Home Docs Claude Developer Platform 25 Aug 2026

One change · api

Analytics changedapi/admin/analytics

Nearest release: v2.1.245, published an hour after 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 25 Aug 2026 03:37 UTC

Lines+398added

Lines−1,454removed

From line 1 where the diff opens

First seen 14 Aug 2026 this site's first read of the page

Recorded edits6to this page, all time

### Query parameters #### Response (200) ## Domain types ## Analytics › Usage ### Get Token Usage Over Time #### Query parameters #### Returns #### Example ##### Response (200) ### Get Per-User Token Usage #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Cost ### Get Cost Over Time #### Query parameters #### Returns #### Example ##### Response (200) ### Get Per-User Cost #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Users ### List User Activity #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Skills ### Get Skill Usage #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Connectors ### Get Connector Usage #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Chat Projects ### Get Chat Project Usage #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Plugins ### Get Plugin Usage #### Query parameters #### Returns #### Example ##### Response (200) ## Analytics › Artifacts ### Get Artifact Activity #### Query parameters #### Returns #### Example ##### Response (200) ### Query Parameters #### Response ## Domain Types # Usage ## Get Token Usage Over Time ### Query Parameters #### Response ## Get Per-User Token Usage ### Query Parameters #### Response ## Domain Types ### Usage Bucket ### User Usage # Cost ## Get Cost Over Time ### Query Parameters #### Response ## Get Per-User Cost ### Query Parameters #### Response ## Domain Types ### Cost Bucket ### User Cost # Users ## List User Activity ### Query Parameters #### Response ## Domain Types ### User Activity # Skills ## Get Skill Usage ### Query Parameters #### Response ## Domain Types ### Skill Usage # Connectors ## Get Connector Usage ### Query Parameters #### Response ## Domain Types ### Connector Usage # Chat Projects ## Get Chat Project Usage ### Query Parameters #### Response ## Domain Types ### Chat Project Usage # Plugins ## Get Plugin Usage ### Query Parameters #### Response ## Domain Types ### Plugin Usage # Artifacts ## Get Artifact Activity ### Query Parameters #### Response ## Domain Types ### Artifact Usage

The whole hunk

from line 1, old and new numbered

lines

The two sides of this change are more than 400 edits apart, too far apart to line up, so this is the differ's own diff of it and the words inside a line are not marked.

from line 1

1---

2title: Analytics

3url: https://platform.claude.com/docs/en/api/admin/analytics

4---

61# Analytics

83## Get Activity Summaries

10**get** `/v1/organizations/analytics/summaries`

5**GET** `/v1/organizations/analytics/summaries`

116

127Get organization-wide activity summaries for a date range.

138

from line 14

1914filter[]=rbac_group_id:<id>. Available to organizations on a Claude

2015Enterprise plan. Requires an API key with the `read:analytics` scope.

2116

22### Query Parameters

17### Query parameters

2318

2419- `starting_date: string`

2520

2621 UTC date in YYYY-MM-DD format. Start of the date range (inclusive). Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

2722

23 format: date

2825- `ending_date: optional string`

2926

3027 UTC date in YYYY-MM-DD format. End of the date range (exclusive). Data is typically available with a 1-day lag, so this can be at most today — which is also the default when omitted, making the last entry cover the most recent available day. Data may be revised by a few percent over the following days. The range may span at most 366 days.

3128

29 format: date

3231- `filter: optional array of string`

3332

3433 Filters as 'dimension:value'. Only rbac_group_id is supported (e.g. filter[]=rbac_group_id:<id>); repeat the param to OR across groups. Scopes the whole day series to members of the matching group(s), re-aggregated from member-level activity — org-wide seat/invite fields and the adoption rates derived from them are null on scoped rows. rbac_group_id accepts the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each UTC day (time-of-usage attribution). At most 100 entries.

3534

35 maxItems: 100

3637### Returns

3738

38- `ActivitySummary object { summaries }`

39- `ActivitySummary object`

3940

4041 Response for GET /v1/organizations/analytics/summaries.

4142

42 - `summaries: array of object { assigned_seat_count, cowork_daily_active_user_count, cowork_monthly_active_user_count, 26 more }`

43 - `summaries: array of object`

4344

4445 - `assigned_seat_count: number or null`

4546

from line 160

159160

160161### Example

161162

162```http

163```bash

163164curl https://api.anthropic.com/v1/organizations/analytics/summaries \

164165 -H 'anthropic-version: 2023-06-01' \

165166 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

166167```

167168

168#### Response

169#### Response (200)

169170

170171```json

171172{

from line 206

205206}

206207```

207208

208## Domain Types

209## Domain types

209210

210211### Activity Summary

211212

212- `ActivitySummary object { summaries }`

213- `ActivitySummary object`

213214

214215 Response for GET /v1/organizations/analytics/summaries.

215216

216 - `summaries: array of object { assigned_seat_count, cowork_daily_active_user_count, cowork_monthly_active_user_count, 26 more }`

217 - `summaries: array of object`

217218

218219 - `assigned_seat_count: number or null`

219220

from line 334

333334

334335### Analytics User

335336

336- `AnalyticsUser object { id, email_address, type }`

337- `AnalyticsUser object`

337338

338339 User identifier.

339340

from line 350

349350

350351 Object type. Always `user`.

351352

352 - `"user"`

353 default: user

353354

354355### Analytics User Actor

355356

356- `AnalyticsUserActor object { deleted, email, name, 2 more }`

357- `AnalyticsUserActor object`

357358

358359 - `deleted: boolean`

359360

from line 372

371372

372373 Actor type. Always `"user_actor"`.

373374

374 - `"user_actor"`

375

376375 - `user_id: string`

377376

378377 Tagged user ID.

379378

380379### Connector Office Product Metrics

381380

382- `ConnectorOfficeProductMetrics object { distinct_session_connector_used_count }`

381- `ConnectorOfficeProductMetrics object`

383382

384383 Office Agent activity metrics for a single connector on a given day within one Office product.

385384

from line 388

389388

390389### Office Product Metrics

391390

392- `OfficeProductMetrics object { connectors_used_count, distinct_connectors_used_count, distinct_session_count, 3 more }`

391- `OfficeProductMetrics object`

393392

394393 Office Agent activity metrics for a single user on a given day within one Office product.

395394

from line 418

419418

420419### Skill Office Product Metrics

421420

422- `SkillOfficeProductMetrics object { distinct_session_skill_used_count }`

421- `SkillOfficeProductMetrics object`

423422

424423 Office Agent activity metrics for a single skill on a given day within one Office product.

425424

from line 428

429428

430429### Tool Action Counts

431430

432- `ToolActionCounts object { accepted_count, rejected_count }`

431- `ToolActionCounts object`

433432

434433 Accepted/rejected counts for a single Claude Code tool type.

435434

from line 440

441440

442441 Number of tool proposals rejected

443442

444# Usage

445

446## Get Token Usage Over Time

447

448**get** `/v1/organizations/analytics/usage_report`

443## Analytics › Usage

444

445### Get Token Usage Over Time

446

447**GET** `/v1/organizations/analytics/usage_report`

449448

450449Get token usage over time across a date range.

451450

from line 453

454453Available to organizations on a Claude Enterprise plan. Requires an API

455454key with the `read:analytics` scope.

456455

457### Query Parameters

456#### Query parameters

458457

459458- `starting_at: string`

460459

461460 Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z.

462461

462 format: date-time

463

463464- `bucket_width: optional "1d" or "1h" or "1m"`

464465

465466 Time bucket granularity.

466467

468 default: 1d

469

467470 - `"1d"`

468471

469472 - `"1h"`

from line 477

474477

475478 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.

476479

480 maxItems: 100

481

477482 - `"0-200k"`

478483

479484 - `"200k-1M"`

from line 487

482487

483488 End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days.

484489

490 format: date-time

491

485492- `group_by: optional array of "context_window" or "inference_geo" or "model" or 4 more`

486493

487494 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.

488495

496 maxItems: 100

497

489498 - `"context_window"`

490499

491500 - `"inference_geo"`

from line 513

504513

505514 Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values.

506515

516 maxItems: 100

517

507518 - `"global"`

508519

509520 - `"not_available"`

from line 525

514525

515526 Maximum number of time buckets per page. Defaults and caps vary by bucket_width (1d: default 7, max 31; 1h: default 24, max 168; 1m: default 60, max 256).

516527

528 minimum: 1

529

517530- `models: optional array of string`

518531

519532 Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values.

520533

534 maxItems: 100

535

521536- `page: optional string`

522537

523538 Opaque cursor from a previous response's `next_page` field.

from line 541

526541

527542 Product surfaces to include. Defaults to all products. Use `group_by[]=product` to break out per-product values. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it.

528543

544 maxItems: 100

545

529546- `rbac_group_ids: optional array of string`

530547

531548 Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches.

532549

550 maxItems: 100

551

533552- `slack_channel_ids: optional array of string`

534553

535554 Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values.

536555

556 maxItems: 100

557

537558- `speeds: optional array of "fast" or "standard"`

538559

539560 Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values.

540561

562 maxItems: 100

563

541564 - `"fast"`

542565

543566 - `"standard"`

from line 569

546569

547570 Filter to specific users by tagged user ID.

548571

549### Returns

550

551- `UsageBucket object { data, data_refreshed_at, has_more, 2 more }`

552

553 - `data: array of object { ending_at, results, starting_at }`

572 maxItems: 100

573

574#### Returns

575

576- `UsageBucket object`

577

578 - `data: array of object`

554579

555580 Time buckets for this page, oldest first: one per `bucket_width` interval, including intervals with no data (their `results` list is empty). A page holds at most `limit` buckets.

556581

from line 583

558583

559584 End of the time bucket (exclusive) in RFC 3339 format.

560585

561 - `results: array of object { cache_creation, cache_read_input_tokens, context_window, 10 more }`

586 format: date-time

587

588 - `results: array of object`

562589

563590 Rows for this time bucket. Empty when the bucket has no data; otherwise a single combined row when `group_by[]` is omitted, or one row per group (subject to the per-bucket group cap described on the `group_by[]` parameter).

564591

565 - `cache_creation: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }`

592 - `cache_creation: object`

566593

567594 The number of input tokens for cache creation.

568595

from line 641

614641

615642 Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).

616643

617 - `server_tool_use: object { web_search_requests }`

644 - `server_tool_use: object`

618645

619646 Server-side tool usage metrics.

620647

from line 669

642669

643670 Start of the time bucket (inclusive) in RFC 3339 format.

644671

672 format: date-time

673

645674 - `data_refreshed_at: string or null`

646675

647676 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is empty. Buckets beyond this watermark are incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

648677

678 format: date-time

679

649680 - `has_more: boolean`

650681

651682 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

from line 689

658689

659690 ID of the Organization.

660691

661### Example

662

663```http

692#### Example

693

694```bash

664695curl https://api.anthropic.com/v1/organizations/analytics/usage_report \

665696 -H 'anthropic-version: 2023-06-01' \

666697 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

667698```

668699

669#### Response

700##### Response (200)

670701

671702```json

672703{

from line 736

705736}

706737```

707738

708## Get Per-User Token Usage

709

710**get** `/v1/organizations/analytics/user_usage_report`

739### Get Per-User Token Usage

740

741**GET** `/v1/organizations/analytics/user_usage_report`

711742

712743Get per-user token usage across a date range.

713744

from line 750

719750organizations on a Claude Enterprise plan. Requires an API key with the

720751`read:analytics` scope.

721752

722### Query Parameters

753#### Query parameters

723754

724755- `starting_at: string`

725756

726757 Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z.

727758

759 format: date-time

760

728761- `bucket_width: optional "1d" or "1h" or "1m"`

729762

730763 Time-bucket granularity. When set, each row's `starting_at` and `ending_at` are populated and one actor may span several rows (one per time bucket with usage). The time bucket counts toward `limit`, so one page can return multiple rows for the same actor. `ending_at` is required when `bucket_width` is set, and with `bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the full `[starting_at, ending_at)` range.

from line 772

739772

740773 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.

741774

775 maxItems: 100

776

742777 - `"0-200k"`

743778

744779 - `"200k-1M"`

from line 782

747782

748783 End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days.

749784

785 format: date-time

786

750787- `exclude_deleted_users: optional boolean`

751788

752789 If true, omit rows for users who are deleted (`deleted: true`). A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual.

753790

791 default: false

792

754793- `group_by: optional array of "context_window" or "inference_geo" or "model" or 4 more`

755794

756795 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.

