Source Intelligence
Sweep 28 Aug 2026 ยท 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

One change

Get Claude Code Usage Report

api/admin/usage_report/retrieve_claude_code

first seen The page's own history The capture it came from

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.

api/admin/usage_report/retrieve_claude_code Changed · +28 / -31 lines

# Get Claude Code Usage Report ## Query parameters ## Returns ## Example ### Response (200) ## Get Claude Code Usage Report ### Query Parameters ### Returns ### Example #### Response

from line 1
----
-title: Get Claude Code Usage Report
-url: https://platform.claude.com/docs/en/api/admin/usage_report/retrieve_claude_code
----
+# Get Claude Code Usage Report
 
-## Get Claude Code Usage Report
+**GET** `/v1/organizations/usage_report/claude_code`
 
-**get** `/v1/organizations/usage_report/claude_code`
-
 Retrieve daily aggregated usage metrics for Claude Code users.
 Enables organizations to analyze developer productivity and build custom dashboards.
 
-### Query Parameters
+## Query parameters
 
 - `starting_at: string`
 
   UTC date in YYYY-MM-DD format. Returns metrics for this single day only.
 
+  pattern: ^\d{4}-\d{2}-\d{2}$
+
 - `limit: optional number`
 
   Number of records per page (default: 20, max: 1000).
 
+  default: 20, maximum: 1000, minimum: 1
+
 - `page: optional string`
 
   Opaque cursor token from previous response's `next_page` field.
 
-### Returns
+## Returns
 
-- `ClaudeCodeUsageReport object { data, has_more, next_page }`
+- `ClaudeCodeUsageReport object`
 
-  - `data: array of object { actor, core_metrics, customer_type, 7 more }`
+  - `data: array of object`
 
     List of Claude Code usage records for the requested date.
 
-    - `actor: object { email_address, type }  or object { api_key_name, type }`
+    - `actor: object or object`
 
       The user or API key that performed the Claude Code actions.
 
-      - `UserActor object { email_address, type }`
+      - `UserActor object`
 
         - `email_address: string`
 
from line 45
 
           Actor type. Always `"user_actor"` for a user.
 
-          - `"user_actor"`
+      - `APIActor object`
 
-      - `APIActor object { api_key_name, type }`
-
         - `api_key_name: string`
 
           Name of the API key used to perform Claude Code actions.
from line 55
 
           Actor type. Always `"api_actor"` for an API key.
 
-          - `"api_actor"`
+    - `core_metrics: object`
 
-    - `core_metrics: object { commits_by_claude_code, lines_of_code, num_sessions, pull_requests_by_claude_code }`
-
       Core productivity metrics measuring Claude Code usage and impact.
 
       - `commits_by_claude_code: number`
from line 63
 
         Number of git commits created through Claude Code's commit functionality.
 
-      - `lines_of_code: object { added, removed }`
+      - `lines_of_code: object`
 
         Statistics on code changes made through Claude Code.
 
from line 96
       UTC day the usage metrics cover, as an RFC 3339 timestamp at midnight UTC
       (for example `2025-08-08T00:00:00Z`).
 
+      format: date-time
+
     - `is_remote: boolean`
 
       Whether the usage came from remote Claude Code sessions, such as Claude Code
       on the web. Remote and local usage are reported as separate rows.
 
-    - `model_breakdown: array of object { estimated_cost, model, tokens }`
+    - `model_breakdown: array of object`
 
       Token usage and cost breakdown by AI model used.
 
-      - `estimated_cost: object { amount, currency }`
+      - `estimated_cost: object`
 
         Estimated cost for using this model
 
from line 123
 
         Name of the AI model used for Claude Code interactions.
 
-      - `tokens: object { cache_creation, cache_read, input, output }`
+      - `tokens: object`
 
         Token usage breakdown for this model
 
from line 151
 
       Type of terminal or environment where Claude Code was used.
 
-    - `tool_actions: map[object { accepted, rejected } ]`
+    - `tool_actions: map[object]`
 
       Breakdown of tool action acceptance and rejection rates by tool type.
 
from line 179
 
     Opaque cursor token for fetching the next page of results, or null if no more pages are available.
 
-### Example
+## Example
 
-```http
+```bash
 curl https://api.anthropic.com/v1/organizations/usage_report/claude_code \
     -H 'anthropic-version: 2023-06-01' \
     -H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
 ```
 
-#### Response
+### Response (200)
 
 ```json
 {