Same AI, fewer tokens. Free forever
Compress AI prompts, cut token costs by 15%
What it does
Most AI prompts are full of filler. "In order to" is 4 tokens — "to" is 1. "Due to the fact that" is 6 tokens — "because" is 1. You're paying for words that add nothing. TokenShrink strips the fluff. Paste any prompt on the web, or npm install tokenshrink for your codebase. Every replacement is verified against GPT-4's tokenizer so it never increases your token count. 12-15% savings on typical system prompts. No AI calls. No API keys. No sign-up. Just cleaner prompts.
Does the same job
all alternatives →- CGCompress GPT-4 Prompts2023 · promptreducer.com · ▲68
Hey HN! I recently built Prompt Reducer, an app that makes it easier to compress GPT-4 prompts. The main goal is to reduce the number of tokens in each prompt, thereby reducing the cost of running GPT-4. I figured since @gfodor tweeted about compressing GPT-4. It’s still early, and it does not work perfectly, but I’d love to hear any feedback or suggestions for how to make it faster or more efficient.
Save AI Tokens with this one Website Apr 2026 · frukal.comPaste your prompt → optimize it → cut token cost instantly.
- CSCtx, save tokens by loading only the relevant toolsJun 2026 · github.com · ▲8
Hi HN! Token cost has started to become a high topic of concern to all of us. I tried a few (awesome) tools such as rtk, caveman, and the recent (hillarious but effective) ponytail. What they usually do, is in-line token reduction, e.g. try to compress requests / responses as much as possible. But then it hit me (and I’m sure others had similar ideas) - just like we have routers that pick the right model, why not have something that will also narrow down the amount of available tools, skills and mcps based on repo/context? People usually accumulate skills, agents, MCP servers,…
Tokavy — Less Tokens. Better Answers.May 2026 · tokavy.com · ▲2Your AI prompts, refined in a keystroke
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
