Request Logs

GET /logs?range=<range>&after=<ts>&after_id=<id>&errors=<bool>&limit=<n>

Returns the full per-request log for your organization, ordered newest-first.

Query parameters

Parameter	Type	Required	Description
`range`	string	No	`15m`, `1h`, `6h`, `24h`, `7days`, `30days`. Default: `24h`.
`after`	RFC3339	No	Pagination cursor — timestamp of the last row of the previous page.
`after_id`	string	No	Pagination cursor — request_id of the last row, breaks timestamp ties.
`errors`	boolean	No	If `true`, only non-2xx requests.
`limit`	integer	No	Page size. Capped at 100. Default: 50.

Response

{
  "data": [
    {
      "id": "...",
      "model": "...",
      "api_key": "sk-...abcd",
      "status_code": 200,
      "ttft_ms": 210,
      "latency_ms": 420,
      "input_tokens": 123,
      "output_tokens": 45,
      "cached_tokens": 64,
      "cost": "0.00420000",
      "currency": "usd",
      "created_at": "2026-05-18 12:34:56.123456+00"
    }
  ],
  "has_more": true,
  "next_after": "2026-05-18 12:34:55.654321+00",
  "next_after_id": "..."
}

cost is denominated in currency — the org’s billing currency (usd or jpy); it is never a bare USD figure. When has_more is false, you’ve reached the end of the available range.

cached_tokens is the portion of input_tokens that was billed at the discounted cached input rate — a repeated prompt prefix. It is 0 when there was no cache hit and null on models without a cached rate.

Pagination

Pass next_after and next_after_id from the previous page as after and after_id. Using after alone is unsafe — multiple requests can share a millisecond timestamp.

Auth

API key or JWT + X-Org-ID. See Authentication.