Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · models-context

Prompt cache controlsCommon product term

Mark, retain, refresh, or invalidate cached prompt context.

Terminology basis: Common product term. Anthropic — How Claude Code uses prompt caching

Prompt cache controls: 0 supported, 1 partial, 0 unsupported, 30 unreviewed across 31 cataloged products.

Markdown · JSON

Explore this familyMore in Models and context11 capabilities

Current evidence by product

Can my agent use Prompt cache controls?

Read across for the answer. 1 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported0
  • Partial1
  • Unsupported0
  • Unknown30
  • Not applicable0

Web

9 products

Desktop

13 products

CLI

9 products

Unknown means no public evidence has been reviewed for that product and capability. It does not mean unsupported.

How statuses are assigned

Definition and scope

What this capability means

This row asks whether the harness exposes a supported way to influence prompt caching rather than relying entirely on automatic provider behavior. Controls can include cache breakpoints, explicit cache objects, retention choices, refresh, or invalidation.

Evidence should record where the control lives—UI, project configuration, command flag, plugin, or provider-specific request setting—and whether the exact harness preserves it. Security review should also identify the tenant, workspace, user, project, or organization boundary around reuse.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

Claude CLIcli · current
Partial
Target
current Claude Code documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimeDISABLE_PROMPT_CACHING and per-model variants disable caching; TTL variables select documented retention behavior where supported
  • policyClaude Code manages prefix breakpoints automatically and does not expose arbitrary per-message breakpoint authoring in the reviewed harness documentation
Evidence
  1. 1. Evidence checked 2026-08-28: Claude Code exposes environment-variable controls to disable prompt caching globally or per model and to choose documented five-minute or one-hour TTL behavior in eligible environments.