Admin

Organization

Audit Logs

List audit logs

$ openai admin:organization:audit-logs list

get /organization/audit_logs

List user actions and configuration changes within this organization.

Parameters

• --actor-email: optional array of string

  Return only events performed by users with these emails.

• --actor-id: optional array of string

  Return only events performed by these actors. Can be a user ID, a service account ID, or an api key tracking ID.

• --after: optional string

  A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

• --before: optional string

  A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

• --effective-at: optional object { gt, gte, lt, lte }

  Return only events whose effective_at (Unix seconds) is in this range.

• --event-type: optional array of "api_key.created" or "api_key.updated" or "api_key.deleted" or 48 more

  Return only events with a type in one of these values. For example, project.created. For all options, see the documentation for the audit log object.

• --limit: optional number

  A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

• --project-id: optional array of string

  Return only events for these projects.

• --resource-id: optional array of string

  Return only events performed on these targets. For example, a project ID updated.

Returns

• ListAuditLogsResponse: object { data, has_more, object, 2 more }

  • data: array of object { id, effective_at, type, 49 more }

    • id: string

      The ID of this log.

    • effective_at: number

      The Unix timestamp (in seconds) of the event.

    • type: "api_key.created" or "api_key.updated" or "api_key.deleted" or 48 more

      The event type.

      • "api_key.created"

      • "api_key.updated"

      • "api_key.deleted"

      • "certificate.created"

      • "certificate.updated"

      • "certificate.deleted"

      • "certificates.activated"

      • "certificates.deactivated"

      • "checkpoint.permission.created"

      • "checkpoint.permission.deleted"

      • "external_key.registered"

      • "external_key.removed"

      • "group.created"

      • "group.updated"

      • "group.deleted"

      • "invite.sent"

      • "invite.accepted"

      • "invite.deleted"

      • "ip_allowlist.created"

      • "ip_allowlist.updated"

      • "ip_allowlist.deleted"

      • "ip_allowlist.config.activated"

      • "ip_allowlist.config.deactivated"

      • "login.succeeded"

      • "login.failed"

      • "logout.succeeded"

      • "logout.failed"

      • "organization.updated"

      • "project.created"

      • "project.updated"

      • "project.archived"

      • "project.deleted"

      • "rate_limit.updated"

      • "rate_limit.deleted"

      • "resource.deleted"

      • "tunnel.created"

      • "tunnel.updated"

      • "tunnel.deleted"

      • "role.created"

      • "role.updated"

      • "role.deleted"

      • "role.assignment.created"

      • "role.assignment.deleted"

      • "scim.enabled"

      • "scim.disabled"

      • "service_account.created"

      • "service_account.updated"

      • "service_account.deleted"

      • "user.added"

      • "user.updated"

      • "user.deleted"

    • actor: optional object { api_key, session, type }

      The actor who performed the audit logged action.

      • api_key: optional object { id, service_account, type, user }

        The API Key used to perform the audit logged action.

        • id: optional string

          The tracking id of the API key.

        • service_account: optional object { id }

          The service account that performed the audit logged action.

          • id: optional string

            The service account id.

        • type: optional "user" or "service_account"

          The type of API key. Can be either user or service_account.

          • "user"

          • "service_account"

        • user: optional object { id, email }

          The user who performed the audit logged action.

          • id: optional string

            The user id.

          • email: optional string

            The user email.

      • session: optional object { ip_address, user }

        The session in which the audit logged action was performed.

        • ip_address: optional string

          The IP address from which the action was performed.

        • user: optional object { id, email }

          The user who performed the audit logged action.

          • id: optional string

            The user id.

          • email: optional string

            The user email.

      • type: optional "session" or "api_key"

        The type of actor. Is either session or api_key.

        • "session"

        • "api_key"

    • api_key.created: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The tracking ID of the API key.

      • data: optional object { scopes }

        The payload used to create the API key.

        • scopes: optional array of string

          A list of scopes allowed for the API key, e.g. ["api.model.request"]

    • api_key.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The tracking ID of the API key.

    • api_key.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The tracking ID of the API key.

      • changes_requested: optional object { scopes }

        The payload used to update the API key.

        • scopes: optional array of string

          A list of scopes allowed for the API key, e.g. ["api.model.request"]

    • certificate.created: optional object { id, name }

      The details for events with this type.

      • id: optional string

        The certificate ID.

      • name: optional string

        The name of the certificate.

