Organization requests

Read request outcomes and usage across your organization. Prompts and completions are not returned.

GET /v1/org/requests

Authorization

Authorizationheader · string
Bearer $BOARDWALK_API_KEY. Requires requests:read.

Request

Request · cURL
curl "https://api.boardwalk.cloud/v1/org/requests?limit=50" \
  -H "Authorization: Bearer $BOARDWALK_API_KEY"

Query parameters

cursorstringoptional
Opaque next_cursor from the previous page, at most 256 characters. Keep all other filters unchanged.
limitintegeroptional
Page size from 1 to 200. Default: 50.
model_idstringoptional
Internal model ID.
api_key_idstringoptional
Filter by API key ID.
statusstringoptional
success, client_error, or server_error.
fromintegeroptional
Inclusive start time in epoch milliseconds.
tointegeroptional
Exclusive end time in epoch milliseconds. Must be later than from.

Response

Example response. IDs, token counts, and rates are illustrative.

200 · application/json
{
  "object": "list",
  "data": [
    {
      "id": "req_example",
      "object": "request",
      "state": "completed",
      "model_id": "mdl_example",
      "model": "support-agent",
      "api_key_id": "key_example",
      "endpoint": "/v1/chat/completions",
      "created_at": "2026-09-16T00:00:00.000Z",
      "status_code": 200,
      "input_tokens": 100,
      "output_tokens": 20,
      "cache_read_tokens": 0,
      "cache_write_tokens": 0,
      "cost_micros": "16",
      "ttft_ms": 120,
      "latency_ms": 450,
      "finish_reason": "stop",
      "streamed": false,
      "error": null,
      "receipt_url": "/v1/org/receipts/req_example"
    }
  ],
  "next_cursor": null
}
object"list"
Object type.
dataobject[]
Records ordered newest first.
Child fields
idstring
Boardwalk request ID.
object"request"
Object type.
statestring
completed, refused, or running. Lists exclude running requests.
model_idstring | null
Internal model ID, when resolved.
modelstring | null
Callable model name, when resolved.
api_key_idstring | null
ID of the key that made the request.
endpointstring
Requested API endpoint.
created_atstring
ISO 8601 request timestamp.
status_codeinteger | null
HTTP outcome; null while running.
input_tokensinteger | null
Uncached input tokens.
output_tokensinteger | null
Generated tokens, including reasoning.
cache_read_tokensinteger | null
Cache reads, or null when unknown.
cache_write_tokensinteger | null
Cache writes, or null when unknown.
cost_microsstring | null
Cost in integer micro-dollars; null while running.
ttft_msnumber | null
Time to first token, in milliseconds.
latency_msnumber | null
Total latency, in milliseconds.
finish_reasonstring | null
Why generation ended, when reported.
streamedboolean | null
Whether streaming was requested, when known.
errorobject | null
Error details, when available.
Child fields
codestring
Machine-readable error code.
messagestring
Explanation of the error.
paramstring | null
Offending parameter, when identified.
receipt_urlstring | null
Receipt location; null for refused or running requests.
next_cursorstring | null
Pass as cursor for the next page. Null marks the end.

Retrieve one record

GET /v1/org/requests/{request_id} returns one object directly, without the list envelope. It accepts no query parameters.

request_idpath · stringrequired
Record ID from a list response.
Request · cURL
curl https://api.boardwalk.cloud/v1/org/requests/req_example \
  -H "Authorization: Bearer $BOARDWALK_API_KEY"
200 · application/json
{
  "id": "req_example",
  "object": "request",
  "state": "completed",
  "model_id": "mdl_example",
  "model": "support-agent",
  "api_key_id": "key_example",
  "endpoint": "/v1/chat/completions",
  "created_at": "2026-09-16T00:00:00.000Z",
  "status_code": 200,
  "input_tokens": 100,
  "output_tokens": 20,
  "cache_read_tokens": 0,
  "cache_write_tokens": 0,
  "cost_micros": "16",
  "ttft_ms": 120,
  "latency_ms": 450,
  "finish_reason": "stop",
  "streamed": false,
  "error": null,
  "receipt_url": "/v1/org/receipts/req_example"
}

Detail fields match the object in data above.

Errors

Errors use the shared error format. Save the x-request-id response header for receipts and support.