Reference 2026-07-15 02:58 UTC to 2026-07-16 20:57 UTC

28 28 

29 Return only events whose `effective_at` (Unix seconds) is in this range.29 Return only events whose `effective_at` (Unix seconds) is in this range.

30 30 

31- `--event-type: optional array of "api_key.created" or "api_key.updated" or "api_key.deleted" or 56 more`31- `--event-type: optional array of "api_key.created" or "api_key.updated" or "api_key.deleted" or 140 more`

32 32 

33 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](https://platform.openai.com/docs/api-reference/audit-logs/object).33 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](https://platform.openai.com/docs/api-reference/audit-logs/object).

34 34 

62 62 

63 The Unix timestamp (in seconds) of the event.63 The Unix timestamp (in seconds) of the event.

64 64 

65 - `type: "api_key.created" or "api_key.updated" or "api_key.deleted" or 56 more`65 - `type: "api_key.created" or "api_key.updated" or "api_key.deleted" or 140 more`

66 66 

67 The event type.67 The event type.

68 68 

184 184 

185 - `"user.deleted"`185 - `"user.deleted"`

186 186 

187 - `"tenant.metadata.updated"`

188 

189 - `"tenant.microsoft_entra_mapping.upserted"`

190 

191 - `"tenant.microsoft_entra_mapping.deleted"`

192 

193 - `"tenant.workload_identity.provider.created"`

194 

195 - `"tenant.workload_identity.provider.updated"`

196 

197 - `"tenant.workload_identity.provider.archived"`

198 

199 - `"tenant.workload_identity.mapping.created"`

200 

201 - `"tenant.workload_identity.mapping.updated"`

202 

203 - `"tenant.workload_identity.mapping.archived"`

204 

205 - `"tenant.workload_identity.binding.created"`

206 

207 - `"tenant.workload_identity.principal.provisioned"`

208 

209 - `"tenant.admin_api_key.created"`

210 

211 - `"tenant.admin_api_key.updated"`

212 

213 - `"tenant.admin_api_key.deleted"`

214 

215 - `"tenant.project_api_key.created"`

216 

217 - `"tenant.chatgpt_access_token.revoked"`

218 

219 - `"tenant.migration.completed"`

220 

221 - `"tenant.sso.migrated"`

222 

223 - `"tenant.domains.migrated"`

224 

225 - `"tenant.sso_connection.created"`

226 

227 - `"tenant.sso_connection.updated"`

228 

229 - `"tenant.sso_connection.deleted"`

230 

231 - `"tenant.sso_connection.setup.started"`

232 

233 - `"tenant.policy.created"`

234 

235 - `"tenant.policy.updated"`

236 

237 - `"tenant.policy.deleted"`

238 

239 - `"tenant.policy.attached"`

240 

241 - `"tenant.policy.detached"`

242 

243 - `"tenant.principal_authentication_policy.resolved"`

244 

245 - `"tenant.scim.setup.started"`

246 

247 - `"tenant.scim.deletion.requested"`

248 

249 - `"tenant.scim.directory.created"`

250 

251 - `"tenant.product_access_policy.updated"`

252 

253 - `"tenant.resource_share_grant.created"`

254 

255 - `"tenant.resource_share_grant.updated"`

256 

257 - `"tenant.resource_share_grant.accepted"`

258 

259 - `"tenant.resource_share_grant.declined"`

260 

261 - `"tenant.resource_share_grant.revoked"`

262 

263 - `"tenant.resource_share_grant.deleted"`

264 

265 - `"tenant.service_account.updated"`

266 

267 - `"tenant.service_account.deleted"`

268 

269 - `"tenant.service_account.token.revoked"`

270 

271 - `"tenant.billing.overage_limit.updated"`

272 

273 - `"tenant.billing.alerts.updated"`

274 

275 - `"tenant.billing.info.updated"`

276 

277 - `"tenant.usage_limit.workspace.updated"`

278 

279 - `"tenant.usage_limit.group.updated"`

280 

281 - `"tenant.usage_limit.user.updated"`

282 

283 - `"tenant.usage_limit.increase_request.updated"`

284 

285 - `"tenant.usage_limit.increase_request.resolved"`

286 

287 - `"tenant.group.created"`

288 

289 - `"tenant.group.updated"`

290 

291 - `"tenant.group.deleted"`

292 

293 - `"tenant.group.member.added"`

294 

295 - `"tenant.group.member.removed"`

296 

297 - `"tenant.migration_rollout.status.updated"`

298 

299 - `"tenant.migration_rollout.tier.updated"`

300 

301 - `"tenant.role.metadata.updated"`

302 

303 - `"tenant.custom_role.created"`

304 

305 - `"tenant.custom_role.updated"`

306 

307 - `"tenant.custom_role.deleted"`

308 

309 - `"tenant.role_assignment.created"`

310 

311 - `"tenant.role_assignment.deleted"`

312 

313 - `"tenant.resource_role_assignment.created"`

314 