    • certificate.deleted: optional object { id, certificate, name }

      The details for events with this type.

      • id: optional string

        The certificate ID.

      • certificate: optional string

        The certificate content in PEM format.

      • name: optional string

        The name of the certificate.

    • certificate.updated: optional object { id, name }

      The details for events with this type.

      • id: optional string

        The certificate ID.

      • name: optional string

        The name of the certificate.

    • certificates.activated: optional object { certificates }

      The details for events with this type.

      • certificates: optional array of object { id, name }

        • id: optional string

          The certificate ID.

        • name: optional string

          The name of the certificate.

    • certificates.deactivated: optional object { certificates }

      The details for events with this type.

      • certificates: optional array of object { id, name }

        • id: optional string

          The certificate ID.

        • name: optional string

          The name of the certificate.

    • checkpoint.permission.created: optional object { id, data }

      The project and fine-tuned model checkpoint that the checkpoint permission was created for.

      • id: optional string

        The ID of the checkpoint permission.

      • data: optional object { fine_tuned_model_checkpoint, project_id }

        The payload used to create the checkpoint permission.

        • fine_tuned_model_checkpoint: optional string

          The ID of the fine-tuned model checkpoint.

        • project_id: optional string

          The ID of the project that the checkpoint permission was created for.

    • checkpoint.permission.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the checkpoint permission.

    • external_key.registered: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The ID of the external key configuration.

      • data: optional unknown

        The configuration for the external key.

    • external_key.removed: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the external key configuration.

    • group.created: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The ID of the group.

      • data: optional object { group_name }

        Information about the created group.

        • group_name: optional string

          The group name.

    • group.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the group.

    • group.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The ID of the group.

      • changes_requested: optional object { group_name }

        The payload used to update the group.

        • group_name: optional string

          The updated group name.

    • invite.accepted: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the invite.

    • invite.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the invite.

    • invite.sent: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The ID of the invite.

      • data: optional object { email, role }

        The payload used to create the invite.

        • email: optional string

          The email invited to the organization.

        • role: optional string

          The role the email was invited to be. Is either owner or member.

    • ip_allowlist.config.activated: optional object { configs }

      The details for events with this type.

      • configs: optional array of object { id, name }

        The configurations that were activated.

        • id: optional string

          The ID of the IP allowlist configuration.

        • name: optional string

          The name of the IP allowlist configuration.

    • ip_allowlist.config.deactivated: optional object { configs }

      The details for events with this type.

      • configs: optional array of object { id, name }

        The configurations that were deactivated.

        • id: optional string

          The ID of the IP allowlist configuration.

        • name: optional string

          The name of the IP allowlist configuration.

    • ip_allowlist.created: optional object { id, allowed_ips, name }

      The details for events with this type.

      • id: optional string

        The ID of the IP allowlist configuration.

      • allowed_ips: optional array of string

        The IP addresses or CIDR ranges included in the configuration.

      • name: optional string

        The name of the IP allowlist configuration.

    • ip_allowlist.deleted: optional object { id, allowed_ips, name }

      The details for events with this type.

      • id: optional string

        The ID of the IP allowlist configuration.

      • allowed_ips: optional array of string

        The IP addresses or CIDR ranges that were in the configuration.

      • name: optional string

        The name of the IP allowlist configuration.

    • ip_allowlist.updated: optional object { id, allowed_ips }

      The details for events with this type.

      • id: optional string

        The ID of the IP allowlist configuration.

      • allowed_ips: optional array of string

        The updated set of IP addresses or CIDR ranges in the configuration.

    • login.failed: optional object { error_code, error_message }

      The details for events with this type.

      • error_code: optional string

        The error code of the failure.

      • error_message: optional string

        The error message of the failure.

    • login.succeeded: optional unknown

      This event has no additional fields beyond the standard audit log attributes.

    • logout.failed: optional object { error_code, error_message }

      The details for events with this type.

      • error_code: optional string

        The error code of the failure.

      • error_message: optional string

        The error message of the failure.

    • logout.succeeded: optional unknown

      This event has no additional fields beyond the standard audit log attributes.

    • organization.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The organization ID.

      • changes_requested: optional object { api_call_logging, api_call_logging_project_ids, description, 4 more }

        The payload used to update the organization settings.

        • api_call_logging: optional string

          How your organization logs data from supported API calls. One of disabled, enabled_per_call, enabled_for_all_projects, or enabled_for_selected_projects

        • api_call_logging_project_ids: optional string

          The list of project ids if api_call_logging is set to enabled_for_selected_projects

        • description: optional string

          The organization description.

