Sample - OpenAI API
GET/organization/usage/completions

Completions

Get completions usage details for the organization.

  • RetriesRetries up to 2×, 500ms backoff, 30s timeout.

11 parameters
start_timeintegerrequired
Start time (Unix seconds) of the query time range, inclusive.
end_timeintegeroptional
End time (Unix seconds) of the query time range, exclusive.
bucket_widthstringoptional
Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.
Allowed:1m1h1dDefault:1d
project_idsarray<string>optional
Return only usage for these projects.
user_idsarray<string>optional
Return only usage for these users.
api_key_idsarray<string>optional
Return only usage for these API keys.
modelsarray<string>optional
Return only usage for these models.
batchbooleanoptional
If `true`, return batch jobs only. If `false`, return non-batch jobs only. By default, return both.
group_byarray<string>optional
Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model`, `batch`, `service_tier` or any combination of them.
limitintegeroptional
Specifies the number of buckets to return. - `bucket_width=1d`: default: 7, max: 31 - `bucket_width=1h`: default: 24, max: 168 - `bucket_width=1m`: default: 60, max: 1440
pagestringoptional
A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.

2 status codes
200Usage data retrieved successfully.
objectstringrequired
Allowed:page
dataarray<object>required
has_morebooleanrequired
next_pagestringrequired
429The request was rejected because a rate limit was exceeded.
errorobjectrequired

Error handling

A 429 is returned: The request was rejected because a rate limit was exceeded.