---
id: "action-implement-caching"
type: "action-item"
source_timestamps: ["00:18:00"]
tags: ["development", "api"]
related: ["concept-prompt-caching", "claim-caching-discount", "framework-kiss-commands"]
speakers: ["Nate B. Jones"]
action: "Enable prompt caching for static context blocks."
outcome: "Secures up to a 90% discount on repeated input tokens."
sources: ["s45-claude-limit-chatgpt-habit"]
sourceVaultSlug: "s45-claude-limit-chatgpt-habit"
originDay: 45
---
# Implement API Prompt Caching

## Action
If you are building applications via API, ensure that **prompt caching** features are enabled for stable context blocks — system instructions, tool schemas, persona definitions, static reference documents.

## Outcome
Secures up to a **90% discount** on repeated input tokens (e.g., $5.00/M → $0.50/M; or for Anthropic Sonnet, $3.75/M → $0.375/M). See [[claim-caching-discount]].

## Implementation Notes
- Native support: Anthropic, OpenAI (Batch API).
- Limited / non-native: Gemini, Mistral (as of overlay snapshot).
- Design stable blocks to be **large and persistent enough** to amortize cache write cost.
- Watch TTLs and minimum chunk sizes per provider.

## Why
See [[concept-prompt-caching]] for mechanism. Commandment #3 of [[framework-kiss-commands]] and checkpoint #5 of [[framework-stupid-button-audit]].