        • name: optional string

          The organization name.

        • threads_ui_visibility: optional string

          Visibility of the threads page which shows messages created with the Assistants API and Playground. One of ANY_ROLE, OWNERS, or NONE.

        • title: optional string

          The organization title.

        • usage_dashboard_visibility: optional string

          Visibility of the usage dashboard which shows activity and costs for your organization. One of ANY_ROLE or OWNERS.

    • project: optional object { id, name }

      The project that the action was scoped to. Absent for actions not scoped to projects. Note that any admin actions taken via Admin API keys are associated with the default project.

      • id: optional string

        The project ID.

      • name: optional string

        The project title.

    • project.archived: optional object { id }

      The details for events with this type.

      • id: optional string

        The project ID.

    • project.created: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The project ID.

      • data: optional object { name, title }

        The payload used to create the project.

        • name: optional string

          The project name.

        • title: optional string

          The title of the project as seen on the dashboard.

    • project.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The project ID.

    • project.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The project ID.

      • changes_requested: optional object { title }

        The payload used to update the project.

        • title: optional string

          The title of the project as seen on the dashboard.

    • rate_limit.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The rate limit ID

    • rate_limit.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The rate limit ID

      • changes_requested: optional object { batch_1_day_max_input_tokens, max_audio_megabytes_per_1_minute, max_images_per_1_minute, 3 more }

        The payload used to update the rate limits.

        • batch_1_day_max_input_tokens: optional number

          The maximum batch input tokens per day. Only relevant for certain models.

        • max_audio_megabytes_per_1_minute: optional number

          The maximum audio megabytes per minute. Only relevant for certain models.

        • max_images_per_1_minute: optional number

          The maximum images per minute. Only relevant for certain models.

        • max_requests_per_1_day: optional number

          The maximum requests per day. Only relevant for certain models.

        • max_requests_per_1_minute: optional number

          The maximum requests per minute.

        • max_tokens_per_1_minute: optional number

          The maximum tokens per minute.

    • role.assignment.created: optional object { id, principal_id, principal_type, 2 more }

      The details for events with this type.

      • id: optional string

        The identifier of the role assignment.

      • principal_id: optional string

        The principal (user or group) that received the role.

      • principal_type: optional string

        The type of principal (user or group) that received the role.

      • resource_id: optional string

        The resource the role assignment is scoped to.

      • resource_type: optional string

        The type of resource the role assignment is scoped to.

    • role.assignment.deleted: optional object { id, principal_id, principal_type, 2 more }

      The details for events with this type.

      • id: optional string

        The identifier of the role assignment.

      • principal_id: optional string

        The principal (user or group) that had the role removed.

      • principal_type: optional string

        The type of principal (user or group) that had the role removed.

      • resource_id: optional string

        The resource the role assignment was scoped to.

      • resource_type: optional string

        The type of resource the role assignment was scoped to.

    • role.created: optional object { id, permissions, resource_id, 2 more }

      The details for events with this type.

      • id: optional string

        The role ID.

      • permissions: optional array of string

        The permissions granted by the role.

      • resource_id: optional string

        The resource the role is scoped to.

      • resource_type: optional string

        The type of resource the role belongs to.

      • role_name: optional string

        The name of the role.

    • role.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The role ID.

    • role.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The role ID.

      • changes_requested: optional object { description, metadata, permissions_added, 4 more }

        The payload used to update the role.

        • description: optional string

          The updated role description, when provided.

        • metadata: optional unknown

          Additional metadata stored on the role.

        • permissions_added: optional array of string

          The permissions added to the role.

        • permissions_removed: optional array of string

          The permissions removed from the role.

        • resource_id: optional string

          The resource the role is scoped to.

        • resource_type: optional string

          The type of resource the role belongs to.

        • role_name: optional string

          The updated role name, when provided.

    • scim.disabled: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the SCIM was disabled for.

    • scim.enabled: optional object { id }

      The details for events with this type.

      • id: optional string

        The ID of the SCIM was enabled for.

    • service_account.created: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The service account ID.

      • data: optional object { role }

        The payload used to create the service account.

        • role: optional string

          The role of the service account. Is either owner or member.

    • service_account.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The service account ID.

    • service_account.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The service account ID.

      • changes_requested: optional object { role }

        The payload used to updated the service account.