757796

797 maxItems: 100

798

758799 - `"context_window"`

759800

760801 - `"inference_geo"`

from line 814

773814

774815 Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values.

775816

817 maxItems: 100

818

776819 - `"global"`

777820

778821 - `"not_available"`

from line 826

783826

784827 Number of rows per page (1-1000, default 20). One row per actor unless `group_by[]` or `bucket_width` splits an actor across rows; `cost_type`/`token_type` fan-out rows (cost endpoint only) are the exception — they do not count toward this limit, so `data` can exceed it.

785828

829 default: 20, maximum: 1000, minimum: 1

830

786831- `models: optional array of string`

787832

788833 Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values.

789834

835 maxItems: 100

836

790837- `order: optional "asc" or "desc"`

791838

792839 Sort direction. Defaults to `desc`.

793840

841 default: desc

842

794843 - `"asc"`

795844

796845 - `"desc"`

from line 848

799848

800849 Metric to rank actors by. Defaults to `total_tokens`.

801850

851 default: total_tokens

852

802853 - `"output_tokens"`

803854

804855 - `"requests"`

from line 866

815866

816867 Product surfaces to include. Defaults to all products. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it.

817868

869 maxItems: 100

870

818871- `rbac_group_ids: optional array of string`

819872

820873 Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches.

821874

875 maxItems: 100

876

822877- `slack_channel_ids: optional array of string`

823878

824879 Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values.

825880

881 maxItems: 100

882

826883- `speeds: optional array of "fast" or "standard"`

827884

828885 Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values.

829886

887 maxItems: 100

888

830889 - `"fast"`

831890

832891 - `"standard"`

from line 894

835894

836895 Filter to specific users by tagged user ID.

837896

838### Returns

839

840- `UserUsage object { data, data_refreshed_at, has_more, 2 more }`

841

842 - `data: array of object { actor, cache_creation, cache_read_input_tokens, 14 more }`

897 maxItems: 100

898

899#### Returns

900

901- `UserUsage object`

902

903 - `data: array of object`

843904

844905 Rows for this page, ranked by `order_by` in the `order` direction. One row per user, or several per user when `group_by[]` or `bucket_width` breaks that user's usage or cost out across rows. Rows split out by `cost_type` or `token_type` (cost endpoint only) stay adjacent and are ranked as one unit.

845906

from line 924

863924

864925 Actor type. Always `"user_actor"`.

865926

866 - `"user_actor"`

867

868927 - `user_id: string`

869928

870929 Tagged user ID.

871930

872 - `cache_creation: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }`

931 - `cache_creation: object`

873932

874933 The number of input tokens for cache creation.

875934

from line 956

897956

898957 End of the row's UTC time bucket (exclusive), as an RFC 3339 timestamp; equal to `starting_at` plus one `bucket_width`. Null unless `bucket_width` is set.

899958

959 format: date-time

960

900961 - `inference_geo: "global" or "us" or null`

901962

902963 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).

from line 986

925986

926987 Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).

927988

928 - `server_tool_use: object { web_search_requests }`

989 - `server_tool_use: object`

929990

930991 Server-side tool usage metrics.

931992

from line 1010

9491010

9501011 Start of the row's UTC time bucket (inclusive), as an RFC 3339 timestamp. Null unless `bucket_width` is set; without `bucket_width`, each row aggregates the full requested range.

9511012

1013 format: date-time

1014

9521015 - `total_tokens: number`

9531016

9541017 Total token count across all token types. This is the value the default order_by='total_tokens' sorts on.

from line 1024

9611024

9621025 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this watermark is incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

9631026

1027 format: date-time

1028

9641029 - `has_more: boolean`

9651030

9661031 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

from line 1038

9731038

9741039 ID of the Organization.

9751040

976### Example

977

978```http

1041#### Example

1042

1043```bash

9791044curl https://api.anthropic.com/v1/organizations/analytics/user_usage_report \

9801045 -H 'anthropic-version: 2023-06-01' \

9811046 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

9821047```

9831048

984#### Response

1049##### Response (200)

9851050

9861051```json

9871052{

from line 1089

10241089}

10251090```

10261091

1027## Domain Types

1028

1029### Usage Bucket

1030

1031- `UsageBucket object { data, data_refreshed_at, has_more, 2 more }`

1032

1033 - `data: array of object { ending_at, results, starting_at }`

1034

1035 Time buckets for this page, oldest first: one per `bucket_width` interval, including intervals with no data (their `results` list is empty). A page holds at most `limit` buckets.

1036

1037 - `ending_at: string`

1038

1039 End of the time bucket (exclusive) in RFC 3339 format.

1040

1041 - `results: array of object { cache_creation, cache_read_input_tokens, context_window, 10 more }`

1042

1043 Rows for this time bucket. Empty when the bucket has no data; otherwise a single combined row when `group_by[]` is omitted, or one row per group (subject to the per-bucket group cap described on the `group_by[]` parameter).

1044

1045 - `cache_creation: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }`

1046

1047 The number of input tokens for cache creation.

1048

1049 - `ephemeral_1h_input_tokens: number`

1050

1051 The number of input tokens used to create the 1 hour cache entry.

1052

1053 - `ephemeral_5m_input_tokens: number`

1054

1055 The number of input tokens used to create the 5 minute cache entry.

1056

1057 - `cache_read_input_tokens: number`

1058

1059 The number of input tokens read from the cache.

1060

1061 - `context_window: "0-200k" or "200k-1M" or null`

1062

1063 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.

1064

1065 - `"0-200k"`

1066

1067 - `"200k-1M"`

1068

1069 - `inference_geo: "global" or "us" or null`

1070

1071 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).

1072

1073 - `"global"`

1074

1075 - `"us"`

1076

1077 - `model: string or null`

1078

1079 Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-4-6`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution.

1080

1081 - `output_tokens: number`

1082

1083 The number of output tokens generated.

1084

1085 - `product: string or null`

1086

1087 Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it. Some unattributed usage is reported as "other".

1088

1089 - `rbac_group_id: string or null`

1090

1091 RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has ONE id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query with no group_by.

1092

1093 - `requests: number or null`

1094

1095 Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).

1096

1097 - `server_tool_use: object { web_search_requests }`

1098

1099 Server-side tool usage metrics.

1100

1101 - `web_search_requests: number`

1102

1103 The number of web search requests made.

1104

1105 - `slack_channel_id: string or null`

1106

1107 Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled).

1108

1109 - `speed: "fast" or "standard" or null`

1110

1111 Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`.

1112

1113 - `"fast"`

1114

1115 - `"standard"`

1116

1117 - `uncached_input_tokens: number`

1118

1119 The number of uncached input tokens processed.

1120

1121 - `starting_at: string`

1122

1123 Start of the time bucket (inclusive) in RFC 3339 format.

1124

1125 - `data_refreshed_at: string or null`

1126

1127 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is empty. Buckets beyond this watermark are incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

1128

1129 - `has_more: boolean`

1130

1131 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

1132

1133 - `next_page: string or null`

1134

1135 Opaque cursor for the next page, or null when `has_more` is false. Pass it as the `page` parameter, keeping the other parameters unchanged. A cursor can expire after the underlying data refreshes; the request then returns HTTP 410 and pagination must restart from the first page.

1136

1137 - `organization_id: string`

1138

1139 ID of the Organization.

1140

1141### User Usage

1142

1143- `UserUsage object { data, data_refreshed_at, has_more, 2 more }`

1144

1145 - `data: array of object { actor, cache_creation, cache_read_input_tokens, 14 more }`

1146

1147 Rows for this page, ranked by `order_by` in the `order` direction. One row per user, or several per user when `group_by[]` or `bucket_width` breaks that user's usage or cost out across rows. Rows split out by `cost_type` or `token_type` (cost endpoint only) stay adjacent and are ranked as one unit.

1148

1149 - `actor: AnalyticsUserActor`

1150

1151 The user this row's usage or cost is attributed to. Always a `user_actor`.

1152

1153 - `deleted: boolean`

1154

1155 True when the user is no longer a member of the organization or its associated organizations: either their membership was removed (for example, deprovisioned via your identity provider) or the account itself has been deleted. The flag reflects organization membership, not account status. `name` and `email` stay populated for removed members; `name` is `"Deleted User"` and `email` null when the account has been deleted. The `user_id` is still populated for reconciliation.

1156

1157 - `email: string or null`

1158

1159 The user's email address, including for users who are no longer members of the organization or its associated organizations. Null when the account has been deleted (check `deleted`) and for system-minted service accounts, which have no person's mailbox behind them (check `name`).

1160

1161 - `name: string or null`

1162

1163 The user's current name, including for users who are no longer members of the organization or its associated organizations. Null when the user has not set a name. Returns `"Deleted User"` when the account itself has been deleted. Rows for system-minted service accounts render the service name (for example, `"Claude Security"` for usage by Anthropic's security-patching service) or null.

1164

1165 - `type: "user_actor"`

1166

1167 Actor type. Always `"user_actor"`.

1168

1169 - `"user_actor"`

1170

1171 - `user_id: string`

1172

1173 Tagged user ID.

1174

1175 - `cache_creation: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }`

1176

1177 The number of input tokens for cache creation.

1178

1179 - `ephemeral_1h_input_tokens: number`

1180

1181 The number of input tokens used to create the 1 hour cache entry.

1182

1183 - `ephemeral_5m_input_tokens: number`

1184

1185 The number of input tokens used to create the 5 minute cache entry.

1186

1187 - `cache_read_input_tokens: number`

1188

1189 The number of input tokens read from the cache.

1190

1191 - `context_window: "0-200k" or "200k-1M" or null`

1192

1193 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.

1194

1195 - `"0-200k"`

1196

1197 - `"200k-1M"`

1198

1199 - `ending_at: string or null`

1200

1201 End of the row's UTC time bucket (exclusive), as an RFC 3339 timestamp; equal to `starting_at` plus one `bucket_width`. Null unless `bucket_width` is set.

1202

1203 - `inference_geo: "global" or "us" or null`

1204

1205 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).

1206

1207 - `"global"`

1208

1209 - `"us"`

1210

1211 - `model: string or null`

1212

1213 Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-4-6`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution.

1214

1215 - `output_tokens: number`

1216

1217 The number of output tokens generated.

1218

1219 - `product: string or null`

1220

1221 Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it. Some unattributed usage is reported as "other".

1222

1223 - `rbac_group_id: string or null`

1224

1225 RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has ONE id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query with no group_by.

1226

1227 - `requests: number or null`

1228

1229 Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).

1230

1231 - `server_tool_use: object { web_search_requests }`

1232

1233 Server-side tool usage metrics.

1234

1235 - `web_search_requests: number`

1236

1237 The number of web search requests made.

1238

1239 - `slack_channel_id: string or null`

1240

1241 Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled).

1242

1243 - `speed: "fast" or "standard" or null`

1244

1245 Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`.

1246

1247 - `"fast"`

1248

1249 - `"standard"`

1250

1251 - `starting_at: string or null`

1252

1253 Start of the row's UTC time bucket (inclusive), as an RFC 3339 timestamp. Null unless `bucket_width` is set; without `bucket_width`, each row aggregates the full requested range.

1254

1255 - `total_tokens: number`

1256

1257 Total token count across all token types. This is the value the default order_by='total_tokens' sorts on.

1258

1259 - `uncached_input_tokens: number`

1260

1261 The number of uncached input tokens processed.

1262

1263 - `data_refreshed_at: string or null`

1264

1265 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this watermark is incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

1266

1267 - `has_more: boolean`

1268

1269 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

1270

1271 - `next_page: string or null`

1272

1273 Opaque cursor for the next page, or null when `has_more` is false. Pass it as the `page` parameter, keeping the other parameters unchanged. A cursor can expire after the underlying data refreshes; the request then returns HTTP 410 and pagination must restart from the first page.

1274

1275 - `organization_id: string`

1276

1277 ID of the Organization.

1278

1279# Cost

1280

1281## Get Cost Over Time

1282

1283**get** `/v1/organizations/analytics/cost_report`

1092## Analytics › Cost

1093

1094### Get Cost Over Time

1095

1096**GET** `/v1/organizations/analytics/cost_report`

12841097

12851098Get cost in USD over time across a date range.

12861099

from line 1102

12891102token type. Available to organizations on a Claude Enterprise plan.

12901103Requires an API key with the `read:analytics` scope.

