Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

Usage changed

api/admin/analytics/usage

Nearest release: v2.1.261, published 3 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+130added
Lines−2removed
From line 31 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits6to this page, all time

The whole hunk

from line 31, old and new numbered
/
lines
from line 31
3131 
3232 - `"1m"`
3333 
34- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
35 
36 Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude-tag`, so combining this filter with `products[]=claude-tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values.
37 
38 maxItems: 100
39 
40 - `"dm"`
41 
42 - `"engaged"`
43 
44 - `"monitoring"`
45 
46 - `"proactive"`
47 
48 - `"scheduled"`
49 
50- `claude_tag_user_ids: optional array of string`
51 
52 Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values.
53 
54 maxItems: 100
55 
3456- `context_windows: optional array of "0-200k" or "200k-1M"`
3557 
3658 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.
from line 69
4769 
4870 format: date-time
4971 
50- `group_by: optional array of "context_window" or "inference_geo" or "model" or 4 more`
72- `group_by: optional array of "claude_tag_category" or "claude_tag_user_id" or "context_window" or 6 more`
5173 
5274 Dimensions to break each time bucket out by. Defaults to no grouping (one total per bucket). Each bucket reports at most its top 100 groups; a group beyond that cap has no row in that bucket (there is no remainder row), so grouped buckets are not exhaustive when a dimension has more than 100 distinct values.
5375 
5476 maxItems: 100
5577 
78 - `"claude_tag_category"`
79 
80 - `"claude_tag_user_id"`
81 
5682 - `"context_window"`
5783 
5884 - `"inference_geo"`
from line 203
177203 
178204 The number of input tokens read from the cache.
179205 
206 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
207 
208 Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time.
209 
210 - `"dm"`
211 
212 - `"engaged"`
213 
214 - `"monitoring"`
215 
216 - `"proactive"`
217 
218 - `"scheduled"`
219 
220 - `claude_tag_user_id: string or null`
221 
222 Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter.
223 
180224 - `context_window: "0-200k" or "200k-1M" or null`
181225 
182226 Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution.
from line 327
283327 "ephemeral_5m_input_tokens": 500
284328 },
285329 "cache_read_input_tokens": 0,
330 "claude_tag_category": "dm",
331 "claude_tag_user_id": "U0123ABCDEF",
286332 "context_window": "0-200k",
287333 "inference_geo": "global",
288334 "model": "claude-opus-5",
from line 386
340386 
341387 - `"1m"`
342388 
389- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
390 
391 Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude-tag`, so combining this filter with `products[]=claude-tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values.
392 
393 maxItems: 100
394 
395 - `"dm"`
396 
397 - `"engaged"`
398 
399 - `"monitoring"`
400 
401 - `"proactive"`
402 
403 - `"scheduled"`
404 
405- `claude_tag_user_ids: optional array of string`
406 
407 Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values.
408 
409 maxItems: 100
410 
343411- `context_windows: optional array of "0-200k" or "200k-1M"`
344412 
345413 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.
from line 430
362430 
363431 default: false
364432 
365- `group_by: optional array of "context_window" or "inference_geo" or "model" or 4 more`
433- `group_by: optional array of "claude_tag_category" or "claude_tag_user_id" or "context_window" or 6 more`
366434 
367435 Break each actor's row out by the given dimensions. Accepts the same values as the bucketed `/usage_report` endpoint. `limit` bounds (actor × time bucket × dimension) rows — with dimensions or `bucket_width` present, one actor may span several rows.
368436 
369437 maxItems: 100
370438 
439 - `"claude_tag_category"`
440 
441 - `"claude_tag_user_id"`
442 
371443 - `"context_window"`
372444 
373445 - `"inference_geo"`
from line 602
530602 
531603 The number of input tokens read from the cache.
532604 
605 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
606 
607 Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time.
608 
609 - `"dm"`
610 
611 - `"engaged"`
612 
613 - `"monitoring"`
614 
615 - `"proactive"`
616 
617 - `"scheduled"`
618 
619 - `claude_tag_user_id: string or null`
620 
621 Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter.
622 
533623 - `context_window: "0-200k" or "200k-1M" or null`
534624 
535625 Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution.
from line 740
650740 "ephemeral_5m_input_tokens": 500
651741 },
652742 "cache_read_input_tokens": 3200000,
743 "claude_tag_category": "dm",
744 "claude_tag_user_id": "U0123ABCDEF",
653745 "context_window": "0-200k",
654746 "ending_at": "2019-12-27T18:11:19.117Z",
655747 "inference_geo": "global",
from line 803
711803 
712804 The number of input tokens read from the cache.
713805 
806 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
807 
808 Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time.
809 
810 - `"dm"`
811 
812 - `"engaged"`
813 
814 - `"monitoring"`
815 
816 - `"proactive"`
817 
818 - `"scheduled"`
819 
820 - `claude_tag_user_id: string or null`
821 
822 Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter.
823 
714824 - `context_window: "0-200k" or "200k-1M" or null`
715825 
716826 Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution.
from line 952
842952 - `cache_read_input_tokens: number`
843953 
844954 The number of input tokens read from the cache.
955 
956 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
957 
958 Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time.
959 
960 - `"dm"`
961 
962 - `"engaged"`
963 
964 - `"monitoring"`
965 
966 - `"proactive"`
967 
968 - `"scheduled"`
969 
970 - `claude_tag_user_id: string or null`
971 
972 Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter.
845973 
846974 - `context_window: "0-200k" or "200k-1M" or null`
847975