        • role: optional string

          The role of the service account. Is either owner or member.

    • user.added: optional object { id, data }

      The details for events with this type.

      • id: optional string

        The user ID.

      • data: optional object { role }

        The payload used to add the user to the project.

        • role: optional string

          The role of the user. Is either owner or member.

    • user.deleted: optional object { id }

      The details for events with this type.

      • id: optional string

        The user ID.

    • user.updated: optional object { id, changes_requested }

      The details for events with this type.

      • id: optional string

        The project ID.

      • changes_requested: optional object { role }

        The payload used to update the user.

        • role: optional string

          The role of the user. Is either owner or member.

  • has_more: boolean

  • object: "list"

  • first_id: optional string

  • last_id: optional string

Example

openai admin:organization:audit-logs list \
  --admin-api-key 'My Admin API Key'

Response

{
  "data": [
    {
      "id": "id",
      "effective_at": 0,
      "type": "api_key.created",
      "actor": {
        "api_key": {
          "id": "id",
          "service_account": {
            "id": "id"
          },
          "type": "user",
          "user": {
            "id": "id",
            "email": "email"
          }
        },
        "session": {
          "ip_address": "ip_address",
          "user": {
            "id": "id",
            "email": "email"
          }
        },
        "type": "session"
      },
      "api_key.created": {
        "id": "id",
        "data": {
          "scopes": [
            "string"
          ]
        }
      },
      "api_key.deleted": {
        "id": "id"
      },
      "api_key.updated": {
        "id": "id",
        "changes_requested": {
          "scopes": [
            "string"
          ]
        }
      },
      "certificate.created": {
        "id": "id",
        "name": "name"
      },
      "certificate.deleted": {
        "id": "id",
        "certificate": "certificate",
        "name": "name"
      },
      "certificate.updated": {
        "id": "id",
        "name": "name"
      },
      "certificates.activated": {
        "certificates": [
          {
            "id": "id",
            "name": "name"
          }
        ]
      },
      "certificates.deactivated": {
        "certificates": [
          {
            "id": "id",
            "name": "name"
          }
        ]
      },
      "checkpoint.permission.created": {
        "id": "id",
        "data": {
          "fine_tuned_model_checkpoint": "fine_tuned_model_checkpoint",
          "project_id": "project_id"
        }
      },
      "checkpoint.permission.deleted": {
        "id": "id"
      },
      "external_key.registered": {
        "id": "id",
        "data": {}
      },
      "external_key.removed": {
        "id": "id"
      },
      "group.created": {
        "id": "id",
        "data": {
          "group_name": "group_name"
        }
      },
      "group.deleted": {
        "id": "id"
      },
      "group.updated": {
        "id": "id",
        "changes_requested": {
          "group_name": "group_name"
        }
      },
      "invite.accepted": {
        "id": "id"
      },
      "invite.deleted": {
        "id": "id"
      },
      "invite.sent": {
        "id": "id",
        "data": {
          "email": "email",
          "role": "role"
        }
      },
      "ip_allowlist.config.activated": {
        "configs": [
          {
            "id": "id",
            "name": "name"
          }
        ]
      },
      "ip_allowlist.config.deactivated": {
        "configs": [
          {
            "id": "id",
            "name": "name"
          }
        ]
      },
      "ip_allowlist.created": {
        "id": "id",
        "allowed_ips": [
          "string"
        ],
        "name": "name"
      },
      "ip_allowlist.deleted": {
        "id": "id",
        "allowed_ips": [
          "string"
        ],
        "name": "name"
      },
      "ip_allowlist.updated": {
        "id": "id",
        "allowed_ips": [
          "string"
        ]
      },
      "login.failed": {
        "error_code": "error_code",
        "error_message": "error_message"
      },
      "login.succeeded": {},
      "logout.failed": {
        "error_code": "error_code",
        "error_message": "error_message"
      },
      "logout.succeeded": {},
      "organization.updated": {
        "id": "id",
        "changes_requested": {
          "api_call_logging": "api_call_logging",
          "api_call_logging_project_ids": "api_call_logging_project_ids",
          "description": "description",
          "name": "name",
          "threads_ui_visibility": "threads_ui_visibility",
          "title": "title",
          "usage_dashboard_visibility": "usage_dashboard_visibility"
        }
      },
      "project": {
        "id": "id",
        "name": "name"
      },
      "project.archived": {
        "id": "id"
      },
      "project.created": {
        "id": "id",
        "data": {
          "name": "name",
          "title": "title"
        }
      },
      "project.deleted": {
        "id": "id"
      },
      "project.updated": {
        "id": "id",
        "changes_requested": {
          "title": "title"
        }
      },
      "rate_limit.deleted": {
        "id": "id"
      },
      "rate_limit.updated": {
        "id": "id",
        "changes_requested": {
          "batch_1_day_max_input_tokens": 0,
          "max_audio_megabytes_per_1_minute": 0,
          "max_images_per_1_minute": 0,
          "max_requests_per_1_day": 0,
          "max_requests_per_1_minute": 0,
          "max_tokens_per_1_minute": 0
        }
      },
      "role.assignment.created": {
        "id": "id",
        "principal_id": "principal_id",
        "principal_type": "principal_type",
        "resource_id": "resource_id",
        "resource_type": "resource_type"
      },
      "role.assignment.deleted": {
        "id": "id",
        "principal_id": "principal_id",
        "principal_type": "principal_type",
        "resource_id": "resource_id",
        "resource_type": "resource_type"
      },
      "role.created": {
        "id": "id",
        "permissions": [
          "string"
        ],
        "resource_id": "resource_id",
        "resource_type": "resource_type",
        "role_name": "role_name"
      },
      "role.deleted": {
        "id": "id"
      },
      "role.updated": {
        "id": "id",
        "changes_requested": {
          "description": "description",
          "metadata": {},
          "permissions_added": [
            "string"
          ],
          "permissions_removed": [
            "string"
          ],
          "resource_id": "resource_id",
          "resource_type": "resource_type",
          "role_name": "role_name"
        }
      },
      "scim.disabled": {
        "id": "id"
      },
      "scim.enabled": {
        "id": "id"
      },
      "service_account.created": {
        "id": "id",
        "data": {
          "role": "role"
        }
      },
      "service_account.deleted": {
        "id": "id"
      },
      "service_account.updated": {
        "id": "id",
        "changes_requested": {
          "role": "role"
        }
      },
      "user.added": {
        "id": "id",
        "data": {
          "role": "role"
        }
      },
      "user.deleted": {
        "id": "id"
      },
      "user.updated": {
        "id": "id",
        "changes_requested": {
          "role": "role"
        }
      }
    }
  ],
  "has_more": true,
  "object": "list",
  "first_id": "audit_log-defb456h8dks",
  "last_id": "audit_log-hnbkd8s93s"
}

