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 "cost_type" or "inference_geo" or 6 more`
72- `group_by: optional array of "claude_tag_category" or "claude_tag_user_id" or "context_window" or 8 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 - `"cost_type"`
from line 195
169195
170196 Amount (post-discount, pre-credit) in fractional cents.
171197
198 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
199
200 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.
201
202 - `"dm"`
203
204 - `"engaged"`
205
206 - `"monitoring"`
207
208 - `"proactive"`
209
210 - `"scheduled"`
211
212 - `claude_tag_user_id: string or null`
213
214 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.
215
172216 - `context_window: "0-200k" or "200k-1M" or null`
173217
174218 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 333
289333 "results": [
290334 {
291335 "amount": "amount",
336 "claude_tag_category": "dm",
337 "claude_tag_user_id": "U0123ABCDEF",
292338 "context_window": "0-200k",
293339 "cost_type": "code_execution",
294340 "currency": "USD",
from line 391
345391
346392 - `"1m"`
347393
394- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
395
396 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.
397
398 maxItems: 100
399
400 - `"dm"`
401
402 - `"engaged"`
403
404 - `"monitoring"`
405
406 - `"proactive"`
407
408 - `"scheduled"`
409
410- `claude_tag_user_ids: optional array of string`
411
412 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.
413
414 maxItems: 100
415
348416- `context_windows: optional array of "0-200k" or "200k-1M"`
349417
350418 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.
from line 435
367435
368436 default: false
369437
370- `group_by: optional array of "context_window" or "cost_type" or "inference_geo" or 6 more`
438- `group_by: optional array of "claude_tag_category" or "claude_tag_user_id" or "context_window" or 8 more`
371439
372440 Break each actor's row out by the given dimensions. Accepts the same values as the bucketed `/cost_report` endpoint. The `product`, `model`, `context_window`, `inference_geo`, and `speed` dimensions — and the time bucket, when `bucket_width` is set — count toward `limit`. `cost_type` and `token_type` do not: `cost_type` returns one row per cost component (tokens, web search, code execution); `token_type` returns one row per token type, each with `cost_type: "tokens"`; combining both returns the per-token-type rows plus the web-search and code-execution rows. A page can therefore contain more rows than `limit` when `cost_type` or `token_type` is requested.
373441
374442 maxItems: 100
375443
444 - `"claude_tag_category"`
445
446 - `"claude_tag_user_id"`
447
376448 - `"context_window"`
377449
378450 - `"cost_type"`
from line 595
523595
524596 Amount (post-discount, pre-credit) in fractional cents (minor units).
525597
598 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
599
600 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.
601
602 - `"dm"`
603
604 - `"engaged"`
605
606 - `"monitoring"`
607
608 - `"proactive"`
609
610 - `"scheduled"`
611
612 - `claude_tag_user_id: string or null`
613
614 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.
615
526616 - `context_window: "0-200k" or "200k-1M" or null`
527617
528618 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 743
653743 "user_id": "user_01AbCdEfGhIjKlMnOpQrSt"
654744 },
655745 "amount": "41280.000000",
746 "claude_tag_category": "dm",
747 "claude_tag_user_id": "U0123ABCDEF",
656748 "context_window": "0-200k",
657749 "cost_type": "code_execution",
658750 "currency": "USD",
from line 792
700792
701793 Amount (post-discount, pre-credit) in fractional cents.
702794
795 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
796
797 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.
798
799 - `"dm"`
800
801 - `"engaged"`
802
803 - `"monitoring"`
804
805 - `"proactive"`
806
807 - `"scheduled"`
808
809 - `claude_tag_user_id: string or null`
810
811 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.
812
703813 - `context_window: "0-200k" or "200k-1M" or null`
704814
705815 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 947
837947 - `amount: string`
838948
839949 Amount (post-discount, pre-credit) in fractional cents (minor units).
950
951 - `claude_tag_category: "dm" or "engaged" or "monitoring" or 2 more or null`
952
953 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.
954
955 - `"dm"`
956
957 - `"engaged"`
958
959 - `"monitoring"`
960
961 - `"proactive"`
962
963 - `"scheduled"`
964
965 - `claude_tag_user_id: string or null`
966
967 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.
840968
841969 - `context_window: "0-200k" or "200k-1M" or null`
842970