Skip to main content

Quickly compare cost and results of different LLMs on the same prompt

· One min read
Luis Fernando De Pombo
Luis Fernando De Pombo

I often want a quick comparison of different LLMs to see the result+price+performance across different tasks or prompts.

So I put together LLMcomp—a straightforward site to compare (some) popular LLMs on cost, latency, and other details in one place. It’s still a work in progress, so any suggestions or ideas are welcome. I can add more LLMs if there is interest. It currently has Claude Sonnet, Deep Seek and 4o which are the ones I compare and contrast the most.

I built it using a port of AgentOps' tokencost for the web to estimate LLM usage costs on the web and the code for the website is open source and roughly 400 LOC

3 common mistakes when integrating the OpenAI API with your web or mobile app

· 7 min read
Luis Fernando De Pombo
Luis Fernando De Pombo

A key concern when building a web or mobile application that uses OpenAI’s language models is protecting your private API key. If you want to keep complexity low and release features quickly, setting up a fully fledged backend just to safeguard an API key can be time consuming. In this article, you’ll learn how to avoid the most common security mistakes when integrating the OpenAI API into a client-side app—without sacrificing simplicity or safety. Overlooking these pitfalls can leave the door open to OpenAI API misuse, which can:

  • Lead to unexpected or excessive charges on your OpenAI account

  • Violate OpenAI’s Acceptable Use Policy and Terms of Service

  • Potentially expose your project to spam or abusive behavior

Built a ChatGPT-like app with no backend/functions at ~1k LOC

· One min read
Luis Fernando De Pombo
Luis Fernando De Pombo

I wanted to showcase something I built using Backmesh. It is a ChatGPT-like app using Flutter, Firebase Authentication and Firestore. It is about 1k lines of code with no backend (server or cloud function). It runs on web, but since it was built with Flutter it could also run on mobile or desktop.

Source code: https://github.com/backmesh/flutter-chatgpt

Live Demo: https://flutter-chatgpt.pages.dev

Backmesh is now open source!

· 2 min read
Luis Fernando De Pombo
Luis Fernando De Pombo

We are proud to announce Backmesh is now open source along with a pricing update! The benefits of open source are many, but primordially we wanted to give any developer the ability to try it out Backmesh for free through our SaaS, or by self hosting it. Backmesh is hosted on Cloudflare so now anyone can host it on their own Cloudflare account without needing to use our SaaS. We should have done this from the get go, but felt like the codebase wasn’t ready yet. This led to a SaaS free tier that unfavorably impacted the bottom line making it difficult to build a sustainable business.