Admin API Keys

List all organization and project API keys.

$ openai admin:organization:admin-api-keys list

get /organization/admin_api_keys

List organization API keys

Parameters

• --after: optional string

  Return keys with IDs that come after this ID in the pagination order.

• --limit: optional number

  Maximum number of keys to return.

• --order: optional "asc" or "desc"

  Order results by creation time, ascending or descending.

Returns

• ApiKeyList: object { data, has_more, object, 2 more }

  • data: array of AdminAPIKey

    • id: string

      The identifier, which can be referenced in API endpoints

    • created_at: number

      The Unix timestamp (in seconds) of when the API key was created

    • object: "organization.admin_api_key"

      The object type, which is always organization.admin_api_key

    • owner: object { id, created_at, name, 3 more }

      • id: optional string

        The identifier, which can be referenced in API endpoints

      • created_at: optional number

        The Unix timestamp (in seconds) of when the user was created

      • name: optional string

        The name of the user

      • object: optional string

        The object type, which is always organization.user

      • role: optional string

        Always owner

      • type: optional string

        Always user

    • redacted_value: string

      The redacted value of the API key

    • last_used_at: optional number

      The Unix timestamp (in seconds) of when the API key was last used

    • name: optional string

      The name of the API key

  • has_more: boolean

  • object: "list"

  • first_id: optional string

  • last_id: optional string

Example

openai admin:organization:admin-api-keys list \
  --admin-api-key 'My Admin API Key'

Response

{
  "data": [
    {
      "id": "key_abc",
      "created_at": 1711471533,
      "object": "organization.admin_api_key",
      "owner": {
        "id": "sa_456",
        "created_at": 1711471533,
        "name": "My Service Account",
        "object": "organization.user",
        "role": "owner",
        "type": "user"
      },
      "redacted_value": "sk-admin...def",
      "last_used_at": 1711471534,
      "name": "Administration Key"
    }
  ],
  "has_more": false,
  "object": "list",
  "first_id": "key_abc",
  "last_id": "key_xyz"
}

Create admin API key

$ openai admin:organization:admin-api-keys create

post /organization/admin_api_keys

Create an organization admin API key

Parameters

• --name: string

Returns

• AdminOrganizationAdminAPIKeyNewResponse: AdminAPIKey

  Represents an individual Admin API key in an org.

