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

Update claude-api skill: Claude Fable 5 and Claude Mythos 5 (#1294)

Browse Source 
- Add Claude Fable 5 and Claude Mythos 5 to the model tables with pricing,
  context window, and model-selection guidance
- Document Fable-specific API behavior: always-on adaptive thinking (explicit
  disabled returns 400), protected-thinking display and replay rules, new
  tokenizer (~30% more tokens), refusal stop reason with server-side fallbacks
  and SDK fallback middleware, 30-day data-retention requirement
- Add the full Migrating to Claude Fable 5 guide section and checklist,
  including the Mythos Preview migration path
- Refresh skill trigger description, effort/compaction/task-budget notes,
  caching minimums, structured-output and dynamic-filtering support tables
This commit is contained in:
Lance Martin
2026-06-09 10:34:55 -07:00
committed by GitHub
parent c30d329f58
commit 5d25128289
13 changed files with 306 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/claude-api/shared/prompt-caching.md
+2 -2
View File
@@ -130,10 +130,10 @@ Fix by moving the dynamic piece after the last breakpoint, making it determinist
| Model | Minimum |
|---|---:|
| Opus 4.8, Opus 4.7, Opus 4.6, Opus 4.5, Haiku 4.5 | 4096 tokens |
| Sonnet 4.6, Haiku 3.5, Haiku 3 | 2048 tokens |
| Fable 5, 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 4.8.
A 3K-token prompt caches on Sonnet 4.5 and Fable 5 but silently won't on Opus 4.8.
**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.