npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

llm-cost

v1.0.5

Published

[![Tests](https://github.com/rogeriochaves/llm-cost/actions/workflows/node.js.yml/badge.svg)](https://github.com/rogeriochaves/llm-cost/actions/workflows/node.js.yml) [![npm version](https://badge.fury.io/js/llm-cost.svg)](https://www.npmjs.com/package/ll

Downloads

7,985

Readme

llm-cost

Tests npm version MIT License

llm-cost is a utility library for counting tokens and estimating the cost of LLMs from various providers such as OpenAI, Anthropic, Cohere, and more.

Features

  • Token Counting: Accurately count the number of tokens for a given input or output text.
  • Cost Estimation: Estimate the cost of using an LLM based on the token count and the specific model's pricing.

Installation

npm install llm-cost

Usage

tokenizeAndEstimateCost

This function takes the model name, input text, and output text. It returns a promise that resolves to an object with the number of input tokens, output tokens, and the estimated cost. Please note that when calling tokenizeAndEstimateCost for the first time with a specific model, it will load the tokenizer for that model and cache it in memory. This means that the first call may be slower, but subsequent calls will be faster due to the tokenizer being cached.

import { tokenizeAndEstimateCost } from "llm-cost";

async function main() {
  const result = await tokenizeAndEstimateCost({
    model: "gpt-4",
    input: "Hello, world!",
    output: "Hi there, how are you?",
  });

  console.log(result);
  // Output: { inputTokens: 4, outputTokens: 7, cost: 0.00054 }
}

main();

estimateCost

This function estimates the cost of using an LLM based on the number of input and output tokens, if you already have them. It takes an object with the model name, input token count, and output token count, returning the estimated cost.

import { estimateCost } from "llm-cost";

const cost = estimateCost({
  model: "gpt-4",
  inputTokens: 3000,
  outputTokens: 2100,
});

console.log(cost);
// Output: 0.216

Contributing

We are actively seeking contributions to expand the tokenizer support for various LLM providers. Currently, the library supports tokenizers for OpenAI models. If you have expertise in other LLMs tokenizers please submit a pull-request!

For any bugs or suggestions to the library, please open an issue at llm-cost issues.

License

This project is licensed under the MIT License - see the LICENSE file for details.