Skip to main content
GET
/
v1
/
organizations
/
usage_report
/
messages
cURL
curl "https://api.anthropic.com/v1/organizations/usage_report/messages\
?starting_at=2025-08-01T00:00:00Z\
&group_by[]=api_key_id\
&group_by[]=workspace_id\
&group_by[]=model\
&group_by[]=service_tier\
&group_by[]=context_window\
&limit=1" \
  --header "anthropic-version: 2023-06-01" \
  --header "content-type: application/json" \
  --header "x-api-key: $ANTHROPIC_ADMIN_KEY"
{
  "data": [
    {
      "starting_at": "2023-11-07T05:31:56Z",
      "ending_at": "2023-11-07T05:31:56Z",
      "results": [
        {
          "uncached_input_tokens": 123,
          "cache_creation": {
            "ephemeral_1h_input_tokens": 123,
            "ephemeral_5m_input_tokens": 123
          },
          "cache_read_input_tokens": 123,
          "output_tokens": 123,
          "server_tool_use": {
            "web_search_requests": 123
          },
          "api_key_id": "apikey_01Rj2N8SVvo6BePZj99NhmiT",
          "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ",
          "model": "claude-sonnet-4-20250514",
          "service_tier": "standard",
          "context_window": "0-200k"
        }
      ]
    }
  ],
  "has_more": true,
  "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo="
}

Documentation Index

Fetch the complete documentation index at: https://docs.claude.com/llms.txt

Use this file to discover all available pages before exploring further.

The Admin API is unavailable for individual accounts. To collaborate with teammates and add members, set up your organization in Console → Settings → Organization.

Headers

​
x-api-key
string
required

Your unique Admin API key for authentication.

This key is required in the header of all Admin API requests, to authenticate your account and access Anthropic's services. Get your Admin API key through the Console.

​
anthropic-version
string
required

The version of the Claude API you want to use.

Read more about versioning and our version history here.

Query Parameters

​
limit
integer

Maximum number of time buckets to return in the response.

The default and max limits depend on bucket_width: • "1d": Default of 7 days, maximum of 31 days • "1h": Default of 24 hours, maximum of 168 hours • "1m": Default of 60 minutes, maximum of 1440 minutes

Example:

7

​
page
string<date-time> | null

Optionally set to the next_page token from the previous response.

Example:

"page_MjAyNS0wNS0xNFQwMDowMDowMFo="

​
starting_at
string<date-time>
required

Time buckets that start on or after this RFC 3339 timestamp will be returned. Each time bucket will be snapped to the start of the minute/hour/day in UTC.

Example:

"2024-10-30T23:58:27.427722Z"

​
ending_at
string<date-time> | null

Time buckets that end before this RFC 3339 timestamp will be returned.

Example:

"2024-10-30T23:58:27.427722Z"

​
api_key_ids[]
string[] | null

Restrict usage returned to the specified API key ID(s).

Example:

"apikey_01Rj2N8SVvo6BePZj99NhmiT"

​
workspace_ids[]
string[] | null

Restrict usage returned to the specified workspace ID(s).

Example:

"wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ"

​
models[]
string[] | null

Restrict usage returned to the specified model(s).

Example:

"claude-sonnet-4-20250514"

​
service_tiers[]
enum<string>[] | null

Restrict usage returned to the specified service tier(s).

Available options:
standard,
batch,
priority
Example:

"standard"

​
context_window[]
enum<string>[] | null

Restrict usage returned to the specified context window(s).

Available options:
0-200k,
200k-1M
Example:

"0-200k"

​
group_by[]
enum<string>[] | null

Group by any subset of the available options.

Available options:
api_key_id,
workspace_id,
model,
service_tier,
context_window
Example:

"api_key_id"

​
bucket_width
enum<string>
default:1d

Time granularity of the response data.

Available options:
1d,
1m,
1h
Examples:

"1d"

"1m"

"1h"

Response

Successful Response

​
data
MessagesUsageReportTimeBucket · object[]
required
​
has_more
boolean
required

Indicates if there are more results.

​
next_page
string<date-time> | null
required

Token to provide in as page in the subsequent request to retrieve the next page of data.

Example:

"page_MjAyNS0wNS0xNFQwMDowMDowMFo="