apicheats.dev anthropic/llms.txt Raw .md
GET

GET /v1/organizations/usage_report/messages?beta=true — Claude API

Beta

Anthropic API key (required); https://api.anthropic.com

Claude API

Get Messages Usage Report

Base URL
https://api.anthropic.com
Auth
x-api-key: <ANTHROPIC_API_KEY>
Last verified
2026-10-20 · upstream hash matched
Actions Try in browser→
Agents: curl -H "Accept: text/markdown" this URL
→ 372 tokens · Vary: Accept

Critical gotchas

Authentication uses the x-api-key header and requests also require an anthropic-version header.

The official OpenAPI URL is discovered from the SDK repository manifest and must remain under Anthropic's trusted Stainless storage prefix.

cURL

curl -X GET 'https://api.anthropic.com/v1/organizations/usage_report/messages?beta=true&limit=10&page=example-page&starting_at=example-starting-at&ending_at=example-ending-at&api_key_ids%5B%5D=example&workspace_ids%5B%5D=example&account_ids%5B%5D=example&service_account_ids%5B%5D=example&models%5B%5D=example&service_tiers%5B%5D=example&context_window%5B%5D=example&inference_geos%5B%5D=example&speeds%5B%5D=example&group_by%5B%5D=example&bucket_width=1d' \  -H "x-api-key: $ANTHROPIC_API_KEY" \  -H 'anthropic-version: 2023-06-01'

Parameters

Name In Type Required Description
limit query integer No 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
page query string No Optionally set to the `next_page` token from the previous response.
starting_at query string Yes 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.
ending_at query string No Time buckets that end before this RFC 3339 timestamp will be returned.
api_key_ids[] query string[] No Restrict usage returned to the specified API key ID(s).
workspace_ids[] query string[] No Restrict usage returned to the specified workspace ID(s).
account_ids[] query string[] No Restrict usage returned to the specified user account ID(s).
service_account_ids[] query string[] No Restrict usage returned to the specified service account ID(s).
models[] query string[] No Restrict usage returned to the specified model(s).
service_tiers[] query string[] No Restrict usage returned to the specified service tier(s).
context_window[] query string[] No Restrict usage returned to the specified context window(s).
inference_geos[] query string[] No Restrict usage returned to the specified inference geo(s). Use `not_available` for models that do not support specifying `inference_geo`.
speeds[] query string[] No Restrict usage returned to the specified speed(s) (Claude Code research preview). Requires the `fast-mode-2026-02-01` beta header.
group_by[] query string[] No Group by any subset of the available options. Grouping by `speed` requires the `fast-mode-2026-02-01` beta header.
bucket_width query string No Time granularity of the response data.

Response 200 OK

{
  "data": [
    {
      "starting_at": "2026-09-03T00:00:00Z",
      "ending_at": "2026-09-03T00:00:00Z",
      "results": [
        {
          "uncached_input_tokens": 0,
          "cache_creation": {
            "ephemeral_1h_input_tokens": "[recursive or deeply nested schema]",
            "ephemeral_5m_input_tokens": "[recursive or deeply nested schema]"
          },
          "cache_read_input_tokens": 0,
          "output_tokens": 0,
          "server_tool_use": {
            "web_search_requests": "[recursive or deeply nested schema]"
          },
          "api_key_id": "string",
          "workspace_id": "string",
          "account_id": "string",
          "service_account_id": "string",
          "model": "string",
          "service_tier": "batch",
          "context_window": "0-200k",
          "inference_geo": "global"
        }
      ]
    }
  ],
  "has_more": true,
  "next_page": "string"
}
Get a free Claude API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.