315 - `"tenant.resource_role_assignment.deleted"`

316 

317 - `"tenant.resource_access.updated"`

318 

319 - `"tenant.resource_access.deleted"`

320 

321 - `"tenant.session_policy.created"`

322 

323 - `"tenant.session_policy.updated"`

324 

325 - `"tenant.session_policy.deleted"`

326 

327 - `"tenant.session_revocation.started"`

328 

329 - `"tenant.third_party_app_policy.updated"`

330 

331 - `"tenant.user.added"`

332 

333 - `"tenant.user.updated"`

334 

335 - `"tenant.user.removed"`

336 

337 - `"tenant.user.looked_up"`

338 

339 - `"tenant.user.invited"`

340 

341 - `"tenant.membership.revoked"`

342 

343 - `"tenant.api_organization_invite.upserted"`

344 

345 - `"tenant.api_organization_invite.deleted"`

346 

347 - `"tenant.chatgpt_workspace_invite.upserted"`

348 

349 - `"tenant.membership.accepted"`

350 

351 - `"tenant.membership.declined"`

352 

353 - `"tenant.workspace_invite_email_settings.updated"`

354 

187 - `actor: optional object { api_key, session, type }`355 - `actor: optional object { api_key, session, type }`

188 356 

189 The actor who performed the audit logged action.357 The actor who performed the audit logged action.

4 4 

5**post** `/organization/projects/{project_id}/service_accounts`5**post** `/organization/projects/{project_id}/service_accounts`

6 6 

7Creates a new service account in the project. This also returns an unredacted API key for the service account.7Creates a new service account in the project. By default, this also returns an unredacted API key for the service account.

8 8 

9### Parameters9### Parameters

10 10 

16 16 

17 The name of the service account being created.17 The name of the service account being created.

18 18 

19- `--create-service-account-only: optional boolean`

20 

21 Create the service account without default roles or an API key.

22 

19### Returns23### Returns

20 24 

21- `AdminOrganizationProjectServiceAccountNewResponse: object { id, api_key, created_at, 3 more }`25- `AdminOrganizationProjectServiceAccountNewResponse: object { id, api_key, created_at, 3 more }`

42 46 

43 - `object: "organization.project.service_account"`47 - `object: "organization.project.service_account"`

44 48 

45 - `role: "member"`49 - `role: "member" or "none"`

50 

51 Service accounts created with default project membership have role `member`. Accounts created with `create_service_account_only` have role `none`.

52 

53 - `"member"`

46 54 

47 Service accounts can only have one role of type `member`55 - `"none"`

48 56 

49### Example57### Example

50 58 

42 42 

43 The object type, which is always `organization.project.service_account`43 The object type, which is always `organization.project.service_account`

44 44 

45 - `role: "owner" or "member"`45 - `role: "owner" or "member" or "none"`

46 46 

47 `owner` or `member`47 `owner`, `member`, or `none`

48 48 

49 - `"owner"`49 - `"owner"`

50 50 

51 - `"member"`51 - `"member"`

52 52 

53 - `"none"`

54 

53 - `has_more: boolean`55 - `has_more: boolean`

54 56 

55 - `object: "list"`57 - `object: "list"`

38 38 

39 The object type, which is always `organization.project.service_account`39 The object type, which is always `organization.project.service_account`

40 40 

41 - `role: "owner" or "member"`41 - `role: "owner" or "member" or "none"`

42 42 

43 `owner` or `member`43 `owner`, `member`, or `none`

44 44 

45 - `"owner"`45 - `"owner"`

46 46 

47 - `"member"`47 - `"member"`

48 48 

49 - `"none"`

50 

49### Example51### Example

50 52 

51```cli53```cli

46 46 

47 The object type, which is always `organization.project.service_account`47 The object type, which is always `organization.project.service_account`

48 48 

49 - `role: "owner" or "member"`49 - `role: "owner" or "member" or "none"`

50 50 

51 `owner` or `member`51 `owner`, `member`, or `none`

52 52 

53 - `"owner"`53 - `"owner"`

54 54 

55 - `"member"`55 - `"member"`

56 56 

57 - `"none"`

58 

57### Example59### Example

58 60 

59```cli61```cli

1## Create project service account API key

2 

3`$ openai admin:organization:projects:service-accounts:api-keys create`

4 

5**post** `/organization/projects/{project_id}/service_accounts/{service_account_id}/api_keys`

6 

7Creates an API key for a service account in the project.

