Design · Orchestration
Prompt Caching
Cache the model's internal state for a long, stable prefix (system prompt, tool defs, docs) so repeat calls only pay for the new suffix. Vendor-native at the API layer.
Verified against docs.anthropic.com
How it works
Cache the model's internal state for a long, stable prefix (system prompt, tool defs, docs) so repeat calls only pay for the new suffix. Vendor-native at the API layer.
At a glance
TechniqueCaching
Cost leverLower, cached prefix tokens billed at ~10% of input rate
Latency leverLower, cached prefix skips recompute
Quality leverIdentical, same model, same context
ExampleAnthropic prompt caching · OpenAI / Gemini cached content
When to use
Agents with large fixed context (long system prompt, big tool schema, RAG docs) reused across many turns.
Basis
Verified against
https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.