Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · models-context

Prompt cache telemetryCommon product term

Inspect cache hits, misses, token counts, latency, or billing effects.

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

Prompt cache telemetry: 1 supported, 1 partial, 0 unsupported, 29 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 telemetry?

Read across for the answer. 2 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported1
  • Partial1
  • Unsupported0
  • Unknown29
  • 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 an operator can verify prompt-cache behavior for the exact harness. A billing dashboard total, per-request cached-token count, cache-hit event, and detailed read/write breakdown provide different levels of evidence and should be qualified.

Useful records identify where telemetry appears, how long it is retained, whether sub-agent and tool-generated requests are included, and how cached reads and writes map to price. A generic statement that caching is automatic does not prove that the harness exposes telemetry.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

Claude CLIcli · current
Supported
Target
current Claude Code documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimecurrent_usage exposes cache_creation_input_tokens and cache_read_input_tokens; OpenTelemetry reports cache read and creation tokens per request, user, and session
Evidence
Gemini CLIcli · current
Partial
Target
current Gemini CLI documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/stats displays cached-token savings when caching is available; the reviewed page does not establish hit/miss events or retained historical telemetry
Evidence
  1. 1. Evidence checked 2026-08-28: Claude Code exposes cache creation and cache read token counts through status-line data and OpenTelemetry, including per-user and per-session organization metrics.
  2. 2. Evidence checked 2026-08-28: Gemini CLI documents cached-token savings in /stats when token caching is available.