8 

9### Parameters

10 

11- `--project-id: string`

12 

13 The ID of the project.

14 

15- `--service-account-id: string`

16 

17 The ID of the service account.

18 

19- `--name: optional string`

20 

21 API key name.

22 

23- `--scope: optional array of string`

24 

25 API key scopes.

26 

27### Returns

28 

29- `AdminOrganizationProjectServiceAccountAPIKeyNewResponse: object { id, created_at, name, 2 more }`

30 

31 - `id: string`

32 

33 - `created_at: number`

34 

35 - `name: string`

36 

37 - `object: "organization.project.service_account.api_key"`

38 

39 The object type, which is always `organization.project.service_account.api_key`

40 

41 - `value: string`

42 

43### Example

44 

45```cli

46openai admin:organization:projects:service-accounts:api-keys create \

47 --admin-api-key 'My Admin API Key' \

48 --project-id project_id \

49 --service-account-id service_account_id

50```

51 

52#### Response

53 

54```json

55{

56 "id": "id",

57 "created_at": 0,

58 "name": "name",

59 "object": "organization.project.service_account.api_key",

60 "value": "value"

61}

62```

62 62 

63 - `object: "bucket"`63 - `object: "bucket"`

64 64 

65 - `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`65 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

66 66 

67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

68 68 

69 The aggregated completions usage details of the specific time bucket.69 The aggregated completions usage details of the specific time bucket.

70 70 

71 - `input_tokens: number`71 - `input_tokens: number`

72 72 

73 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.73 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

74 74 

75 - `num_model_requests: number`75 - `num_model_requests: number`

76 76 

80 80 

81 - `output_tokens: number`81 - `output_tokens: number`

82 82 

83 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.83 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

84 84 

85 - `api_key_id: optional string`85 - `api_key_id: optional string`

86 86 

92 92 

93 - `input_audio_tokens: optional number`93 - `input_audio_tokens: optional number`

94 94 

95 The aggregated number of audio input tokens used, including cached tokens.95 The aggregated number of uncached audio input tokens used.

96 

97 - `input_cache_write_tokens: optional number`

98 

99 The aggregated number of input tokens written to the cache.

100 

101 - `input_cached_audio_tokens: optional number`

102 

103 The aggregated number of cached audio input tokens used.

104 

105 - `input_cached_image_tokens: optional number`

106 

107 The aggregated number of cached image input tokens used.

108 

109 - `input_cached_text_tokens: optional number`

110 

111 The aggregated number of cached text input tokens used.

96 112 

97 - `input_cached_tokens: optional number`113 - `input_cached_tokens: optional number`

98 114 

99 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.115 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

116 

117 - `input_image_tokens: optional number`

118 

119 The aggregated number of uncached image input tokens used.

120 

121 - `input_text_tokens: optional number`

122 

123 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

124 

125 - `input_uncached_tokens: optional number`

126 

127 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

100 128 

101 - `model: optional string`129 - `model: optional string`

102 130 

106 134 

107 The aggregated number of audio output tokens used.135 The aggregated number of audio output tokens used.

108 136 

137 - `output_image_tokens: optional number`

138 

139 The aggregated number of image output tokens used.

140 

141 - `output_text_tokens: optional number`

142 

143 The aggregated number of text output tokens used.

144 

109 - `project_id: optional string`145 - `project_id: optional string`

110 146 

111 When `group_by=project_id`, this field provides the project ID of the grouped usage result.147 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

431 "api_key_id": "api_key_id",467 "api_key_id": "api_key_id",

432 "batch": true,468 "batch": true,

433 "input_audio_tokens": 0,469 "input_audio_tokens": 0,

470 "input_cache_write_tokens": 0,

471 "input_cached_audio_tokens": 0,

472 "input_cached_image_tokens": 0,

473 "input_cached_text_tokens": 0,

434 "input_cached_tokens": 0,474 "input_cached_tokens": 0,

475 "input_image_tokens": 0,

476 "input_text_tokens": 0,

477 "input_uncached_tokens": 0,

435 "model": "model",478 "model": "model",

436 "output_audio_tokens": 0,479 "output_audio_tokens": 0,

480 "output_image_tokens": 0,

481 "output_text_tokens": 0,

437 "project_id": "project_id",482 "project_id": "project_id",

438 "service_tier": "service_tier",483 "service_tier": "service_tier",

439 "user_id": "user_id"484 "user_id": "user_id"

62 62 

63 - `object: "bucket"`63 - `object: "bucket"`

64 64 

65 - `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`65 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

66 66 

67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

68 68 

69 The aggregated completions usage details of the specific time bucket.69 The aggregated completions usage details of the specific time bucket.

70 70 

71 - `input_tokens: number`71 - `input_tokens: number`

72 72 

73 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.73 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

74 74 

75 - `num_model_requests: number`75 - `num_model_requests: number`

76 76 

80 80 

81 - `output_tokens: number`81 - `output_tokens: number`

82 82 

83 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.83 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

84 84 

85 - `api_key_id: optional string`85 - `api_key_id: optional string`

86 86 

92 92 

93 - `input_audio_tokens: optional number`93 - `input_audio_tokens: optional number`

94 94 

95 The aggregated number of audio input tokens used, including cached tokens.95 The aggregated number of uncached audio input tokens used.

