#per

tashfeenahmed/freellmapi

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

Show HN: I wrote an email app that accepts only one sender per inbox

The United Kingdom generates less electricity per person than in the 1970s

Indra OCR: a 1M-parameter OCR model that reads 49 pages per second on CPU

Parsing JSON at gigabytes per second in Python

Show HN: Aura – a self-hosted, multi-user AI agent with per-person graph memory

Optimizing x264 settings and per-title ladders

Mercury 2.5 LLM hits 770 tokens per second

9 Ads per Minute: FIFA Cup 26 – "the price of the beautiful game"

Iran war has cost on average $246M per day in its first five months

Micron Shows Off 512GB DDR5 Rdimm: 12TB per Dual-Socket Server at 9,200 MT/S

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI