Hacker News new | ask | show | jobs
user: christalingx
created: 2026-02-23
karma: 4

submissions:

0 points | 0 comments
Show HN: I built a proxy that cuts LLM costs 40-60% – no AI involved
2 points | 1 comments
0 points | 0 comments
Show HN: Compression API for LLM prompts (40-60% token savings, ~5ms overhead)
2 points | 2 comments
0 points | 0 comments
Show HN: I cut LLM API bill by 55% with a Python text compressor, no AI involved
3 points | 1 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Show HN: AgentReady – Drop-in proxy that cuts LLM token costs 40-60%
8 points | 13 comments