96 

97 - `input_cache_write_tokens: optional number`

98 

99 The aggregated number of input tokens written to the cache.

100 

101 - `input_cached_audio_tokens: optional number`

102 

103 The aggregated number of cached audio input tokens used.

104 

105 - `input_cached_image_tokens: optional number`

106 

107 The aggregated number of cached image input tokens used.

108 

109 - `input_cached_text_tokens: optional number`

110 

111 The aggregated number of cached text input tokens used.

96 112 

97 - `input_cached_tokens: optional number`113 - `input_cached_tokens: optional number`

98 114 

99 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.115 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

116 

117 - `input_image_tokens: optional number`

118 

119 The aggregated number of uncached image input tokens used.

120 

121 - `input_text_tokens: optional number`

122 

123 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

124 

125 - `input_uncached_tokens: optional number`

126 

127 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

100 128 

101 - `model: optional string`129 - `model: optional string`

102 130 

106 134 

107 The aggregated number of audio output tokens used.135 The aggregated number of audio output tokens used.

108 136 

137 - `output_image_tokens: optional number`

138 

139 The aggregated number of image output tokens used.

140 

141 - `output_text_tokens: optional number`

142 

143 The aggregated number of text output tokens used.

144 

109 - `project_id: optional string`145 - `project_id: optional string`

110 146 

111 When `group_by=project_id`, this field provides the project ID of the grouped usage result.147 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

431 "api_key_id": "api_key_id",467 "api_key_id": "api_key_id",

432 "batch": true,468 "batch": true,

433 "input_audio_tokens": 0,469 "input_audio_tokens": 0,

470 "input_cache_write_tokens": 0,

471 "input_cached_audio_tokens": 0,

472 "input_cached_image_tokens": 0,

473 "input_cached_text_tokens": 0,

434 "input_cached_tokens": 0,474 "input_cached_tokens": 0,

475 "input_image_tokens": 0,

476 "input_text_tokens": 0,

477 "input_uncached_tokens": 0,

435 "model": "model",478 "model": "model",

436 "output_audio_tokens": 0,479 "output_audio_tokens": 0,

480 "output_image_tokens": 0,

481 "output_text_tokens": 0,

437 "project_id": "project_id",482 "project_id": "project_id",

438 "service_tier": "service_tier",483 "service_tier": "service_tier",

439 "user_id": "user_id"484 "user_id": "user_id"

50 50 

51 - `object: "bucket"`51 - `object: "bucket"`

52 52 

53 - `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`53 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

54 54 

55 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`55 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

56 56 

57 The aggregated completions usage details of the specific time bucket.57 The aggregated completions usage details of the specific time bucket.

58 58 

59 - `input_tokens: number`59 - `input_tokens: number`

60 60 

61 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.61 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

62 62 

63 - `num_model_requests: number`63 - `num_model_requests: number`

64 64 

68 68 

69 - `output_tokens: number`69 - `output_tokens: number`

70 70 

71 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.71 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

72 72 

73 - `api_key_id: optional string`73 - `api_key_id: optional string`

74 74 

80 80 

81 - `input_audio_tokens: optional number`81 - `input_audio_tokens: optional number`

82 82 

83 The aggregated number of audio input tokens used, including cached tokens.83 The aggregated number of uncached audio input tokens used.

84 

85 - `input_cache_write_tokens: optional number`

86 

87 The aggregated number of input tokens written to the cache.

88 

89 - `input_cached_audio_tokens: optional number`

90 

91 The aggregated number of cached audio input tokens used.

92 

93 - `input_cached_image_tokens: optional number`

94 

95 The aggregated number of cached image input tokens used.

96 

97 - `input_cached_text_tokens: optional number`

98 

99 The aggregated number of cached text input tokens used.

84 100 

85 - `input_cached_tokens: optional number`101 - `input_cached_tokens: optional number`

86 102 

87 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.103 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

104 

105 - `input_image_tokens: optional number`

106 

107 The aggregated number of uncached image input tokens used.

108 

109 - `input_text_tokens: optional number`

110 

111 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

112 

113 - `input_uncached_tokens: optional number`

114 

115 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

88 116 

89 - `model: optional string`117 - `model: optional string`

90 118 

94 122 

95 The aggregated number of audio output tokens used.123 The aggregated number of audio output tokens used.

96 124 

125 - `output_image_tokens: optional number`

126 

127 The aggregated number of image output tokens used.

128 

129 - `output_text_tokens: optional number`

130 

131 The aggregated number of text output tokens used.

132 

97 - `project_id: optional string`133 - `project_id: optional string`

98 134 

99 When `group_by=project_id`, this field provides the project ID of the grouped usage result.135 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