12911104

1292### Query Parameters

1105#### Query parameters

12931106

12941107- `starting_at: string`

12951108

12961109 Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z.

12971110

1111 format: date-time

1112

12981113- `bucket_width: optional "1d" or "1h" or "1m"`

12991114

13001115 Time bucket granularity.

13011116

1117 default: 1d

1118

13021119 - `"1d"`

13031120

13041121 - `"1h"`

from line 1126

13091126

13101127 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.

13111128

1129 maxItems: 100

1130

13121131 - `"0-200k"`

13131132

13141133 - `"200k-1M"`

from line 1136

13171136

13181137 End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days.

13191138

1139 format: date-time

1140

13201141- `group_by: optional array of "context_window" or "cost_type" or "inference_geo" or 6 more`

13211142

13221143 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.

13231144

1145 maxItems: 100

1146

13241147 - `"context_window"`

13251148

13261149 - `"cost_type"`

from line 1166

13431166

13441167 Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values.

13451168

1169 maxItems: 100

1170

13461171 - `"global"`

13471172

13481173 - `"not_available"`

from line 1178

13531178

13541179 Maximum number of time buckets per page. Defaults and caps vary by bucket_width (1d: default 7, max 31; 1h: default 24, max 168; 1m: default 60, max 256).

13551180

1181 minimum: 1

1182

13561183- `models: optional array of string`

13571184

13581185 Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values.

13591186

1187 maxItems: 100

1188

13601189- `page: optional string`

13611190

13621191 Opaque cursor from a previous response's `next_page` field.

from line 1194

13651194

13661195 Product surfaces to include. Defaults to all products. Use `group_by[]=product` to break out per-product values. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it.

13671196

1197 maxItems: 100

1198

13681199- `rbac_group_ids: optional array of string`

13691200

13701201 Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches.

13711202

1203 maxItems: 100

1204

13721205- `slack_channel_ids: optional array of string`

13731206

13741207 Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values.

13751208

1209 maxItems: 100

1210

13761211- `speeds: optional array of "fast" or "standard"`

13771212

13781213 Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values.

13791214

1215 maxItems: 100

1216

13801217 - `"fast"`

13811218

13821219 - `"standard"`

from line 1222

13851222

13861223 Filter to specific users by tagged user ID.

13871224

1388### Returns

1389

1390- `CostBucket object { data, data_refreshed_at, has_more, 2 more }`

1391

1392 - `data: array of object { ending_at, results, starting_at }`

1225 maxItems: 100

1226

1227#### Returns

1228

1229- `CostBucket object`

1230

1231 - `data: array of object`

13931232

13941233 Time buckets for this page, oldest first: one per `bucket_width` interval, including intervals with no data (their `results` list is empty). A page holds at most `limit` buckets.

13951234

from line 1236

13971236

13981237 End of the time bucket (exclusive) in RFC 3339 format.

13991238

1400 - `results: array of object { amount, context_window, cost_type, 10 more }`

1239 format: date-time

1240

1241 - `results: array of object`

14011242

14021243 Rows for this time bucket. Empty when the bucket has no data; otherwise a single combined row when `group_by[]` is omitted, or one row per group (subject to the per-bucket group cap described on the `group_by[]` parameter).

14031244

from line 1268

14271268

14281269 Currency code for the cost amount. Currently always `"USD"`.

14291270

1430 - `"USD"`

1271 default: USD

14311272

14321273 - `inference_geo: "global" or "us" or null`

14331274

from line 1328

14871328

14881329 Start of the time bucket (inclusive) in RFC 3339 format.

14891330

1331 format: date-time

1332

14901333 - `data_refreshed_at: string or null`

14911334

14921335 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is empty. Buckets beyond this watermark are incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

14931336

1337 format: date-time

1338

14941339 - `has_more: boolean`

14951340

14961341 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

from line 1348

15031348

15041349 ID of the Organization.

15051350

1506### Example

1507

1508```http

1351#### Example

1352

1353```bash

15091354curl https://api.anthropic.com/v1/organizations/analytics/cost_report \

15101355 -H 'anthropic-version: 2023-06-01' \

15111356 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

15121357```

15131358

1514#### Response

1359##### Response (200)

15151360

15161361```json

15171362{

from line 1390

15451390}

15461391```

15471392

1548## Get Per-User Cost

1549

1550**get** `/v1/organizations/analytics/user_cost_report`

1393### Get Per-User Cost

1394

1395**GET** `/v1/organizations/analytics/user_cost_report`

15511396

15521397Get per-user cost in USD across a date range.

15531398

from line 1404

15591404organizations on a Claude Enterprise plan. Requires an API key with the

15601405`read:analytics` scope.

15611406

1562### Query Parameters

1407#### Query parameters

15631408

15641409- `starting_at: string`

15651410

15661411 Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z.

15671412

1413 format: date-time

1414

15681415- `bucket_width: optional "1d" or "1h" or "1m"`

15691416

15701417 Time-bucket granularity. When set, each row's `starting_at` and `ending_at` are populated and one actor may span several rows (one per time bucket with usage). The time bucket counts toward `limit`, so one page can return multiple rows for the same actor. `ending_at` is required when `bucket_width` is set, and with `bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the full `[starting_at, ending_at)` range.

from line 1426

15791426

15801427 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.

15811428

1429 maxItems: 100

1430

15821431 - `"0-200k"`

15831432

15841433 - `"200k-1M"`

from line 1436

15871436

15881437 End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days.

15891438

1439 format: date-time

1440

15901441- `exclude_deleted_users: optional boolean`

15911442

15921443 If true, omit rows for users who are deleted (`deleted: true`). A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual.

15931444

1445 default: false

1446

15941447- `group_by: optional array of "context_window" or "cost_type" or "inference_geo" or 6 more`

15951448

15961449 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.

15971450

1451 maxItems: 100

1452

15981453 - `"context_window"`

15991454

16001455 - `"cost_type"`

from line 1472

16171472

16181473 Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values.

16191474

1475 maxItems: 100

1476

16201477 - `"global"`

16211478

16221479 - `"not_available"`

from line 1484

16271484

16281485 Number of rows per page (1-1000, default 20). One row per actor unless `group_by[]` or `bucket_width` splits an actor across rows; `cost_type`/`token_type` fan-out rows (cost endpoint only) are the exception — they do not count toward this limit, so `data` can exceed it.

16291486

1487 default: 20, maximum: 1000, minimum: 1

1488

16301489- `models: optional array of string`

16311490

16321491 Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values.

16331492

1493 maxItems: 100

1494

16341495- `order: optional "asc" or "desc"`

16351496

16361497 Sort direction. Defaults to `desc`.

16371498

1499 default: desc

1500

16381501 - `"asc"`

16391502

16401503 - `"desc"`

from line 1506

16431506

16441507 Metric to rank actors by. Defaults to `amount`.

16451508

1509 default: amount

1510

16461511 - `"amount"`

16471512

16481513 - `"list_amount"`

from line 1520

16551520

16561521 Product surfaces to include. Defaults to all products. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it.

16571522

1523 maxItems: 100

1524

16581525- `rbac_group_ids: optional array of string`

16591526

16601527 Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches.

16611528

1529 maxItems: 100

1530

16621531- `slack_channel_ids: optional array of string`

16631532

16641533 Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values.

16651534

1535 maxItems: 100

1536

16661537- `speeds: optional array of "fast" or "standard"`

16671538

16681539 Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values.

16691540

1541 maxItems: 100

1542

16701543 - `"fast"`

16711544

16721545 - `"standard"`

from line 1548

16751548

16761549 Filter to specific users by tagged user ID.

16771550

1678### Returns

1679

1680- `UserCost object { data, data_refreshed_at, has_more, 2 more }`

1681

1682 - `data: array of object { actor, amount, context_window, 13 more }`

1551 maxItems: 100

1552

1553#### Returns

1554

1555- `UserCost object`

1556

1557 - `data: array of object`

16831558

16841559 Rows for this page, ranked by `order_by` in the `order` direction. One row per user, or several per user when `group_by[]` or `bucket_width` breaks that user's usage or cost out across rows. Rows split out by `cost_type` or `token_type` (cost endpoint only) stay adjacent and are ranked as one unit.

16851560

from line 1578

17031578

17041579 Actor type. Always `"user_actor"`.

17051580

1706 - `"user_actor"`

1707

17081581 - `user_id: string`

17091582

17101583 Tagged user ID.

from line 1608

17351608

17361609 Currency code for the cost amount. Currently always `"USD"`.

17371610

1738 - `"USD"`

1611 default: USD

17391612

17401613 - `ending_at: string or null`

17411614

17421615 End of the row's UTC time bucket (exclusive), as an RFC 3339 timestamp; equal to `starting_at` plus one `bucket_width`. Null unless `bucket_width` is set.

17431616

1617 format: date-time

1618

17441619 - `inference_geo: "global" or "us" or null`

17451620

17461621 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).

from line 1660

17851660

17861661 Start of the row's UTC time bucket (inclusive), as an RFC 3339 timestamp. Null unless `bucket_width` is set; without `bucket_width`, each row aggregates the full requested range.

17871662

1663 format: date-time

1664

17881665 - `token_type: "cache_creation.ephemeral_1h_input_tokens" or "cache_creation.ephemeral_5m_input_tokens" or "cache_read_input_tokens" or 2 more or null`

17891666

17901667 Token type when cost_type=tokens; null otherwise.

from line 1680

18031680

18041681 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this watermark is incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

18051682

1683 format: date-time

1684

18061685 - `has_more: boolean`

18071686

18081687 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

from line 1694

18151694

18161695 ID of the Organization.

18171696

1818### Example

1819

1820```http

1697#### Example

1698

1699```bash

18211700curl https://api.anthropic.com/v1/organizations/analytics/user_cost_report \

18221701 -H 'anthropic-version: 2023-06-01' \

18231702 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

18241703```

18251704

1826#### Response

1705##### Response (200)

18271706

18281707```json

18291708{

from line 1739

18601739}

18611740```

18621741

1863## Domain Types

1864

1865### Cost Bucket

1866

1867- `CostBucket object { data, data_refreshed_at, has_more, 2 more }`

1868

1869 - `data: array of object { ending_at, results, starting_at }`

1870

1871 Time buckets for this page, oldest first: one per `bucket_width` interval, including intervals with no data (their `results` list is empty). A page holds at most `limit` buckets.

1872

1873 - `ending_at: string`

1874

1875 End of the time bucket (exclusive) in RFC 3339 format.

1876

1877 - `results: array of object { amount, context_window, cost_type, 10 more }`

1878

1879 Rows for this time bucket. Empty when the bucket has no data; otherwise a single combined row when `group_by[]` is omitted, or one row per group (subject to the per-bucket group cap described on the `group_by[]` parameter).

1880

1881 - `amount: string`

1882

1883 Amount (post-discount, pre-credit) in fractional cents.

1884

1885 - `context_window: "0-200k" or "200k-1M" or null`

1886

1887 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.

1888

1889 - `"0-200k"`

1890

1891 - `"200k-1M"`

1892

1893 - `cost_type: "code_execution" or "tokens" or "web_search" or null`

1894

1895 Cost component when `group_by[]=cost_type`; null otherwise (amount is the combined total).

1896

1897 - `"code_execution"`

1898

1899 - `"tokens"`

1900

1901 - `"web_search"`

1902

1903 - `currency: "USD"`

1904

1905 Currency code for the cost amount. Currently always `"USD"`.

1906

1907 - `"USD"`

1908

1909 - `inference_geo: "global" or "us" or null`

1910

1911 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).

1912

1913 - `"global"`

1914

1915 - `"us"`

1916

1917 - `list_amount: string`

1918

1919 List-price amount (pre-discount) in fractional cents.

1920

1921 - `model: string or null`

1922

1923 Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-4-6`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution.

1924

1925 - `product: string or null`

1926

1927 Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it. Some unattributed usage is reported as "other".

1928

1929 - `rbac_group_id: string or null`

1930

1931 RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has ONE id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query with no group_by.

1932

1933 - `requests: number or null`

1934

1935 Number of API requests in this row's scope. Null when `group_by` includes `cost_type` or `token_type` (the count has no per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).

1936

1937 - `slack_channel_id: string or null`

1938

1939 Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled).

1940

1941 - `speed: "fast" or "standard" or null`

1942

1943 Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`.

