monitoring & optimization platform. Track spend across... |
|
Experimental |
| 41 |
CYzhr/AICostMonitor
AI API cost monitoring tool - Track and manage costs across multiple AI providers |
|
Experimental |
| 42 |
AreteDriver/ai-spend
Aggregate AI API costs across providers into a single CLI dashboard |
|
Experimental |
| 43 |
mikolajbadyl/PicoWatch
Lightweight self-hosted dashboard for tracking LLM API usage, costs and performance. |
|
Experimental |
| 44 |
tokenpak/tokenpak
Drop-in HTTP proxy that compresses LLM context, optimizes cache hits, routes... |
|
Experimental |
| 45 |
ArivunidhiA/forecost
Know exactly what your AI project will cost. Local-first LLM cost forecasting. |
|
Experimental |
| 46 |
sriinnu/Runic
macOS menu bar app for tracking AI usage, costs, quotas, and token windows... |
|
Experimental |
| 47 |
Vishwaksena94/tokenloom
π Parse streamed text into structured events using TokenLoom, a TypeScript... |
|
Experimental |
| 48 |
gyeningcorp/tokenizer
Real-time token counting & cost monitoring for every major LLM β Chrome,... |
|
Experimental |
| 49 |
cNoNim/llm-report
Aggregate usage and cost reports for Codex, Claude Code, and Gemini CLI sessions. |
|
Experimental |
| 50 |
hidearmoon/token-meter
Track every token, control every dollar. Lightweight LLM API cost & usage... |
|
Experimental |
| 51 |
ghoshsoham71/tokentaxi
tokentaxi is a lightweight Python library that sits between your application... |
|
Experimental |
| 52 |
sarth6/pydantic-ai-tool-budget
Per-tool budget reminders for Pydantic AI agents |
|
Experimental |
| 53 |
ManasVardhan/llm-cost-guardian
π° Real-time cost monitoring and budget enforcement for LLM API calls |
|
Experimental |
| 54 |
Mintlens/Mintlens
LLM cost tracking & governance for AI builders β the missing financial layer... |
|
Experimental |
| 55 |
artur28544/tokenmeter
π’ Count tokens and estimate API costs for OpenAI, Anthropic, and Google... |
|
Experimental |
| 56 |
artosien/Tokensense-Ai
TokenSense is a lightning-fast token cost calculator for LLMs. Paste your... |
|
Experimental |
| 57 |
ritik250505/tokenfirewall
Enforce and monitor LLM API budgets automatically with middleware that... |
|
Experimental |
| 58 |
jcxpjau/llm-burn
Cost tracking and budget enforcement for LLM calls in NestJS β with a single... |
|
Experimental |
| 59 |
HandyS11/DotnetTokenKiller
.NET CLI proxy that aim to reduce the LLM token usage though the dotnet commands |
|
Experimental |
| 60 |
ollieb89/llm-cost-tracker
GitHub Action to track LLM API costs in CI pipelines and alert on budget overruns |
|
Experimental |
| 61 |
olivelliott/fathom
Know what your AI coding actually costs. Headless intelligence layer for... |
|
Experimental |
| 62 |
mlabouardy/practical-finops
Practical FinOps: Managing cloud cost, visibility, and accountability |
|
Experimental |
| 63 |
Mattbusel/llm-cost-dashboard
Real-time terminal dashboard for LLM token spend β cost/request, projected... |
|
Experimental |
| 64 |
nicepkg/ai-spend
Track your LLM API costs with one line of code. Wraps OpenAI & Anthropic... |
|
Experimental |
| 65 |
lymagics/tokemon
A unified Python library for counting tokens across multiple LLM providers. |
|
Experimental |
| 66 |
lymagics/tokemon.dev
A web application for counting tokens across multiple LLM providers. Built... |
|
Experimental |
| 67 |
vizra-ai/ai-tokens
A lightweight PHP package for AI token cost management. Estimate costs... |
|
Experimental |
| 68 |
DevelopedBy-Siva/token-scope
Profile your LLM payloads. Find the waste. Cut the cost. Field-level token... |
|
Experimental |
| 69 |
ivelin-web/tokenflow
Real-time context-window token usage tracking for AI chat platforms |
|
Experimental |
| 70 |
tobiasleibrock/token-terminator
TokenTerminator is an AI prompt optimization tool that helps reduce token... |
|
Experimental |
| 71 |
MukundaKatta/tokenlens
See every dollar your AI spends |
|
Experimental |
| 72 |
tranhoangtu-it/ai-cost-profiler
Token usage, latency, and cost profiling across OpenAI, Anthropic, and... |
|
Experimental |
| 73 |
Ali-Raza-Arain/llm-spend-guard
Enforce real-time token budgets and spending limits for OpenAI, Anthropic... |
|
Experimental |
| 74 |
endless999-x/WealthDog-AI
A local desktop monitoring tool for managing multiple AI API keys and... |
|
Experimental |
| 75 |
lazymac2x/ai-cost-calculator-api
AI Cost Calculator API - calculate token costs for GPT-4, Claude, Gemini. REST + MCP. |
|
Experimental |
| 76 |
huntermussel/IRon
IRon: a βtoken dietβ agent for people who are tired of paying for markup |
|
Experimental |
| 77 |
daveschumaker/tokenflow
Interactive tool to visualize and compare different LLM token streaming speeds |
|
Experimental |
| 78 |
mohsenhe/infercost
AI FinOps Engine - GPU/LLM cost attribution for Kubernetes |
|
Experimental |
| 79 |
adriangalilea/vibe-coding-lang-bench
Token cost comparison: why higher-level languages win for LLM-assisted coding |
|
Experimental |
| 80 |
RishiMdvrm/TeraOps---Quantum-Compute-Cost-Optimization
An AI-powered quantum compute optimizer that minimizes cost and maximizes... |
|
Experimental |