419 "api_key_id": "api_key_id",455 "api_key_id": "api_key_id",

420 "batch": true,456 "batch": true,

421 "input_audio_tokens": 0,457 "input_audio_tokens": 0,

458 "input_cache_write_tokens": 0,

459 "input_cached_audio_tokens": 0,

460 "input_cached_image_tokens": 0,

461 "input_cached_text_tokens": 0,

422 "input_cached_tokens": 0,462 "input_cached_tokens": 0,

463 "input_image_tokens": 0,

464 "input_text_tokens": 0,

465 "input_uncached_tokens": 0,

423 "model": "model",466 "model": "model",

424 "output_audio_tokens": 0,467 "output_audio_tokens": 0,

468 "output_image_tokens": 0,

469 "output_text_tokens": 0,

425 "project_id": "project_id",470 "project_id": "project_id",

426 "service_tier": "service_tier",471 "service_tier": "service_tier",

427 "user_id": "user_id"472 "user_id": "user_id"

66 66 

67 - `object: "bucket"`67 - `object: "bucket"`

68 68 

69 - `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`69 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

70 70 

71 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`71 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

72 72 

73 The aggregated completions usage details of the specific time bucket.73 The aggregated completions usage details of the specific time bucket.

74 74 

75 - `input_tokens: number`75 - `input_tokens: number`

76 76 

77 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.77 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

78 78 

79 - `num_model_requests: number`79 - `num_model_requests: number`

80 80 

84 84 

85 - `output_tokens: number`85 - `output_tokens: number`

86 86 

87 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.87 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

88 88 

89 - `api_key_id: optional string`89 - `api_key_id: optional string`

90 90 

96 96 

97 - `input_audio_tokens: optional number`97 - `input_audio_tokens: optional number`

98 98 

99 The aggregated number of audio input tokens used, including cached tokens.99 The aggregated number of uncached audio input tokens used.

100 

101 - `input_cache_write_tokens: optional number`

102 

103 The aggregated number of input tokens written to the cache.

104 

105 - `input_cached_audio_tokens: optional number`

106 

107 The aggregated number of cached audio input tokens used.

108 

109 - `input_cached_image_tokens: optional number`

110 

111 The aggregated number of cached image input tokens used.

112 

113 - `input_cached_text_tokens: optional number`

114 

115 The aggregated number of cached text input tokens used.

100 116 

101 - `input_cached_tokens: optional number`117 - `input_cached_tokens: optional number`

102 118 

103 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.119 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

120 

121 - `input_image_tokens: optional number`

122 

123 The aggregated number of uncached image input tokens used.

124 

125 - `input_text_tokens: optional number`

126 

127 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

128 

129 - `input_uncached_tokens: optional number`

130 

131 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

104 132 

105 - `model: optional string`133 - `model: optional string`

106 134 

110 138 

111 The aggregated number of audio output tokens used.139 The aggregated number of audio output tokens used.

112 140 

141 - `output_image_tokens: optional number`

142 

143 The aggregated number of image output tokens used.

144 

145 - `output_text_tokens: optional number`

146 

147 The aggregated number of text output tokens used.

148 

113 - `project_id: optional string`149 - `project_id: optional string`

114 150 

115 When `group_by=project_id`, this field provides the project ID of the grouped usage result.151 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

435 "api_key_id": "api_key_id",471 "api_key_id": "api_key_id",

436 "batch": true,472 "batch": true,

437 "input_audio_tokens": 0,473 "input_audio_tokens": 0,

474 "input_cache_write_tokens": 0,

475 "input_cached_audio_tokens": 0,

476 "input_cached_image_tokens": 0,

477 "input_cached_text_tokens": 0,

438 "input_cached_tokens": 0,478 "input_cached_tokens": 0,

479 "input_image_tokens": 0,

480 "input_text_tokens": 0,

481 "input_uncached_tokens": 0,

439 "model": "model",482 "model": "model",

440 "output_audio_tokens": 0,483 "output_audio_tokens": 0,

484 "output_image_tokens": 0,

485 "output_text_tokens": 0,

441 "project_id": "project_id",486 "project_id": "project_id",

442 "service_tier": "service_tier",487 "service_tier": "service_tier",

443 "user_id": "user_id"488 "user_id": "user_id"

50 50 

51 - `object: "bucket"`51 - `object: "bucket"`

52 52 

53 - `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`53 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

54 54 

55 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`55 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

56 56 

57 The aggregated completions usage details of the specific time bucket.57 The aggregated completions usage details of the specific time bucket.