  • value: string

    The value of the API key. Only shown on create.

Example

openai admin:organization:admin-api-keys create \
  --admin-api-key 'My Admin API Key' \
  --name 'New Admin Key'

Response

{
  "id": "key_abc",
  "created_at": 1711471533,
  "object": "organization.admin_api_key",
  "owner": {
    "id": "sa_456",
    "created_at": 1711471533,
    "name": "My Service Account",
    "object": "organization.user",
    "role": "owner",
    "type": "user"
  },
  "redacted_value": "sk-admin...def",
  "last_used_at": 1711471534,
  "name": "Administration Key",
  "value": "sk-admin-1234abcd"
}

Retrieve admin API key

$ openai admin:organization:admin-api-keys retrieve

get /organization/admin_api_keys/{key_id}

Retrieve a single organization API key

Parameters

• --key-id: string

  The ID of the API key.

Returns

• admin_api_key: object { id, created_at, object, 4 more }

  Represents an individual Admin API key in an org.

  • id: string

    The identifier, which can be referenced in API endpoints

  • created_at: number

    The Unix timestamp (in seconds) of when the API key was created

  • object: "organization.admin_api_key"

    The object type, which is always organization.admin_api_key

  • owner: object { id, created_at, name, 3 more }

    • id: optional string

      The identifier, which can be referenced in API endpoints

    • created_at: optional number

      The Unix timestamp (in seconds) of when the user was created

    • name: optional string

      The name of the user

    • object: optional string

      The object type, which is always organization.user

    • role: optional string

      Always owner

    • type: optional string

      Always user

  • redacted_value: string

    The redacted value of the API key

  • last_used_at: optional number

    The Unix timestamp (in seconds) of when the API key was last used

  • name: optional string

    The name of the API key

Example

openai admin:organization:admin-api-keys retrieve \
  --admin-api-key 'My Admin API Key' \
  --key-id key_id

Response

{
  "id": "key_abc",
  "created_at": 1711471533,
  "object": "organization.admin_api_key",
  "owner": {
    "id": "sa_456",
    "created_at": 1711471533,
    "name": "My Service Account",
    "object": "organization.user",
    "role": "owner",
    "type": "user"
  },
  "redacted_value": "sk-admin...def",
  "last_used_at": 1711471534,
  "name": "Administration Key"
}

Delete admin API key

$ openai admin:organization:admin-api-keys delete

delete /organization/admin_api_keys/{key_id}

Delete an organization admin API key

Parameters

• --key-id: string

  The ID of the API key to be deleted.

Returns

• AdminOrganizationAdminAPIKeyDeleteResponse: object { id, deleted, object }

  • id: string

  • deleted: boolean

  • object: "organization.admin_api_key.deleted"

Example

openai admin:organization:admin-api-keys delete \
  --admin-api-key 'My Admin API Key' \
  --key-id key_id

Response

{
  "id": "key_abc",
  "deleted": true,
  "object": "organization.admin_api_key.deleted"
}

Domain Types

Admin API Key

• admin_api_key: object { id, created_at, object, 4 more }

  Represents an individual Admin API key in an org.

  • id: string

    The identifier, which can be referenced in API endpoints

  • created_at: number

    The Unix timestamp (in seconds) of when the API key was created

  • object: "organization.admin_api_key"

    The object type, which is always organization.admin_api_key

  • owner: object { id, created_at, name, 3 more }

    • id: optional string

      The identifier, which can be referenced in API endpoints

    • created_at: optional number

      The Unix timestamp (in seconds) of when the user was created

    • name: optional string

      The name of the user

    • object: optional string

      The object type, which is always organization.user

    • role: optional string

      Always owner

    • type: optional string

      Always user

  • redacted_value: string

    The redacted value of the API key

  • last_used_at: optional number

    The Unix timestamp (in seconds) of when the API key was last used

  • name: optional string

    The name of the API key

Usage

Audio speeches

$ openai admin:organization:usage audio-speeches

get /organization/usage/audio_speeches

Get audio speeches usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or "model"

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageAudioSpeechesResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage audio-speeches \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Audio transcriptions

$ openai admin:organization:usage audio-transcriptions

get /organization/usage/audio_transcriptions

Get audio transcriptions usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or "model"

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageAudioTranscriptionsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage audio-transcriptions \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Code interpreter sessions

$ openai admin:organization:usage code-interpreter-sessions

get /organization/usage/code_interpreter_sessions

Get code interpreter sessions usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id"

  Group the usage data by the specified fields. Support fields include project_id.

