Follow Discord
Sweep 03 Nov 2026 · 22:27Z Build v2.1.318 536 read Stable v2.1.311 Latest v2.1.318 Next v2.1.318 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · claude-code

Monitoring changedmonitoring-usage

Upstream edited this page at 28 Oct 2026 19:51 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 28 Oct 2026 20:07 UTC.

Upstream edited
Recorded here
Lines+1added
Lines−0removed
From line 857 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits73to this page, all time

The whole hunk

from line 857, old and new numbered
/
lines
from line 857
857857* `output_tokens`: Number of output tokens
858858* `cache_read_tokens`: Number of tokens read from cache
859859* `cache_creation_tokens`: Number of tokens used for cache creation
860* `cache_creation_5m_tokens`, `cache_creation_1h_tokens`: the number of tokens the API response reports as written to the cache with a five-minute [cache lifetime](https://code.claude.com/docs/en/prompt-caching.md#cache-lifetime) and the number written with a one-hour lifetime. Both are `0` when the API response doesn't report them, even when `cache_creation_tokens` is above zero. Requires Claude Code v2.1.300 or later
860861* `request_id`: API request ID, such as `"req_011..."`, described under [Event correlation attributes](#event-correlation-attributes).
861862* `client_request_id`: Client-generated UUID sent as the `x-client-request-id` request header; see the [event correlation attributes](#event-correlation-attributes) table for when it's present
862863* `speed`: `"fast"` or `"normal"`, indicating whether fast mode was active
Feedback