58 58 

59 - `input_tokens: number`59 - `input_tokens: number`

60 60 

61 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.61 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

62 62 

63 - `num_model_requests: number`63 - `num_model_requests: number`

64 64 

68 68 

69 - `output_tokens: number`69 - `output_tokens: number`

70 70 

71 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.71 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

72 72 

73 - `api_key_id: optional string`73 - `api_key_id: optional string`

74 74 

80 80 

81 - `input_audio_tokens: optional number`81 - `input_audio_tokens: optional number`

82 82 

83 The aggregated number of audio input tokens used, including cached tokens.83 The aggregated number of uncached audio input tokens used.

84 

85 - `input_cache_write_tokens: optional number`

86 

87 The aggregated number of input tokens written to the cache.

88 

89 - `input_cached_audio_tokens: optional number`

90 

91 The aggregated number of cached audio input tokens used.

92 

93 - `input_cached_image_tokens: optional number`

94 

95 The aggregated number of cached image input tokens used.

96 

97 - `input_cached_text_tokens: optional number`

98 

99 The aggregated number of cached text input tokens used.

84 100 

85 - `input_cached_tokens: optional number`101 - `input_cached_tokens: optional number`

86 102 

87 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.103 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

104 

105 - `input_image_tokens: optional number`

106 

107 The aggregated number of uncached image input tokens used.

108 

109 - `input_text_tokens: optional number`

110 

111 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

112 

113 - `input_uncached_tokens: optional number`

114 

115 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

88 116 

89 - `model: optional string`117 - `model: optional string`

90 118 

94 122 

95 The aggregated number of audio output tokens used.123 The aggregated number of audio output tokens used.

96 124 

125 - `output_image_tokens: optional number`

126 

127 The aggregated number of image output tokens used.

128 

129 - `output_text_tokens: optional number`

130 

131 The aggregated number of text output tokens used.

132 

97 - `project_id: optional string`133 - `project_id: optional string`

98 134 

99 When `group_by=project_id`, this field provides the project ID of the grouped usage result.135 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

419 "api_key_id": "api_key_id",455 "api_key_id": "api_key_id",

420 "batch": true,456 "batch": true,

421 "input_audio_tokens": 0,457 "input_audio_tokens": 0,

458 "input_cache_write_tokens": 0,

459 "input_cached_audio_tokens": 0,

460 "input_cached_image_tokens": 0,

461 "input_cached_text_tokens": 0,

422 "input_cached_tokens": 0,462 "input_cached_tokens": 0,

463 "input_image_tokens": 0,

464 "input_text_tokens": 0,

465 "input_uncached_tokens": 0,

423 "model": "model",466 "model": "model",

424 "output_audio_tokens": 0,467 "output_audio_tokens": 0,

468 "output_image_tokens": 0,

469 "output_text_tokens": 0,

425 "project_id": "project_id",470 "project_id": "project_id",

426 "service_tier": "service_tier",471 "service_tier": "service_tier",

427 "user_id": "user_id"472 "user_id": "user_id"

62 62 

63 - `object: "bucket"`63 - `object: "bucket"`

64 64 

65 - `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`65 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

66 66 

67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

68 68 

69 The aggregated completions usage details of the specific time bucket.69 The aggregated completions usage details of the specific time bucket.

70 70 

71 - `input_tokens: number`71 - `input_tokens: number`

72 72 

73 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.73 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

74 74 

75 - `num_model_requests: number`75 - `num_model_requests: number`

76 76 

80 80 

81 - `output_tokens: number`81 - `output_tokens: number`

82 82 

83 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.83 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

84 84 

85 - `api_key_id: optional string`85 - `api_key_id: optional string`

86 86 

92 92 

93 - `input_audio_tokens: optional number`93 - `input_audio_tokens: optional number`

94 94 

95 The aggregated number of audio input tokens used, including cached tokens.95 The aggregated number of uncached audio input tokens used.

96 

97 - `input_cache_write_tokens: optional number`

98 

99 The aggregated number of input tokens written to the cache.

100 

101 - `input_cached_audio_tokens: optional number`

102 

103 The aggregated number of cached audio input tokens used.

104 

105 - `input_cached_image_tokens: optional number`

106 

107 The aggregated number of cached image input tokens used.

108 

109 - `input_cached_text_tokens: optional number`

110 

111 The aggregated number of cached text input tokens used.

96 112 

97 - `input_cached_tokens: optional number`113 - `input_cached_tokens: optional number`

98 114 

99 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.115 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

116 

117 - `input_image_tokens: optional number`

118 

119 The aggregated number of uncached image input tokens used.

120 

121 - `input_text_tokens: optional number`

122 

123 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

124 

125 - `input_uncached_tokens: optional number`

126 

127 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

100 128 

101 - `model: optional string`129 - `model: optional string`

102 130 

106 134 

107 The aggregated number of audio output tokens used.135 The aggregated number of audio output tokens used.

108 136 

137 - `output_image_tokens: optional number`

138 

139 The aggregated number of image output tokens used.

140 

141 - `output_text_tokens: optional number`

142 

143 The aggregated number of text output tokens used.

144 

109 - `project_id: optional string`145 - `project_id: optional string`

110 146 

111 When `group_by=project_id`, this field provides the project ID of the grouped usage result.147 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