1944

1945 - `"fast"`

1946

1947 - `"standard"`

1948

1949 - `token_type: "cache_creation.ephemeral_1h_input_tokens" or "cache_creation.ephemeral_5m_input_tokens" or "cache_read_input_tokens" or 2 more or null`

1950

1951 Token type when `group_by[]=token_type` and `cost_type=tokens`; null otherwise.

1952

1953 - `"cache_creation.ephemeral_1h_input_tokens"`

1954

1955 - `"cache_creation.ephemeral_5m_input_tokens"`

1956

1957 - `"cache_read_input_tokens"`

1958

1959 - `"output_tokens"`

1960

1961 - `"uncached_input_tokens"`

1962

1963 - `starting_at: string`

1964

1965 Start of the time bucket (inclusive) in RFC 3339 format.

1966

1967 - `data_refreshed_at: string or null`

1968

1969 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is empty. Buckets beyond this watermark are incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

1970

1971 - `has_more: boolean`

1972

1973 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

1974

1975 - `next_page: string or null`

1976

1977 Opaque cursor for the next page, or null when `has_more` is false. Pass it as the `page` parameter, keeping the other parameters unchanged. A cursor can expire after the underlying data refreshes; the request then returns HTTP 410 and pagination must restart from the first page.

1978

1979 - `organization_id: string`

1980

1981 ID of the Organization.

1982

1983### User Cost

1984

1985- `UserCost object { data, data_refreshed_at, has_more, 2 more }`

1986

1987 - `data: array of object { actor, amount, context_window, 13 more }`

1988

1989 Rows for this page, ranked by `order_by` in the `order` direction. One row per user, or several per user when `group_by[]` or `bucket_width` breaks that user's usage or cost out across rows. Rows split out by `cost_type` or `token_type` (cost endpoint only) stay adjacent and are ranked as one unit.

1990

1991 - `actor: AnalyticsUserActor`

1992

1993 The user this row's usage or cost is attributed to. Always a `user_actor`.

1994

1995 - `deleted: boolean`

1996

1997 True when the user is no longer a member of the organization or its associated organizations: either their membership was removed (for example, deprovisioned via your identity provider) or the account itself has been deleted. The flag reflects organization membership, not account status. `name` and `email` stay populated for removed members; `name` is `"Deleted User"` and `email` null when the account has been deleted. The `user_id` is still populated for reconciliation.

1998

1999 - `email: string or null`

2000

2001 The user's email address, including for users who are no longer members of the organization or its associated organizations. Null when the account has been deleted (check `deleted`) and for system-minted service accounts, which have no person's mailbox behind them (check `name`).

2002

2003 - `name: string or null`

2004

2005 The user's current name, including for users who are no longer members of the organization or its associated organizations. Null when the user has not set a name. Returns `"Deleted User"` when the account itself has been deleted. Rows for system-minted service accounts render the service name (for example, `"Claude Security"` for usage by Anthropic's security-patching service) or null.

2006

2007 - `type: "user_actor"`

2008

2009 Actor type. Always `"user_actor"`.

2010

2011 - `"user_actor"`

2012

2013 - `user_id: string`

2014

2015 Tagged user ID.

2016

2017 - `amount: string`

2018

2019 Amount (post-discount, pre-credit) in fractional cents (minor units).

2020

2021 - `context_window: "0-200k" or "200k-1M" or null`

2022

2023 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.

2024

2025 - `"0-200k"`

2026

2027 - `"200k-1M"`

2028

2029 - `cost_type: "code_execution" or "tokens" or "web_search" or null`

2030

2031 Cost component breakdown; null when returning the combined total.

2032

2033 - `"code_execution"`

2034

2035 - `"tokens"`

2036

2037 - `"web_search"`

2038

2039 - `currency: "USD"`

2040

2041 Currency code for the cost amount. Currently always `"USD"`.

2042

2043 - `"USD"`

2044

2045 - `ending_at: string or null`

2046

2047 End of the row's UTC time bucket (exclusive), as an RFC 3339 timestamp; equal to `starting_at` plus one `bucket_width`. Null unless `bucket_width` is set.

2048

2049 - `inference_geo: "global" or "us" or null`

2050

2051 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).

2052

2053 - `"global"`

2054

2055 - `"us"`

2056

2057 - `list_amount: string`

2058

2059 List-price amount (pre-discount) in fractional cents.

2060

2061 - `model: string or null`

2062

2063 Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-4-6`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution.

2064

2065 - `product: string or null`

2066

2067 Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include "chat", "claude_code", "cowork", "office_agent", "claude_in_chrome", "claude_design", and "claude-in-slack". "claude-in-slack" (with hyphens) is Claude Tag, the Claude product in Slack. A similarly spelled legacy value (underscores instead of hyphens) identifies the retiring v1 Slack chat bot and appears only for organizations that used it. Some unattributed usage is reported as "other".

2068

2069 - `rbac_group_id: string or null`

2070

2071 RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has ONE id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query with no group_by.

2072

2073 - `requests: number or null`

2074

2075 Number of API requests in this row's scope. Null when `group_by` includes `cost_type` or `token_type` (the count has no per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).

2076

2077 - `slack_channel_id: string or null`

2078

2079 Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled).

2080

2081 - `speed: "fast" or "standard" or null`

2082

2083 Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`.

2084

2085 - `"fast"`

2086

2087 - `"standard"`

2088

2089 - `starting_at: string or null`

2090

2091 Start of the row's UTC time bucket (inclusive), as an RFC 3339 timestamp. Null unless `bucket_width` is set; without `bucket_width`, each row aggregates the full requested range.

2092

2093 - `token_type: "cache_creation.ephemeral_1h_input_tokens" or "cache_creation.ephemeral_5m_input_tokens" or "cache_read_input_tokens" or 2 more or null`

2094

2095 Token type when cost_type=tokens; null otherwise.

2096

2097 - `"cache_creation.ephemeral_1h_input_tokens"`

2098

2099 - `"cache_creation.ephemeral_5m_input_tokens"`

2100

2101 - `"cache_read_input_tokens"`

2102

2103 - `"output_tokens"`

2104

2105 - `"uncached_input_tokens"`

2106

2107 - `data_refreshed_at: string or null`

2108

2109 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this watermark is incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours but not final until about 30 days after the usage date (late-arriving events, reconciliation adjustments).

2110

2111 - `has_more: boolean`

2112

2113 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.

2114

2115 - `next_page: string or null`

2116

2117 Opaque cursor for the next page, or null when `has_more` is false. Pass it as the `page` parameter, keeping the other parameters unchanged. A cursor can expire after the underlying data refreshes; the request then returns HTTP 410 and pagination must restart from the first page.

2118

2119 - `organization_id: string`

2120

2121 ID of the Organization.

2122

2123# Users

2124

2125## List User Activity

2126

2127**get** `/v1/organizations/analytics/users`

1742## Analytics › Users

1743

1744### List User Activity

1745

1746**GET** `/v1/organizations/analytics/users`

21281747

21291748Get per-user activity for a given day, with cursor-based pagination.

21301749

from line 1753

21341753to organizations on a Claude Enterprise plan. Requires an API key with

21351754the `read:analytics` scope.

21361755

2137### Query Parameters

1756#### Query parameters

21381757

21391758- `date: optional string`

21401759

21411760 UTC date in YYYY-MM-DD format. The day to get user activity for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

21421761

1762 format: date

1763

21431764- `ending_date: optional string`

21441765

21451766 UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with starting_date. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after starting_date.

21461767

1768 format: date

1769

21471770- `filter: optional array of string`

21481771

21491772 Filters as 'dimension:value', e.g. filter[]=rbac_group_id:<id>. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: project_id, rbac_group_id, user_id. Value forms: project_id takes a tagged project id (claude_proj_...) and scopes each member's row to their claude.ai chat activity within that project (it cannot be combined with group_by[] or an rbac_group_id filter); rbac_group_id takes the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); user_id takes a tagged user id (user_...), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.

21501773

1774 maxItems: 100

1775

21511776- `group_by: optional array of "rbac_group_id"`

21521777

21531778 Dimensions to break results out by (e.g. group_by[]=rbac_group_id). Supported on this endpoint: rbac_group_id. Rows are already per-member, so the one supported grouping aggregates them per RBAC group instead. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via next_page; an unsupported dimension returns 400. rbac_group_id attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries.

21541779

2155 - `"rbac_group_id"`

1780 maxItems: 100

21561781

21571782- `limit: optional number`

21581783

21591784 Number of results per page (1-1000, default 100).

21601785

1786 minimum: 1, maximum: 1000

1787

21611788- `order: optional "asc" or "desc"`

21621789

21631790 Sort direction: 'asc' or 'desc'. Defaults to 'asc' for the endpoint's sort column and to 'desc' when order_by names a metric (a top-N ranking). Applies to order_by, or to the endpoint's default sort field when order_by is omitted.

from line 1805

21781805

21791806 UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either date or starting_date, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

21801807

2181### Returns

2182

2183- `UserActivity object { data, next_page }`

1808 format: date

1809

1810#### Returns

1811

1812- `UserActivity object`

21841813

21851814 Response for GET /v1/organizations/analytics/users.

21861815

2187 - `data: array of object { chat_metrics, claude_code_metrics, cowork_metrics, 9 more }`

2188

2189 - `chat_metrics: object { connectors_used_count, distinct_artifacts_created_count, distinct_connectors_used_count, 9 more }`

1816 - `data: array of object`

1817

1818 - `chat_metrics: object`

21901819

21911820 Claude.ai activity metrics for a single user on a given day.

21921821

from line 1867

22381867

22391868 Number of messages that used extended thinking

22401869

2241 - `claude_code_metrics: object { core_metrics, tool_actions }`

1870 - `claude_code_metrics: object`

22421871

22431872 Claude Code activity metrics for a single user on a given day.

22441873

2245 - `core_metrics: object { commit_count, distinct_session_count, lines_of_code, pull_request_count }`

1874 - `core_metrics: object`

22461875

22471876 Core Claude Code activity metrics for a single user on a given day.

22481877

from line 1883

22541883

22551884 Number of distinct Claude Code sessions. On aggregated rows and in date-range mode: summed per-day distinct counts. A session essentially never spans a UTC day, so the sum is in practice the true distinct count.

22561885

2257 - `lines_of_code: object { added_count, removed_count }`

1886 - `lines_of_code: object`

22581887

22591888 Lines of code added and removed via Claude Code.

22601889

from line 1899

22701899

22711900 Number of pull requests created via Claude Code

22721901

2273 - `tool_actions: object { edit_tool, multi_edit_tool, notebook_edit_tool, write_tool }`

1902 - `tool_actions: object`

22741903

22751904 Per-tool accepted/rejected counts for Claude Code file modification tools.

22761905

from line 1927

22981927

22991928 Accepted/rejected counts for a single Claude Code tool type.

23001929

2301 - `cowork_metrics: object { action_count, connectors_used_count, dispatch_turn_count, 13 more }`

1930 - `cowork_metrics: object`

23021931

23031932 Cowork activity metrics for a single user on a given day.

23041933

from line 1995

23661995

23671996 Number of successful Write tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization.

23681997

2369 - `design_metrics: object { distinct_projects_created_count, distinct_projects_used_count, distinct_session_count, message_count }`

1998 - `design_metrics: object`

23701999

23712000 Claude Design activity metrics for a single user on a given day.

23722001

from line 2015

23862015

23872016 Number of messages sent in Claude Design sessions

23882017

2389 - `office_metrics: object { excel, outlook, powerpoint, word }`

2018 - `office_metrics: object`

23902019

23912020 Office Agent activity metrics for a single user on a given day, broken out by Office product.

23922021

from line 2059

24302059

24312060 Office Agent activity metrics for a single user on a given day within one Office product.

24322061

2433 - `science_metrics: object { delegation_count, distinct_session_count, message_count, 2 more }`

2062 - `science_metrics: object`

24342063

24352064 Claude Science activity metrics for a single user on a given day.

24362065

from line 2119

24902119

24912120 Object type. Always `user`.

24922121

2493 - `"user"`

2122 default: user

24942123

24952124 - `next_page: string or null`

24962125

24972126 Opaque cursor for the next page, or null if no more results

24982127

2499### Example

2500

2501```http

2128#### Example

2129

2130```bash

25022131curl https://api.anthropic.com/v1/organizations/analytics/users \

25032132 -H 'anthropic-version: 2023-06-01' \

25042133 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

25052134```

25062135

2507#### Response

2136##### Response (200)

