ngrok Blog company blog
Prompt caching for cheaper LLM tokens
A far more detailed explanation of prompt caching than anyone asked for: how tokens, embeddings, and attention make cached LLM tokens 10x cheaper and faster.
- Points
- 306
- HN comments
- 72
- Submissions
- 1
- Cited by
- 4 commenters
AI & Machine LearningSoftware Engineering2025
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Dec 16, 2025 | Prompt caching for cheaper LLM tokens by samwho | 306 | 72 |
Cited in comments
Linked from 4 Hacker News comments by 4 different people, from Dec 2025 to Jul 2026.
Most recent:
- NeutralForest · Jul 21, 2026
- keeda · Feb 12, 2026
- beklein · Jan 8, 2026
- machinationu · Dec 22, 2025