431 "api_key_id": "api_key_id",467 "api_key_id": "api_key_id",

432 "batch": true,468 "batch": true,

433 "input_audio_tokens": 0,469 "input_audio_tokens": 0,

470 "input_cache_write_tokens": 0,

471 "input_cached_audio_tokens": 0,

472 "input_cached_image_tokens": 0,

473 "input_cached_text_tokens": 0,

434 "input_cached_tokens": 0,474 "input_cached_tokens": 0,

475 "input_image_tokens": 0,

476 "input_text_tokens": 0,

477 "input_uncached_tokens": 0,

435 "model": "model",478 "model": "model",

436 "output_audio_tokens": 0,479 "output_audio_tokens": 0,

480 "output_image_tokens": 0,

481 "output_text_tokens": 0,

437 "project_id": "project_id",482 "project_id": "project_id",

438 "service_tier": "service_tier",483 "service_tier": "service_tier",

439 "user_id": "user_id"484 "user_id": "user_id"

62 62 

63 - `object: "bucket"`63 - `object: "bucket"`

64 64 

65 - `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`65 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

66 66 

67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

68 68 

69 The aggregated completions usage details of the specific time bucket.69 The aggregated completions usage details of the specific time bucket.

70 70 

71 - `input_tokens: number`71 - `input_tokens: number`

72 72 

73 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.73 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

74 74 

75 - `num_model_requests: number`75 - `num_model_requests: number`

76 76 

80 80 

81 - `output_tokens: number`81 - `output_tokens: number`

82 82 

83 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.83 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

84 84 

85 - `api_key_id: optional string`85 - `api_key_id: optional string`

86 86 

92 92 

93 - `input_audio_tokens: optional number`93 - `input_audio_tokens: optional number`

94 94 

95 The aggregated number of audio input tokens used, including cached tokens.95 The aggregated number of uncached audio input tokens used.

96 

97 - `input_cache_write_tokens: optional number`

98 

99 The aggregated number of input tokens written to the cache.

100 

101 - `input_cached_audio_tokens: optional number`

102 

103 The aggregated number of cached audio input tokens used.

104 

105 - `input_cached_image_tokens: optional number`

106 

107 The aggregated number of cached image input tokens used.

108 

109 - `input_cached_text_tokens: optional number`

110 

111 The aggregated number of cached text input tokens used.

96 112 

97 - `input_cached_tokens: optional number`113 - `input_cached_tokens: optional number`

98 114 

99 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.115 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

116 

117 - `input_image_tokens: optional number`

118 

119 The aggregated number of uncached image input tokens used.

120 

121 - `input_text_tokens: optional number`

122 

123 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

124 

125 - `input_uncached_tokens: optional number`

126 

127 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

100 128 

101 - `model: optional string`129 - `model: optional string`

102 130 

106 134 

107 The aggregated number of audio output tokens used.135 The aggregated number of audio output tokens used.

108 136 

137 - `output_image_tokens: optional number`

138 

139 The aggregated number of image output tokens used.

140 

141 - `output_text_tokens: optional number`

142 

143 The aggregated number of text output tokens used.

144 

109 - `project_id: optional string`145 - `project_id: optional string`

110 146 

111 When `group_by=project_id`, this field provides the project ID of the grouped usage result.147 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

431 "api_key_id": "api_key_id",467 "api_key_id": "api_key_id",

432 "batch": true,468 "batch": true,

433 "input_audio_tokens": 0,469 "input_audio_tokens": 0,

470 "input_cache_write_tokens": 0,

471 "input_cached_audio_tokens": 0,

472 "input_cached_image_tokens": 0,

473 "input_cached_text_tokens": 0,

434 "input_cached_tokens": 0,474 "input_cached_tokens": 0,

475 "input_image_tokens": 0,

476 "input_text_tokens": 0,

477 "input_uncached_tokens": 0,

435 "model": "model",478 "model": "model",

436 "output_audio_tokens": 0,479 "output_audio_tokens": 0,

480 "output_image_tokens": 0,

481 "output_text_tokens": 0,

437 "project_id": "project_id",482 "project_id": "project_id",

438 "service_tier": "service_tier",483 "service_tier": "service_tier",

439 "user_id": "user_id"484 "user_id": "user_id"

70 70 

71 - `object: "bucket"`71 - `object: "bucket"`

72 72 

73 - `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`73 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

74 74 

75 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`75 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

76 76 

77 The aggregated completions usage details of the specific time bucket.77 The aggregated completions usage details of the specific time bucket.