25082137

25092138```json

25102139{

from line 2263

26342263}

26352264```

26362265

2637## Domain Types

2638

2639### User Activity

2640

2641- `UserActivity object { data, next_page }`

2642

2643 Response for GET /v1/organizations/analytics/users.

2644

2645 - `data: array of object { chat_metrics, claude_code_metrics, cowork_metrics, 9 more }`

2646

2647 - `chat_metrics: object { connectors_used_count, distinct_artifacts_created_count, distinct_connectors_used_count, 9 more }`

2648

2649 Claude.ai activity metrics for a single user on a given day.

2650

2651 - `connectors_used_count: number`

2652

2653 Number of MCP connector invocations.

2654

2655 - `distinct_artifacts_created_count: number`

2656

2657 Number of distinct artifacts created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

2658

2659 - `distinct_connectors_used_count: number or null`

2660

2661 Distinct claude.ai connectors this user used. Excludes calls whose connector could not be identified and all calls from organizations with zero data retention. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2662

2663 - `distinct_conversation_count: number or null`

2664

2665 Number of distinct conversations the user participated in. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2666

2667 - `distinct_files_uploaded_count: number or null`

2668

2669 Number of distinct files uploaded. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2670

2671 - `distinct_projects_created_count: number`

2672

2673 Number of distinct projects created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

2674

2675 - `distinct_projects_used_count: number or null`

2676

2677 Number of distinct projects used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2678

2679 - `distinct_shared_artifacts_viewed_count: number or null`

2680

2681 Number of distinct shared artifacts the user viewed. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2682

2683 - `distinct_skills_used_count: number or null`

2684

2685 Number of distinct skills used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2686

2687 - `message_count: number`

2688

2689 Number of messages sent

2690

2691 - `shared_conversations_viewed_count: number`

2692

2693 Number of times the user opened a shared conversation in a project

2694

2695 - `thinking_message_count: number`

2696

2697 Number of messages that used extended thinking

2698

2699 - `claude_code_metrics: object { core_metrics, tool_actions }`

2700

2701 Claude Code activity metrics for a single user on a given day.

2702

2703 - `core_metrics: object { commit_count, distinct_session_count, lines_of_code, pull_request_count }`

2704

2705 Core Claude Code activity metrics for a single user on a given day.

2706

2707 - `commit_count: number`

2708

2709 Number of commits made via Claude Code

2710

2711 - `distinct_session_count: number or null`

2712

2713 Number of distinct Claude Code sessions. On aggregated rows and in date-range mode: summed per-day distinct counts. A session essentially never spans a UTC day, so the sum is in practice the true distinct count.

2714

2715 - `lines_of_code: object { added_count, removed_count }`

2716

2717 Lines of code added and removed via Claude Code.

2718

2719 - `added_count: number`

2720

2721 Lines of code added

2722

2723 - `removed_count: number`

2724

2725 Lines of code removed

2726

2727 - `pull_request_count: number`

2728

2729 Number of pull requests created via Claude Code

2730

2731 - `tool_actions: object { edit_tool, multi_edit_tool, notebook_edit_tool, write_tool }`

2732

2733 Per-tool accepted/rejected counts for Claude Code file modification tools.

2734

2735 - `edit_tool: ToolActionCounts`

2736

2737 Accepted/rejected counts for a single Claude Code tool type.

2738

2739 - `accepted_count: number`

2740

2741 Number of tool proposals accepted

2742

2743 - `rejected_count: number`

2744

2745 Number of tool proposals rejected

2746

2747 - `multi_edit_tool: ToolActionCounts`

2748

2749 Accepted/rejected counts for a single Claude Code tool type.

2750

2751 - `notebook_edit_tool: ToolActionCounts`

2752

2753 Accepted/rejected counts for a single Claude Code tool type.

2754

2755 - `write_tool: ToolActionCounts`

2756

2757 Accepted/rejected counts for a single Claude Code tool type.

2758

2759 - `cowork_metrics: object { action_count, connectors_used_count, dispatch_turn_count, 13 more }`

2760

2761 Cowork activity metrics for a single user on a given day.

2762

2763 - `action_count: number`

2764

2765 Number of tool actions completed in Cowork sessions

2766

2767 - `connectors_used_count: number`

2768

2769 Total number of connector invocations in Cowork sessions

2770

2771 - `dispatch_turn_count: number`

2772

2773 Number of Dispatch (background agent) turns completed

2774

2775 - `distinct_connectors_used_count: number or null`

2776

2777 Number of distinct connectors used in Cowork sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2778

2779 - `distinct_session_count: number or null`

2780

2781 Number of distinct Cowork sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2782

2783 - `distinct_skills_used_count: number or null`

2784

2785 Number of distinct skills used in Cowork sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2786

2787 - `message_count: number`

2788

2789 Number of messages sent in Cowork sessions

2790

2791 - `skills_used_count: number`

2792

2793 Total number of skill invocations in Cowork sessions

2794

2795 - `distinct_plugins_used_count: optional number or null`

2796

2797 Number of distinct plugins used in Cowork sessions. Null while Cowork plugin-use metrics are not enabled for this organization. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2798

2799 - `edit_tool_count: optional number or null`

2800

2801 Number of successful Edit tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization.

2802

2803 - `file_edit_count: optional number or null`

2804

2805 Number of successful file-edit tool calls (Edit, MultiEdit, Write, NotebookEdit) in Cowork sessions. Null, never 0, while the file-edit metrics are not enabled for this organization.

2806

2807 - `multi_edit_tool_count: optional number or null`

2808

2809 Number of successful MultiEdit tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization.

2810

2811 - `notebook_edit_tool_count: optional number or null`

2812

2813 Number of successful NotebookEdit tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization.

2814

2815 - `plugins_used_count: optional number or null`

2816

2817 Total number of plugin invocations in Cowork sessions. Null while Cowork plugin-use metrics are not enabled for this organization.

2818

2819 - `sessions_with_file_edits_count: optional number or null`

2820

2821 Number of distinct Cowork sessions with at least one successful file-edit tool call. Null while the file-edit metrics are not enabled for this organization. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2822

2823 - `write_tool_count: optional number or null`

2824

2825 Number of successful Write tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization.

2826

2827 - `design_metrics: object { distinct_projects_created_count, distinct_projects_used_count, distinct_session_count, message_count }`

2828

2829 Claude Design activity metrics for a single user on a given day.

2830

2831 - `distinct_projects_created_count: number`

2832

2833 Number of distinct Claude Design projects created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

2834

2835 - `distinct_projects_used_count: number or null`

2836

2837 Number of distinct Claude Design projects the user worked in. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2838

2839 - `distinct_session_count: number or null`

2840

2841 Number of distinct Claude Design sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2842

2843 - `message_count: number`

2844

2845 Number of messages sent in Claude Design sessions

2846

2847 - `office_metrics: object { excel, outlook, powerpoint, word }`

2848

2849 Office Agent activity metrics for a single user on a given day, broken out by Office product.

2850

2851 - `excel: OfficeProductMetrics`

2852

2853 Office Agent activity metrics for a single user on a given day within one Office product.

2854

2855 - `connectors_used_count: number`

2856

2857 Number of MCP connector invocations

2858

2859 - `distinct_connectors_used_count: number or null`

2860

2861 Number of distinct MCP connectors used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2862

2863 - `distinct_session_count: number or null`

2864

2865 Number of distinct Office Agent sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2866

2867 - `distinct_skills_used_count: number or null`

2868

2869 Number of distinct skills used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2870

2871 - `message_count: number`

2872

2873 Number of messages sent

2874

2875 - `skills_used_count: number`

2876

2877 Number of skill invocations

2878

2879 - `outlook: OfficeProductMetrics`

2880

2881 Office Agent activity metrics for a single user on a given day within one Office product.

2882

2883 - `powerpoint: OfficeProductMetrics`

2884

2885 Office Agent activity metrics for a single user on a given day within one Office product.

2886

2887 - `word: OfficeProductMetrics`

2888

2889 Office Agent activity metrics for a single user on a given day within one Office product.

2890

2891 - `science_metrics: object { delegation_count, distinct_session_count, message_count, 2 more }`

2892

2893 Claude Science activity metrics for a single user on a given day.

2894

2895 - `delegation_count: number`

2896

2897 Number of delegations (handoffs to a specialized agent) in Claude Science sessions

2898

2899 - `distinct_session_count: number or null`

2900

2901 Number of distinct Claude Science sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

2902

2903 - `message_count: number`

2904

2905 Number of messages sent in Claude Science sessions

2906

2907 - `remote_compute_job_count: number`

2908

2909 Number of remote compute jobs launched from Claude Science sessions

2910

2911 - `skills_used_count: number`

2912

2913 Total number of skill invocations in Claude Science sessions

2914

2915 - `web_search_count: number`

2916

2917 Number of web searches performed

2918

2919 - `distinct_user_count: optional number or null`

2920

2921 Number of distinct active users represented by this row. Only set for grouped rollups (`group_by[]`); null for per-user rows. In date-range mode, recomputed as an exact distinct count of the group's active members over the requested window, never a sum of per-day values.

2922

2923 - `last_activity_date: optional string or null`

2924

2925 Most recent UTC day (YYYY-MM-DD) on which the user had any counted activity, within the requested window: equal to the requested date in single-day mode, and to the latest active day in [starting_date, ending_date) in date-range rollup mode — never a day earlier than the window start. On filtered requests (`filter[]`) only days matching the filter count: with `filter[]=rbac_group_id` it is the last day the user was active while a member of that group, consistent with the row's other metrics. Null on grouped (`group_by[]`) rows. Omitted from the response while last-activity reporting is not enabled for this organization.

2926

2927 - `rbac_group_id: optional string or null`

2928

2929 Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`.

2930

2931 - `rbac_group_name: optional string or null`

2932

2933 Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key.

2934

2935 - `user: optional AnalyticsUser or null`

2936

2937 User identifier.

2938

2939 - `id: string`

2940

2941 Tagged user identifier (e.g. `user_...`)

2942

2943 - `email_address: string`

2944

2945 Email address of the user

2946

2947 - `type: optional "user"`

2948

2949 Object type. Always `user`.

2950

2951 - `"user"`

2952

2953 - `next_page: string or null`

2954

2955 Opaque cursor for the next page, or null if no more results

2956

2957# Skills

2958

2959## Get Skill Usage

2960

2961**get** `/v1/organizations/analytics/skills`

2266## Analytics › Skills

2267

2268### Get Skill Usage

2269

2270**GET** `/v1/organizations/analytics/skills`

29622271

29632272Get per-skill usage for a given day, with cursor-based pagination.

29642273

from line 2278

29692278on a Claude Enterprise plan. Requires an API key with the

29702279`read:analytics` scope.

29712280

2972### Query Parameters

2281#### Query parameters

29732282

29742283- `date: optional string`

29752284

29762285 UTC date in YYYY-MM-DD format. The day to get skill usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

29772286

2287 format: date

2288

29782289- `ending_date: optional string`

29792290

29802291 UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with starting_date. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after starting_date.

29812292

2293 format: date

2294

29822295- `filter: optional array of string`

29832296

29842297 Filters as 'dimension:value', e.g. filter[]=rbac_group_id:<id>. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: product, rbac_group_id, share_status, skill_name, user_id. Value forms: product is one of chat, claude_code, cowork, or office_agent; rbac_group_id takes the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); share_status is one of organization, private, or public; skill_name matches case-insensitively; user_id takes a tagged user id (user_...), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.

29852298

2299 maxItems: 100

2300

29862301- `group_by: optional array of "product" or "rbac_group_id" or "user_id"`

29872302

29882303 Dimensions to break results out by (e.g. group_by[]=user_id). Supported on this endpoint: product, rbac_group_id, user_id. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via next_page; an unsupported dimension returns 400. rbac_group_id attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries.

