TokenSwarm

Live LLM API pricing & accurate GPU VRAM calculator

7 followers

Live LLM API pricing & accurate GPU VRAM calculator

7 followers

TokenSwarm is a free, no-signup utility hub for AI builders. Instantly compare live API pricing across 300+ models and accurately calculate GPU VRAM requirements (including KV cache and context length overhead) before running local models.

Free

Launch tags:Developer Tools•Artificial Intelligence

Launch Team

Topview Motion StudioGet a launch video for about $3, not thousands

Promoted

Maker

📌

Hi Product Hunt! 👋 I built TokenSwarm out of personal frustration. Running local models is amazing, but the constant math required to figure out if a model will fit in my GPU (calculating weights, KV cache, batch sizes) was slowing me down. The same goes for tracking live API costs. So, I built a central hub to handle all this instantly. It’s a 100% free utility, with no sign-ups or ads. Just raw tools for developers. I would absolutely love to hear your feedback. Are there any specific VRAM parameters I missed? Which model providers should I add next? Let me know!

Report

2mo ago

how does the VRAM calculator handle models that need to split across multiple GPUs, does it just flag an error or suggest a workable split?

Report

2mo ago

finally a pricing page that does not feel like it was designed to confuse me. The VRAM calc caught me off guard, it actually factored in KV cache for longer contexts instead of giving me the usual misleading number.

Report

2mo ago

Reviews

No reviews yetBe the first to leave a review for TokenSwarm