• --limit: optional number

  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

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

Returns

• AdminOrganizationUsageCodeInterpreterSessionsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage code-interpreter-sessions \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Completions

$ openai admin:organization:usage completions

get /organization/usage/completions

Get completions usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --batch: optional boolean

  If true, return batch jobs only. If false, return non-batch jobs only. By default, return both.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or 3 more

  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.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageCompletionsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage completions \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Embeddings

$ openai admin:organization:usage embeddings

get /organization/usage/embeddings

Get embeddings usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or "model"

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageEmbeddingsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage embeddings \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Images

$ openai admin:organization:usage images

get /organization/usage/images

Get images usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or 3 more

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model, size, source or any combination of them.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --size: optional array of "256x256" or "512x512" or "1024x1024" or 2 more

  Return only usages for these image sizes. Possible values are 256x256, 512x512, 1024x1024, 1792x1792, 1024x1792 or any combination of them.

• --source: optional array of "image.generation" or "image.edit" or "image.variation"

  Return only usages for these sources. Possible values are image.generation, image.edit, image.variation or any combination of them.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageImagesResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage images \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Moderations

$ openai admin:organization:usage moderations

get /organization/usage/moderations

Get moderations usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or "model"

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageModerationsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage moderations \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Vector stores

$ openai admin:organization:usage vector-stores

get /organization/usage/vector_stores

Get vector stores usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id"

  Group the usage data by the specified fields. Support fields include project_id.

• --limit: optional number

  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

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

Returns

• AdminOrganizationUsageVectorStoresResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage vector-stores \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

File search calls

$ openai admin:organization:usage file-search-calls

get /organization/usage/file_search_calls

Get file search calls usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or "vector_store_id"

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, vector_store_id or any combination of them.

• --limit: optional number

  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

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

• --vector-store-id: optional array of string

  Return only usage for these vector stores.

Returns

• AdminOrganizationUsageFileSearchCallsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage file-search-calls \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Web search calls

$ openai admin:organization:usage web-search-calls

get /organization/usage/web_search_calls

Get web search calls usage details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only usage for these API keys.

• --bucket-width: optional "1m" or "1h" or "1d"

  Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

• --context-level: optional array of "low" or "medium" or "high"

  Return only web search usage for these context levels.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "user_id" or "api_key_id" or 2 more

  Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model, context_level or any combination of them.

• --limit: optional number

  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

• --model: optional array of string

  Return only usage for these models.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only usage for these projects.

• --user-id: optional array of string

  Return only usage for these users.

Returns

• AdminOrganizationUsageWebSearchCallsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"

Example

openai admin:organization:usage web-search-calls \
  --admin-api-key 'My Admin API Key' \
  --start-time 0

Response

{
  "data": [
    {
      "end_time": 0,
      "object": "bucket",
      "results": [
        {
          "input_tokens": 0,
          "num_model_requests": 0,
          "object": "organization.usage.completions.result",
          "output_tokens": 0,
          "api_key_id": "api_key_id",
          "batch": true,
          "input_audio_tokens": 0,
          "input_cached_tokens": 0,
          "model": "model",
          "output_audio_tokens": 0,
          "project_id": "project_id",
          "service_tier": "service_tier",
          "user_id": "user_id"
        }
      ],
      "start_time": 0
    }
  ],
  "has_more": true,
  "next_page": "next_page",
  "object": "page"
}

Costs

$ openai admin:organization:usage costs

get /organization/costs

Get costs details for the organization.

Parameters

• --start-time: number

  Start time (Unix seconds) of the query time range, inclusive.

• --api-key-id: optional array of string

  Return only costs for these API keys.

• --bucket-width: optional "1d"

  Width of each time bucket in response. Currently only 1d is supported, default to 1d.

• --end-time: optional number

  End time (Unix seconds) of the query time range, exclusive.

• --group-by: optional array of "project_id" or "line_item" or "api_key_id"

  Group the costs by the specified fields. Support fields include project_id, line_item, api_key_id and any combination of them.

