wowdespacito/anthropics_skills
1
0
Fork 0
mirror of https://github.com/anthropics/skills.git synced 2026-08-02 13:05:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: update claude-api skill (#956)

Browse Source 
Add shared/model-migration.md and refresh model references, managed
agents docs, and skill description across all language guides.
This commit is contained in:
Eric Harmeling
2026-04-16 12:12:57 -07:00
committed by GitHub
parent 0f7c287eaf
commit 2c7ec5e78b
36 changed files with 1049 additions and 211 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/claude-api/shared/prompt-caching.md
+2 -2
View File
@@ -111,11 +111,11 @@ Fix by moving the dynamic piece after the last breakpoint, making it determinist
| Model | Minimum |
|---|---:|
| Opus 4.6, Opus 4.5, Haiku 4.5 | 4096 tokens |
| Opus 4.7, Opus 4.6, Opus 4.5, Haiku 4.5 | 4096 tokens |
| Sonnet 4.6, Haiku 3.5, Haiku 3 | 2048 tokens |
| Sonnet 4.5, Sonnet 4.1, Sonnet 4, Sonnet 3.7 | 1024 tokens |
A 3K-token prompt caches on Sonnet 4.5 but silently won't on Opus 4.6.
A 3K-token prompt caches on Sonnet 4.5 but silently won't on Opus 4.7.
**Economics:** Cache reads cost ~0.1× base input price. Cache writes cost **1.25× for 5-minute TTL, 2× for 1-hour TTL**. Break-even depends on TTL: with 5-minute TTL, two requests break even (1.25× + 0.1× = 1.35× vs 2× uncached); with 1-hour TTL, you need at least three requests (2× + 0.2× = 2.2× vs 3× uncached). The 1-hour TTL keeps entries alive across gaps in bursty traffic, but the doubled write cost means it needs more reads to pay off.