29892304

2305 maxItems: 100

2306

29902307 - `"product"`

29912308

29922309 - `"rbac_group_id"`

from line 2314

29972314

29982315 Number of results per page (1-1000, default 100).

29992316

2317 minimum: 1, maximum: 1000

2318

30002319- `order: optional "asc" or "desc"`

30012320

30022321 Sort direction: 'asc' or 'desc'. Defaults to 'asc' for the endpoint's sort column and to 'desc' when order_by names a metric (a top-N ranking). Applies to order_by, or to the endpoint's default sort field when order_by is omitted.

from line 2336

30172336

30182337 UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either date or starting_date, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

30192338

3020### Returns

3021

3022- `SkillUsage object { data, next_page }`

2339 format: date

2340

2341#### Returns

2342

2343- `SkillUsage object`

30232344

30242345 Response for GET /v1/organizations/analytics/skills.

30252346

3026 - `data: array of object { chat_metrics, claude_code_metrics, cowork_metrics, 14 more }`

3027

3028 - `chat_metrics: object { distinct_conversation_skill_used_count }`

2347 - `data: array of object`

2348

2349 - `chat_metrics: object`

30292350

30302351 Claude.ai activity metrics for a single skill on a given day.

30312352

from line 2354

30332354

30342355 Number of distinct conversations in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

30352356

3036 - `claude_code_metrics: object { distinct_session_skill_used_count }`

2357 - `claude_code_metrics: object`

30372358

30382359 Claude Code activity metrics for a single skill on a given day.

30392360

from line 2362

30412362

30422363 Number of distinct Claude Code sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

30432364

3044 - `cowork_metrics: object { distinct_session_skill_used_count }`

2365 - `cowork_metrics: object`

30452366

30462367 Cowork activity metrics for a single skill on a given day.

30472368

from line 2374

30532374

30542375 Number of distinct users who used the skill on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted.

30552376

3056 - `office_metrics: object { excel, outlook, powerpoint, word }`

2377 - `office_metrics: object`

30572378

30582379 Office Agent activity metrics for a single skill on a given day, broken out by Office product.

30592380

from line 2410

30892410

30902411 Currency for this row's monetary fields (estimated_overage_spend and attributed_list_price), as an uppercase ISO-4217 code. Always "USD" when either amount is populated; null whenever both amounts are null.

30912412

3092 - `"USD"`

3093

30942413 - `enable_count: optional number or null`

30952414

30962415 Distinct accounts that enabled this skill on the requested day (claude.ai only — the skill analog of plugin install_count). The count is org-wide: null when enable reporting is not enabled for this organization, or when the request scopes to `user_id` / `rbac_group_id` / `product` via `group_by[]` or `filter[]` (an org-wide count would be misleading on per-cut rows). A distinct count, not an event count: summing across days double-counts members who enable the skill on more than one day, so it is also null in date-range rollup mode (starting_date/ending_date).

from line 2450

31312450

31322451 Opaque cursor for the next page, or null if no more results

31332452

3134### Example

3135

3136```http

2453#### Example

2454

2455```bash

31372456curl https://api.anthropic.com/v1/organizations/analytics/skills \

31382457 -H 'anthropic-version: 2023-06-01' \

31392458 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

31402459```

31412460

3142#### Response

2461##### Response (200)

31432462

31442463```json

31452464{

from line 2506

31872506}

31882507```

31892508

3190## Domain Types

3191

3192### Skill Usage

3193

3194- `SkillUsage object { data, next_page }`

3195

3196 Response for GET /v1/organizations/analytics/skills.

3197

3198 - `data: array of object { chat_metrics, claude_code_metrics, cowork_metrics, 14 more }`

3199

3200 - `chat_metrics: object { distinct_conversation_skill_used_count }`

3201

3202 Claude.ai activity metrics for a single skill on a given day.

3203

3204 - `distinct_conversation_skill_used_count: number or null`

3205

3206 Number of distinct conversations in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3207

3208 - `claude_code_metrics: object { distinct_session_skill_used_count }`

3209

3210 Claude Code activity metrics for a single skill on a given day.

3211

3212 - `distinct_session_skill_used_count: number or null`

3213

3214 Number of distinct Claude Code sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3215

3216 - `cowork_metrics: object { distinct_session_skill_used_count }`

3217

3218 Cowork activity metrics for a single skill on a given day.

3219

3220 - `distinct_session_skill_used_count: number or null`

3221

3222 Number of distinct Cowork sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3223

3224 - `distinct_user_count: number`

3225

3226 Number of distinct users who used the skill on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted.

3227

3228 - `office_metrics: object { excel, outlook, powerpoint, word }`

3229

3230 Office Agent activity metrics for a single skill on a given day, broken out by Office product.

3231

3232 - `excel: SkillOfficeProductMetrics`

3233

3234 Office Agent activity metrics for a single skill on a given day within one Office product.

3235

3236 - `distinct_session_skill_used_count: number or null`

3237

3238 Number of distinct Office Agent sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3239

3240 - `outlook: SkillOfficeProductMetrics`

3241

3242 Office Agent activity metrics for a single skill on a given day within one Office product.

3243

3244 - `powerpoint: SkillOfficeProductMetrics`

3245

3246 Office Agent activity metrics for a single skill on a given day within one Office product.

3247

3248 - `word: SkillOfficeProductMetrics`

3249

3250 Office Agent activity metrics for a single skill on a given day within one Office product.

3251

3252 - `skill_name: string`

3253

3254 Name of the skill

3255

3256 - `attributed_list_price: optional string or null`

3257

3258 List-price (rate-card) value of the member requests attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD), from Claude Code, Cowork, and Office Agent request-level attribution — the value of requests that INVOLVED the skill, not the skill's incremental cost. Unlike estimated_overage_spend this reflects usage value regardless of how it was funded — seat-covered usage counts — but it is undiscounted and does NOT tie to billed spend or the organization's spend reporting. claude.ai chat usage carries no request-level attribution and contributes nothing: the field is null on chat product rows and on office_agent product cuts dated before 2026-06-18 (the Office Agent attribution data-start), and on ungrouped rows it covers the Claude Code + Cowork + Office Agent share only (null when no attributable usage exists). Also null under the same conditions as estimated_overage_spend (spend reporting not enabled for this organization, office_agent product cuts before the 2026-06-18 data-start). "0" means attributable usage existed but none was attributed to this skill. Addable across days: date-range rollup mode returns the window's sum. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts.

3259

3260 - `currency: optional "USD" or null`

3261

3262 Currency for this row's monetary fields (estimated_overage_spend and attributed_list_price), as an uppercase ISO-4217 code. Always "USD" when either amount is populated; null whenever both amounts are null.

3263

3264 - `"USD"`

3265

3266 - `enable_count: optional number or null`

3267

3268 Distinct accounts that enabled this skill on the requested day (claude.ai only — the skill analog of plugin install_count). The count is org-wide: null when enable reporting is not enabled for this organization, or when the request scopes to `user_id` / `rbac_group_id` / `product` via `group_by[]` or `filter[]` (an org-wide count would be misleading on per-cut rows). A distinct count, not an event count: summing across days double-counts members who enable the skill on more than one day, so it is also null in date-range rollup mode (starting_date/ending_date).

3269

3270 - `estimated_overage_spend: optional string or null`

3271

3272 Estimated OVERAGE spend attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD; "1250" is $12.50, fractional cents possible) — an allocation of each member's daily post-discount, pre-credit metered overage spend (the same cost basis as the organization's spend reporting and the Cost & Usage API, so per-skill figures are directly comparable; spend with no skill attribution — including any member-day without skill invocations — is not represented, so skill rows sum to at most those totals) across the skills the member used. Overage only: usage covered by included seat allowances bills nothing and allocates $0 here — see attributed_list_price for the funding-independent usage-value companion. Claude Code, Cowork, and Office Agent spend use request-level skill attribution; claude.ai chat spend is approximated proportionally to skill-invoking messages. An estimate, not a billing number — and the cost of the requests/messages that INVOLVED the skill, not the skill's incremental cost (the same request would still have cost something without the skill active). "0" means no overage spend was attributed; null when spend reporting is not enabled for this organization, on office_agent product cuts dated before 2026-06-18 (the Office Agent attribution data-start). Addable across days: date-range rollup mode (starting_date/ending_date) returns the window's sum. With `group_by[]=user_id` each row carries the user's own attributed spend. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts.

3273

3274 - `invocation_count: optional number or null`

3275

3276 Total number of times this skill was invoked on the requested day (the skill analog of plugin invocation_count). Unlike distinct_user_count — which answers '\# of users' — this is the true '# of uses'. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Null when invocation reporting is not enabled for this organization. Sum across a date range for total uses in the window — date-range rollup mode (starting_date/ending_date) returns this sum directly.

3277

3278 - `product: optional string or null`

3279

3280 Product that produced this row's activity: one of chat, claude_code, cowork, or office_agent (the canonical Cost & Usage product naming; an office_agent row's per-surface breakdown is in its office_metrics). On /plugins only cowork and claude_code occur (the only surfaces with plugin attribution); /artifacts and /apps/chat/projects do not support the product dimension (a product `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by product.

3281

3282 - `rbac_group_id: optional string or null`

3283

3284 Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`.

3285

3286 - `rbac_group_name: optional string or null`

3287

3288 Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key.

3289

3290 - `share_status: optional string or null`

3291

3292 Skill share status (claude.ai only): one of 'private', 'organization', or 'public'. Null for skills used only in Claude Code or Office (no per-skill share-status concept) and when share-status reporting is not yet available for the organization. Filterable via `filter[]=share_status:<value>`.

3293

3294 - `skill_display_name: optional string or null`

3295

3296 Human-readable display name for rows whose skill_name is an opaque skill id (user/organization skill types — user-defined names are withheld from the analytics pipeline). Only organization-shared skills resolve; the literal 'unknown' bucket row also gets a fixed 'Unknown skill' label. Null for private (user-defined) skills — their names are not disclosed to analytics-key holders — and null when skill_name is already a display name, when the skill was deleted, or when display-name resolution is not enabled for this organization.

3297

3298 - `user_id: optional string or null`

3299

3300 Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`.

3301

3302 - `next_page: string or null`

3303

3304 Opaque cursor for the next page, or null if no more results

3305

3306# Connectors

3307

3308## Get Connector Usage

3309

3310**get** `/v1/organizations/analytics/connectors`

2509## Analytics › Connectors

2510

2511### Get Connector Usage

2512

2513**GET** `/v1/organizations/analytics/connectors`

33112514

33122515Get per-connector usage for a given day, with cursor-based pagination.

33132516

from line 2523

33202523organizations on a Claude Enterprise plan. Requires an API key with the

33212524`read:analytics` scope.

33222525

3323### Query Parameters

2526#### Query parameters

33242527

33252528- `date: optional string`

33262529

33272530 UTC date in YYYY-MM-DD format. The day to get connector usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

33282531

2532 format: date

2533

33292534- `ending_date: optional string`

33302535

33312536 UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with starting_date. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after starting_date.

33322537

2538 format: date

2539

33332540- `filter: optional array of string`

33342541

33352542 Filters as 'dimension:value', e.g. filter[]=rbac_group_id:<id>. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: connector_name, product, rbac_group_id, user_id. Value forms: connector_name matches case-insensitively, a display name such as 'GitHub MCP' also matches its normalized stored form ('github'), and for rows whose connector_name is an opaque connector id the connector's display name (connector_display_name) also matches; product is one of chat, claude_code, cowork, or office_agent; rbac_group_id takes the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); user_id takes a tagged user id (user_...), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.

33362543

2544 maxItems: 100

2545

33372546- `group_by: optional array of "product" or "rbac_group_id" or "user_id"`

33382547

33392548 Dimensions to break results out by (e.g. group_by[]=user_id). Supported on this endpoint: product, rbac_group_id, user_id. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via next_page; an unsupported dimension returns 400. rbac_group_id attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries.

33402549

2550 maxItems: 100

2551

33412552 - `"product"`

33422553

33432554 - `"rbac_group_id"`

from line 2559

33482559

33492560 Number of results per page (1-1000, default 100).

33502561

2562 minimum: 1, maximum: 1000

2563

33512564- `order: optional "asc" or "desc"`

33522565

33532566 Sort direction: 'asc' or 'desc'. Defaults to 'asc' for the endpoint's sort column and to 'desc' when order_by names a metric (a top-N ranking). Applies to order_by, or to the endpoint's default sort field when order_by is omitted.

from line 2581

33682581

33692582 UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either date or starting_date, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

33702583

3371### Returns

3372

3373- `ConnectorUsage object { data, next_page }`

2584 format: date

2585

2586#### Returns

2587

2588- `ConnectorUsage object`

33742589

33752590 Response for GET /v1/organizations/analytics/connectors.

33762591

3377 - `data: array of object { chat_metrics, claude_code_metrics, connector_name, 13 more }`

3378

3379 - `chat_metrics: object { distinct_conversation_connector_used_count }`

2592 - `data: array of object`

2593

2594 - `chat_metrics: object`

33802595

33812596 Claude.ai activity metrics for a single connector on a given day.

33822597

from line 2599

33842599

33852600 Number of distinct conversations in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

33862601

3387 - `claude_code_metrics: object { distinct_session_connector_used_count }`

2602 - `claude_code_metrics: object`

33882603

33892604 Claude Code activity metrics for a single connector on a given day.

33902605

from line 2611

33962611

33972612 Name of the connector. Some rows carry an opaque connector id here instead of a readable name; connector_display_name holds the resolved name for those rows.

