adarshxs/TokenTally
Estimate Your LLM's Token Toll Across Various Platforms and Configurations
TokenTally helps data scientists and ML engineers estimate the computing resources and costs for running large language models (LLMs). You input details about your LLM and deployment configuration, and it calculates the minimum GPU memory needed for training or inference, and the approximate cost per 1,000 tokens on various cloud platforms. This helps you plan your infrastructure and budget before deploying or fine-tuning an LLM.
Use this if you need to understand the GPU requirements and potential costs of deploying or training a large language model on a cloud platform.
Not ideal if you need precise, real-time cost tracking or an exact breakdown of proprietary optimization techniques for production LLM deployments.
Stars
39
Forks
8
Language
Python
License
MIT
Category
Last pushed
Nov 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/adarshxs/TokenTally"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jmuncor/tokentap
Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track...
AgentOps-AI/tokencost
Easy token price estimates for 400+ LLMs. TokenOps.
Merit-Systems/echo
The User Pays AI SDK
Ruthwik000/tokenfirewall
Scalable LLM cost enforcement middleware for Node.js with budget protection and multi-provider support
azat-io/token-limit
🛰 Monitor how many tokens your code and configs consume in AI tools. Set budgets and get alerts...