• --limit: optional number

  A limit on the number of buckets to be returned. Limit can range between 1 and 180, and the default is 7.

• --page: optional string

  A cursor for use in pagination. Corresponding to the next_page field from the previous response.

• --project-id: optional array of string

  Return only costs for these projects.

Returns

• AdminOrganizationUsageCostsResponse: object { data, has_more, next_page, object }

  • data: array of object { end_time, object, results, start_time }

    • end_time: number

    • object: "bucket"

    • results: array of object { input_tokens, num_model_requests, object, 10 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more

      • organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }

        The aggregated completions usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.completions.result"

        • output_tokens: number

          The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • batch: optional boolean

          When group_by=batch, this field tells whether the grouped usage result is batch or not.

        • input_audio_tokens: optional number

          The aggregated number of audio input tokens used, including cached tokens.

        • input_cached_tokens: optional number

          The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • output_audio_tokens: optional number

          The aggregated number of audio output tokens used.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • service_tier: optional string

          When group_by=service_tier, this field provides the service tier of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.embeddings.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated embeddings usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.embeddings.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.moderations.result: object { input_tokens, num_model_requests, object, 4 more }

        The aggregated moderations usage details of the specific time bucket.

        • input_tokens: number

          The aggregated number of input tokens used.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.moderations.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.images.result: object { images, num_model_requests, object, 6 more }

        The aggregated images usage details of the specific time bucket.

        • images: number

          The number of images processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.images.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • size: optional string

          When group_by=size, this field provides the image size of the grouped usage result.

        • source: optional string

          When group_by=source, this field provides the source of the grouped usage result, possible values are image.generation, image.edit, image.variation.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_speeches.result: object { characters, num_model_requests, object, 4 more }

        The aggregated audio speeches usage details of the specific time bucket.

        • characters: number

          The number of characters processed.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_speeches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.audio_transcriptions.result: object { num_model_requests, object, seconds, 4 more }

        The aggregated audio transcriptions usage details of the specific time bucket.

        • num_model_requests: number

          The count of requests made to the model.

        • object: "organization.usage.audio_transcriptions.result"

        • seconds: number

          The number of seconds processed.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.usage.vector_stores.result: object { object, usage_bytes, project_id }

        The aggregated vector stores usage details of the specific time bucket.

        • object: "organization.usage.vector_stores.result"

        • usage_bytes: number

          The vector stores usage in bytes.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.code_interpreter_sessions.result: object { num_sessions, object, project_id }

        The aggregated code interpreter sessions usage details of the specific time bucket.

        • num_sessions: number

          The number of code interpreter sessions.

        • object: "organization.usage.code_interpreter_sessions.result"

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

      • organization.usage.file_searches.result: object { num_requests, object, api_key_id, 3 more }

        The aggregated file search calls usage details of the specific time bucket.

        • num_requests: number

          The count of file search calls.

        • object: "organization.usage.file_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

        • vector_store_id: optional string

          When group_by=vector_store_id, this field provides the vector store ID of the grouped usage result.

      • organization.usage.web_searches.result: object { num_model_requests, num_requests, object, 5 more }

        The aggregated web search calls usage details of the specific time bucket.

        • num_model_requests: number

          The count of model requests.

        • num_requests: number

          The count of web search calls.

        • object: "organization.usage.web_searches.result"

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API key ID of the grouped usage result.

        • context_level: optional string

          When group_by=context_level, this field provides the search context size of the grouped usage result.

        • model: optional string

          When group_by=model, this field provides the model name of the grouped usage result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped usage result.

        • user_id: optional string

          When group_by=user_id, this field provides the user ID of the grouped usage result.

      • organization.costs.result: object { object, amount, api_key_id, 3 more }

        The aggregated costs details of the specific time bucket.

        • object: "organization.costs.result"

        • amount: optional object { currency, value }

          The monetary value in its associated currency.

          • currency: optional string

            Lowercase ISO-4217 currency e.g. "usd"

          • value: optional number

            The numeric value of the cost.

        • api_key_id: optional string

          When group_by=api_key_id, this field provides the API Key ID of the grouped costs result.

        • line_item: optional string

          When group_by=line_item, this field provides the line item of the grouped costs result.

        • project_id: optional string

          When group_by=project_id, this field provides the project ID of the grouped costs result.

        • quantity: optional number

          When group_by=line_item, this field provides the quantity of the grouped costs result.

    • start_time: number

  • has_more: boolean

  • next_page: string

  • object: "page"