33982613

3399 - `cowork_metrics: object { distinct_session_connector_used_count }`

2614 - `cowork_metrics: object`

34002615

34012616 Cowork activity metrics for a single connector on a given day.

34022617

from line 2623

34082623

34092624 Number of distinct users who used the connector on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values.

34102625

3411 - `office_metrics: object { excel, outlook, powerpoint, word }`

2626 - `office_metrics: object`

34122627

34132628 Office Agent activity metrics for a single connector on a given day, broken out by Office product.

34142629

from line 2691

34762691

34772692 Opaque cursor for the next page, or null if no more results

34782693

3479### Example

3480

3481```http

2694#### Example

2695

2696```bash

34822697curl https://api.anthropic.com/v1/organizations/analytics/connectors \

34832698 -H 'anthropic-version: 2023-06-01' \

34842699 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

34852700```

34862701

3487#### Response

2702##### Response (200)

34882703

34892704```json

34902705{

from line 2746

35312746}

35322747```

35332748

3534## Domain Types

3535

3536### Connector Usage

3537

3538- `ConnectorUsage object { data, next_page }`

3539

3540 Response for GET /v1/organizations/analytics/connectors.

3541

3542 - `data: array of object { chat_metrics, claude_code_metrics, connector_name, 13 more }`

3543

3544 - `chat_metrics: object { distinct_conversation_connector_used_count }`

3545

3546 Claude.ai activity metrics for a single connector on a given day.

3547

3548 - `distinct_conversation_connector_used_count: number or null`

3549

3550 Number of distinct conversations in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3551

3552 - `claude_code_metrics: object { distinct_session_connector_used_count }`

3553

3554 Claude Code activity metrics for a single connector on a given day.

3555

3556 - `distinct_session_connector_used_count: number or null`

3557

3558 Number of distinct Claude Code sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3559

3560 - `connector_name: string`

3561

3562 Name of the connector. Some rows carry an opaque connector id here instead of a readable name; connector_display_name holds the resolved name for those rows.

3563

3564 - `cowork_metrics: object { distinct_session_connector_used_count }`

3565

3566 Cowork activity metrics for a single connector on a given day.

3567

3568 - `distinct_session_connector_used_count: number or null`

3569

3570 Number of distinct Cowork sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3571

3572 - `distinct_user_count: number`

3573

3574 Number of distinct users who used the connector on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values.

3575

3576 - `office_metrics: object { excel, outlook, powerpoint, word }`

3577

3578 Office Agent activity metrics for a single connector on a given day, broken out by Office product.

3579

3580 - `excel: ConnectorOfficeProductMetrics`

3581

3582 Office Agent activity metrics for a single connector on a given day within one Office product.

3583

3584 - `distinct_session_connector_used_count: number or null`

3585

3586 Number of distinct Office Agent sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

3587

3588 - `outlook: ConnectorOfficeProductMetrics`

3589

3590 Office Agent activity metrics for a single connector on a given day within one Office product.

3591

3592 - `powerpoint: ConnectorOfficeProductMetrics`

3593

3594 Office Agent activity metrics for a single connector on a given day within one Office product.

3595

3596 - `word: ConnectorOfficeProductMetrics`

3597

3598 Office Agent activity metrics for a single connector on a given day within one Office product.

3599

3600 - `connector_display_name: optional string or null`

3601

3602 Human-readable display name for rows whose connector_name is an opaque connector id rather than a readable name, resolved at request time from the organization's connectors (including connectors that have since been removed). connector_name remains the row's stable key for sorting and pagination, and filter[]=connector_name:<value> also matches these rows by display name. Display names are not unique, and the same connector's claude.ai usage can appear under a separate row with a readable connector_name. Null when connector_name is already a readable name, when the id cannot be resolved to one of the organization's connectors, or when display-name resolution is not enabled for this organization.

3603

3604 - `individual_auth_distinct_user_count: optional number or null`

3605

3606 Number of distinct users whose use of this connector on the requested day ran on their own individual credential, connected through their own consent flow. Companion bucket to managed_auth_distinct_user_count, which carries the measurement, attribution, and null rules. Users whose requests used no stored credential count in neither bucket.

3607

3608 - `managed_auth_distinct_user_count: optional number or null`

3609

3610 Number of distinct users whose use of this connector on the requested day ran on Enterprise Managed Auth (an organization-managed credential provisioned through the organization's identity provider), read from the token record each request used. Null, never 0, when managed-auth reporting is not enabled for the organization, the value cannot be attributed to the row, no credentialed requests and no managed-token mint events (a managed credential being provisioned for a user's use of the connector) were observed that day, or the day predates 2026-07-01, the first day the backing data exists (forward-only data, no backfill). When credentialed requests or mint events were observed and attributed, both managed-auth fields populate, reporting 0 for a bucket with no users; the two counts are independent, not a partition — a user whose requests that day used both kinds of credential counts in both. Mint events carry user but not surface attribution, so they count as observed auth activity on user_id and rbac_group_id cuts — attributed to the user the credential was provisioned for — but never on a cut that references product (group or filter). Date-range rollup mode (starting_date/ending_date) computes both fields exactly over the window — distinct users with at least one qualifying day — when the whole window starts on or after 2026-07-01, with the null-versus-0 and mint-event rules applying with the window in place of the day; a range starting earlier reports every managed-auth field as null, never a partial-window value.

3611

3612 - `product: optional string or null`

3613

3614 Product that produced this row's activity: one of chat, claude_code, cowork, or office_agent (the canonical Cost & Usage product naming; an office_agent row's per-surface breakdown is in its office_metrics). On /plugins only cowork and claude_code occur (the only surfaces with plugin attribution); /artifacts and /apps/chat/projects do not support the product dimension (a product `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by product.

3615

3616 - `rbac_group_id: optional string or null`

3617

3618 Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`.

3619

3620 - `rbac_group_name: optional string or null`

3621

3622 Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key.

3623

3624 - `read_call_count: optional number or null`

3625

3626 Number of connector tool calls on the requested day whose trusted read-only annotation marked them read-only. Call count, not distinct users. Every call recorded on a classified surface lands in exactly one of read_call_count, write_call_count, or unclassified_call_count, so the three sum to the day's classified calls. Classification is forward-only per surface: claude.ai from 2026-06-01, Claude Code from 2026-05-30, Claude in Office from 2026-05-29, Cowork from 2026-06-02 (Cowork clients predating annotation forwarding land in unclassified_call_count). Null, never 0, when the value cannot be stated: the read/write split is not enabled for this organization, or the day predates 2026-05-29. For a date-range total, sum the per-day values, but treat a window that extends before 2026-05-29 as null rather than summing only its covered days — date-range rollup mode (starting_date/ending_date) applies both rules server-side.

3627

3628 - `unclassified_call_count: optional number or null`

3629

3630 Number of connector tool calls on the requested day with no trusted read-only annotation — the annotation is optional in the MCP spec and is discarded when connector access controls are active, so unclassified calls are common. This field shows how much of the day's classified activity the read/write split actually covers. Call count, not distinct users. One of the three call-classification buckets; see read_call_count for the per-surface data-start dates, null conditions, and date-range guidance.

3631

3632 - `user_id: optional string or null`

3633

3634 Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`.

3635

3636 - `write_call_count: optional number or null`

3637

3638 Number of connector tool calls on the requested day whose trusted read-only annotation marked them not read-only. Call count, not distinct users. One of the three call-classification buckets; see read_call_count for the per-surface data-start dates, null conditions, and date-range guidance.

3639

3640 - `next_page: string or null`

3641

3642 Opaque cursor for the next page, or null if no more results

3643

3644# Chat Projects

3645

3646## Get Chat Project Usage

3647

3648**get** `/v1/organizations/analytics/apps/chat/projects`

2749## Analytics › Chat Projects

2750

2751### Get Chat Project Usage

2752

2753**GET** `/v1/organizations/analytics/apps/chat/projects`

36492754

36502755Get per-project activity for a given day, with cursor-based pagination.

36512756

from line 2760

36552760supported dimensions. Available to organizations on a Claude Enterprise

36562761plan. Requires an API key with the `read:analytics` scope.

36572762

3658### Query Parameters

2763#### Query parameters

36592764

36602765- `date: optional string`

36612766

36622767 UTC date in YYYY-MM-DD format. The day to get project activity for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

36632768

2769 format: date

2770

36642771- `ending_date: optional string`

36652772

36662773 UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with starting_date. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after starting_date.

36672774

2775 format: date

2776

36682777- `filter: optional array of string`

36692778

36702779 Filters as 'dimension:value', e.g. filter[]=rbac_group_id:<id>. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: project_id, rbac_group_id, user_id. Value forms: project_id takes a tagged project id (claude_proj_...); rbac_group_id takes the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); user_id takes a tagged user id (user_...), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.

36712780

2781 maxItems: 100

2782

36722783- `group_by: optional array of "rbac_group_id" or "user_id"`

36732784

36742785 Dimensions to break results out by (e.g. group_by[]=user_id). Supported on this endpoint: rbac_group_id, user_id. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via next_page; an unsupported dimension returns 400. rbac_group_id attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries.

36752786

2787 maxItems: 100

2788

36762789 - `"rbac_group_id"`

36772790

36782791 - `"user_id"`

from line 2794

36812794

36822795 Number of results per page (1-1000, default 100).

36832796

2797 minimum: 1, maximum: 1000

2798

36842799- `order: optional "asc" or "desc"`

36852800

36862801 Sort direction: 'asc' or 'desc'. Defaults to 'asc' for the endpoint's sort column and to 'desc' when order_by names a metric (a top-N ranking). Applies to order_by, or to the endpoint's default sort field when order_by is omitted.

from line 2816

37012816

37022817 UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either date or starting_date, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

37032818

3704### Returns

3705

3706- `ChatProjectUsage object { data, next_page }`

2819 format: date

2820

2821#### Returns

2822

2823- `ChatProjectUsage object`

37072824

37082825 Response for GET /v1/organizations/analytics/apps/chat/projects.

37092826

3710 - `data: array of object { distinct_user_count, message_count, project_id, 8 more }`

2827 - `data: array of object`

37112828

37122829 - `distinct_user_count: number`

37132830

from line 2862

37452862

37462863 Object type. Always `user`.

37472864

3748 - `"user"`

2865 default: user

37492866

37502867 - `distinct_conversation_count: optional number or null`

37512868

from line 2888

37712888

37722889 Opaque cursor for the next page, or null if no more results

37732890

3774### Example

3775

3776```http

2891#### Example

2892

2893```bash

37772894curl https://api.anthropic.com/v1/organizations/analytics/apps/chat/projects \

37782895 -H 'anthropic-version: 2023-06-01' \

37792896 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

37802897```

37812898

3782#### Response

2899##### Response (200)

37832900

37842901```json

37852902{

from line 2923

38062923}

38072924```

38082925

3809## Domain Types

3810

3811### Chat Project Usage

3812

3813- `ChatProjectUsage object { data, next_page }`

3814

3815 Response for GET /v1/organizations/analytics/apps/chat/projects.

3816

3817 - `data: array of object { distinct_user_count, message_count, project_id, 8 more }`

3818

3819 - `distinct_user_count: number`

3820

3821 Number of distinct users who used the project on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values.

3822

3823 - `message_count: number`

3824

3825 Number of messages sent in the project on the requested day

3826

3827 - `project_id: string`

3828

3829 Tagged project identifier (e.g. claude_proj_...)

3830

3831 - `project_name: string`

3832

3833 Name of the project

3834

3835 - `created_at: optional string or null`

3836

3837 Project creation timestamp, RFC 3339. Null if the project was deleted before attribution was recorded.

3838

3839 - `created_by: optional AnalyticsUser or null`

3840

3841 User identifier.

3842

3843 - `id: string`

3844

3845 Tagged user identifier (e.g. `user_...`)

3846

3847 - `email_address: string`

3848

3849 Email address of the user

3850

3851 - `type: optional "user"`

3852

3853 Object type. Always `user`.

3854

3855 - `"user"`

3856

3857 - `distinct_conversation_count: optional number or null`

3858

3859 Number of distinct conversations in the project. Null on aggregated rows where a distinct count cannot be computed.

3860

3861 - `product: optional string or null`

3862

3863 Product that produced this row's activity: one of chat, claude_code, cowork, or office_agent (the canonical Cost & Usage product naming; an office_agent row's per-surface breakdown is in its office_metrics). On /plugins only cowork and claude_code occur (the only surfaces with plugin attribution); /artifacts and /apps/chat/projects do not support the product dimension (a product `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by product.

3864

3865 - `rbac_group_id: optional string or null`

3866

3867 Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`.

3868

3869 - `rbac_group_name: optional string or null`

3870

3871 Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key.

3872

3873 - `user_id: optional string or null`

3874

3875 Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`.

3876

3877 - `next_page: string or null`

3878

3879 Opaque cursor for the next page, or null if no more results

3880

3881# Plugins

3882

3883## Get Plugin Usage

3884

3885**get** `/v1/organizations/analytics/plugins`

2926## Analytics › Plugins

2927

2928### Get Plugin Usage

2929

2930**GET** `/v1/organizations/analytics/plugins`

38862931

38872932Get per-plugin install + invocation usage for a given day, with pagination.

38882933

from line 2943

38982943`read:analytics` scope. `starting_date` / `ending_date` select

38992944range-rollup mode like /skills.

39002945

3901### Query Parameters

2946#### Query parameters

39022947

39032948- `date: optional string`

39042949

39052950 UTC date in YYYY-MM-DD format. The day to get plugin usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

39062951

2952 format: date

2953

39072954- `ending_date: optional string`

39082955

39092956 UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with starting_date. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after starting_date.

39102957

2958 format: date

2959

39112960- `filter: optional array of string`

39122961

39132962 Filters as 'dimension:value', e.g. filter[]=rbac_group_id:<id>. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: plugin_name, product, rbac_group_id, user_id. Value forms: plugin_name matches case-insensitively; product is claude_code or cowork (the only surfaces with plugin attribution); rbac_group_id takes the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); user_id takes a tagged user id (user_...), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.

39142963

2964 maxItems: 100

2965

39152966- `group_by: optional array of "product" or "rbac_group_id" or "user_id"`

39162967

39172968 Dimensions to break results out by (e.g. group_by[]=user_id). Supported on this endpoint: product, rbac_group_id, user_id. On this endpoint product takes the values claude_code or cowork only (the surfaces with plugin attribution). Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via next_page; an unsupported dimension returns 400. rbac_group_id attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries.

39182969

2970 maxItems: 100

2971

39192972 - `"product"`

39202973

39212974 - `"rbac_group_id"`

from line 2979

39262979

39272980 Number of results per page (1-1000, default 100).

39282981

2982 minimum: 1, maximum: 1000

2983

39292984- `order: optional "asc" or "desc"`

39302985

39312986 Sort direction: 'asc' or 'desc'. Defaults to 'asc' for the endpoint's sort column and to 'desc' when order_by names a metric (a top-N ranking). Applies to order_by, or to the endpoint's default sort field when order_by is omitted.

from line 3001

39463001

39473002 UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either date or starting_date, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

39483003

3949### Returns

3950

3951- `PluginUsage object { data, next_page }`

3004 format: date

3005

3006#### Returns

3007

3008- `PluginUsage object`

39523009

39533010 Response for GET /v1/organizations/analytics/plugins.

39543011

3955 - `data: array of object { claude_code_metrics, cowork_metrics, distinct_user_count, 8 more }`

3956

3957 - `claude_code_metrics: object { distinct_session_plugin_used_count }`

3012 - `data: array of object`

3013

3014 - `claude_code_metrics: object`

39583015

39593016 Claude Code activity metrics for a single plugin on a given day.

39603017

from line 3019

39623019

39633020 Number of distinct Claude Code sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

39643021

3965 - `cowork_metrics: object { distinct_session_plugin_used_count }`

3022 - `cowork_metrics: object`

39663023

39673024 Cowork activity metrics for a single plugin on a given day.

39683025

from line 3067

40103067

40113068 Opaque cursor for the next page, or null if no more results

40123069

4013### Example

4014

4015```http

3070#### Example

3071

3072```bash

40163073curl https://api.anthropic.com/v1/organizations/analytics/plugins \

40173074 -H 'anthropic-version: 2023-06-01' \

40183075 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

40193076```

40203077

4021#### Response

3078##### Response (200)

40223079

40233080```json

40243081{

from line 3102

40453102}

40463103```

40473104

4048## Domain Types

4049

4050### Plugin Usage

4051

4052- `PluginUsage object { data, next_page }`

4053

4054 Response for GET /v1/organizations/analytics/plugins.

4055

4056 - `data: array of object { claude_code_metrics, cowork_metrics, distinct_user_count, 8 more }`

4057

4058 - `claude_code_metrics: object { distinct_session_plugin_used_count }`

4059

4060 Claude Code activity metrics for a single plugin on a given day.

4061

4062 - `distinct_session_plugin_used_count: number or null`

4063

4064 Number of distinct Claude Code sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

4065

4066 - `cowork_metrics: object { distinct_session_plugin_used_count }`

4067

4068 Cowork activity metrics for a single plugin on a given day.

4069

4070 - `distinct_session_plugin_used_count: number or null`

4071

4072 Number of distinct Cowork sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

4073

4074 - `distinct_user_count: number`

4075

4076 Number of distinct users with recorded install or invocation activity for the plugin on the requested day (install-only users count), or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values.

4077

4078 - `install_count: number or null`

4079

4080 Number of distinct users who installed the plugin on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values.

4081

4082 - `invocation_count: number`

4083

4084 Number of plugin invocations on the requested day

4085

4086 - `plugin_name: string`

4087

4088 Name of the plugin

4089

4090 - `plugin_id: optional string or null`

4091

4092 Stable plugin identifier when available (e.g. serena@claude-plugins-official). Null for third-party Claude Code plugins (redacted at the source) and Cowork slash commands that carry only a hashed id.

4093

4094 - `product: optional string or null`

4095

4096 Product that produced this row's activity: one of chat, claude_code, cowork, or office_agent (the canonical Cost & Usage product naming; an office_agent row's per-surface breakdown is in its office_metrics). On /plugins only cowork and claude_code occur (the only surfaces with plugin attribution); /artifacts and /apps/chat/projects do not support the product dimension (a product `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by product.

4097

4098 - `rbac_group_id: optional string or null`

4099

4100 Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`.

4101

4102 - `rbac_group_name: optional string or null`

4103

4104 Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key.

4105

4106 - `user_id: optional string or null`

4107

4108 Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`.

4109

4110 - `next_page: string or null`

4111

4112 Opaque cursor for the next page, or null if no more results

4113

4114# Artifacts

4115

4116## Get Artifact Activity

4117

4118**get** `/v1/organizations/analytics/artifacts`

3105## Analytics › Artifacts

3106

3107### Get Artifact Activity

3108

3109**GET** `/v1/organizations/analytics/artifacts`

41193110

41203111Get artifact-creation activity for a given day, broken out by MIME type.

41213112

from line 3115

41243115can be broken out per member or per RBAC group via group_by[], and scoped

41253116via filter[]. Requires an API key with the `read:analytics` scope.

41263117

4127### Query Parameters

3118#### Query parameters

41283119

41293120- `date: string`

41303121

41313122 UTC date in YYYY-MM-DD format. The day to get artifact activity for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

41323123

3124 format: date

3125

41333126- `filter: optional array of string`

41343127

41353128 Filters as 'dimension:value', e.g. filter[]=rbac_group_id:<id>. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: artifact_type, is_shared, rbac_group_id, user_id. Value forms: artifact_type is a canonical artifact MIME type (e.g. text/markdown) or 'other'; is_shared is 'true' or 'false'; rbac_group_id takes the tagged id (rbac_group_..., as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); user_id takes a tagged user id (user_...), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.

41363129

3130 maxItems: 100

3131

41373132- `group_by: optional array of "rbac_group_id" or "user_id"`

41383133

41393134 Dimensions to break results out by: user_id and/or rbac_group_id. The ungrouped artifact-type cube is finite and returned in full; grouped queries multiply the cube and paginate via next_page. rbac_group_id attributes a user to every group they held at any point during the requested UTC day, so grouped rows are not an exclusive partition. At most 100 entries.

41403135

3136 maxItems: 100

3137

41413138 - `"rbac_group_id"`

41423139

41433140 - `"user_id"`

from line 3143

41463143

41473144 Maximum rows to return (1-1000, default 100). The ungrouped artifact-type cube is finite and returned in full; limit is the page size only when group_by[] multiplies the cube.

41483145

3146 minimum: 1, maximum: 1000

3147

41493148- `page: optional string`

41503149

41513150 Opaque cursor from a previous response's next_page field. Only valid with group_by[] — the ungrouped cube is never paginated.

41523151

4153### Returns

4154

4155- `ArtifactUsage object { data, next_page }`

3152#### Returns

3153

3154- `ArtifactUsage object`

41563155

41573156 Response for GET /v1/organizations/analytics/artifacts.

41583157

from line 3160

41613160 `rbac_group_id`) multiply the cube and paginate like the other analytics

41623161 list endpoints.

41633162

4164 - `data: array of object { artifact_type, artifacts_created_count, distinct_user_count, 6 more }`

3163 - `data: array of object`

41653164

41663165 - `artifact_type: string`

41673166

from line 3202

42033202

42043203 Cursor for the next page of a grouped query; always null for the ungrouped artifact-type cube, which is returned in full.

42053204

4206### Example

4207

4208```http

3205#### Example

3206

3207```bash

42093208curl https://api.anthropic.com/v1/organizations/analytics/artifacts \

42103209 -H 'anthropic-version: 2023-06-01' \

42113210 -H "X-Api-Key: $ANTHROPIC_ADMIN_API_KEY"

42123211```

42133212

4214#### Response

3213##### Response (200)

42153214

42163215```json

42173216{

from line 3230

42313230 "next_page": "next_page"

42323231}

42333232```

4234

4235## Domain Types

4236

4237### Artifact Usage

4238

4239- `ArtifactUsage object { data, next_page }`

4240

4241 Response for GET /v1/organizations/analytics/artifacts.

4242

4243 `next_page` is null on ungrouped queries — the artifact-type cube is

4244 finite and returned in full. Grouped queries (`group_by[]` on `user_id` /

4245 `rbac_group_id`) multiply the cube and paginate like the other analytics

4246 list endpoints.

4247

4248 - `data: array of object { artifact_type, artifacts_created_count, distinct_user_count, 6 more }`

4249

4250 - `artifact_type: string`

4251

4252 Canonical artifact MIME type (e.g. text/markdown, application/vnd.ant.react, image/svg+xml), or 'other'.

4253

4254 - `artifacts_created_count: number`

4255

4256 Number of artifacts created in this bucket on the requested day

4257

4258 - `distinct_user_count: number`

4259

4260 Number of distinct users who created artifacts in this bucket on the requested day

4261

4262 - `is_shared: boolean`

4263

4264 Whether the artifacts in this bucket have ever been shared.

4265

4266 - `published_artifacts_created_count: number`

4267

4268 Number of those artifacts that have been published

4269

4270 - `product: optional string or null`

4271

4272 Product that produced this row's activity: one of chat, claude_code, cowork, or office_agent (the canonical Cost & Usage product naming; an office_agent row's per-surface breakdown is in its office_metrics). On /plugins only cowork and claude_code occur (the only surfaces with plugin attribution); /artifacts and /apps/chat/projects do not support the product dimension (a product `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by product.

4273

4274 - `rbac_group_id: optional string or null`

4275

4276 Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`.

4277

4278 - `rbac_group_name: optional string or null`

4279

4280 Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key.

4281

4282 - `user_id: optional string or null`

4283

4284 Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`.

4285

4286 - `next_page: optional string or null`

4287

4288 Cursor for the next page of a grouped query; always null for the ungrouped artifact-type cube, which is returned in full.

42893233

This page’s history 6 edits

10 Sep 2026 +0 −3504
4 Sep 2026 +189 −5
28 Aug 2026 +243 −155
25 Aug 2026 +398 −1454 · this one
21 Aug 2026 +11 −11
14 Aug 2026 +4288 −0

The page’s own history →

Where it came from

The captureapi
Upstream pageplatform.claude.com

Around it

Every changethe ledger
That day25 Aug 2026