78 78 

79 - `input_tokens: number`79 - `input_tokens: number`

80 80 

81 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.81 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

82 82 

83 - `num_model_requests: number`83 - `num_model_requests: number`

84 84 

88 88 

89 - `output_tokens: number`89 - `output_tokens: number`

90 90 

91 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.91 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

92 92 

93 - `api_key_id: optional string`93 - `api_key_id: optional string`

94 94 

100 100 

101 - `input_audio_tokens: optional number`101 - `input_audio_tokens: optional number`

102 102 

103 The aggregated number of audio input tokens used, including cached tokens.103 The aggregated number of uncached audio input tokens used.

104 

105 - `input_cache_write_tokens: optional number`

106 

107 The aggregated number of input tokens written to the cache.

108 

109 - `input_cached_audio_tokens: optional number`

110 

111 The aggregated number of cached audio input tokens used.

112 

113 - `input_cached_image_tokens: optional number`

114 

115 The aggregated number of cached image input tokens used.

116 

117 - `input_cached_text_tokens: optional number`

118 

119 The aggregated number of cached text input tokens used.

104 120 

105 - `input_cached_tokens: optional number`121 - `input_cached_tokens: optional number`

106 122 

107 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.123 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

124 

125 - `input_image_tokens: optional number`

126 

127 The aggregated number of uncached image input tokens used.

128 

129 - `input_text_tokens: optional number`

130 

131 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

132 

133 - `input_uncached_tokens: optional number`

134 

135 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

108 136 

109 - `model: optional string`137 - `model: optional string`

110 138 

114 142 

115 The aggregated number of audio output tokens used.143 The aggregated number of audio output tokens used.

116 144 

145 - `output_image_tokens: optional number`

146 

147 The aggregated number of image output tokens used.

148 

149 - `output_text_tokens: optional number`

150 

151 The aggregated number of text output tokens used.

152 

117 - `project_id: optional string`153 - `project_id: optional string`

118 154 

119 When `group_by=project_id`, this field provides the project ID of the grouped usage result.155 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

439 "api_key_id": "api_key_id",475 "api_key_id": "api_key_id",

440 "batch": true,476 "batch": true,

441 "input_audio_tokens": 0,477 "input_audio_tokens": 0,

478 "input_cache_write_tokens": 0,

479 "input_cached_audio_tokens": 0,

480 "input_cached_image_tokens": 0,

481 "input_cached_text_tokens": 0,

442 "input_cached_tokens": 0,482 "input_cached_tokens": 0,

483 "input_image_tokens": 0,

484 "input_text_tokens": 0,

485 "input_uncached_tokens": 0,

443 "model": "model",486 "model": "model",

444 "output_audio_tokens": 0,487 "output_audio_tokens": 0,

488 "output_image_tokens": 0,

489 "output_text_tokens": 0,

445 "project_id": "project_id",490 "project_id": "project_id",

446 "service_tier": "service_tier",491 "service_tier": "service_tier",

447 "user_id": "user_id"492 "user_id": "user_id"

62 62 

63 - `object: "bucket"`63 - `object: "bucket"`

64 64 

65 - `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`65 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

66 66 

67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`67 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

68 68 

69 The aggregated completions usage details of the specific time bucket.69 The aggregated completions usage details of the specific time bucket.

70 70 

71 - `input_tokens: number`71 - `input_tokens: number`

72 72 

73 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.73 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

74 74 

75 - `num_model_requests: number`75 - `num_model_requests: number`

76 76 

80 80 

81 - `output_tokens: number`81 - `output_tokens: number`

82 82 

83 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.83 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

84 84 

85 - `api_key_id: optional string`85 - `api_key_id: optional string`

86 86 

92 92 

93 - `input_audio_tokens: optional number`93 - `input_audio_tokens: optional number`

94 94 

95 The aggregated number of audio input tokens used, including cached tokens.95 The aggregated number of uncached audio input tokens used.

96 

97 - `input_cache_write_tokens: optional number`

98 

99 The aggregated number of input tokens written to the cache.

100 

101 - `input_cached_audio_tokens: optional number`

102 

103 The aggregated number of cached audio input tokens used.

104 

105 - `input_cached_image_tokens: optional number`

106 

107 The aggregated number of cached image input tokens used.

108 

109 - `input_cached_text_tokens: optional number`

110 

111 The aggregated number of cached text input tokens used.

96 112 

97 - `input_cached_tokens: optional number`113 - `input_cached_tokens: optional number`

98 114 

99 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.115 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

116 

117 - `input_image_tokens: optional number`

118 

119 The aggregated number of uncached image input tokens used.

120 

121 - `input_text_tokens: optional number`

122 

123 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

124 

125 - `input_uncached_tokens: optional number`

126 

127 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

100 128 

101 - `model: optional string`129 - `model: optional string`

102 130 

106 134 

107 The aggregated number of audio output tokens used.135 The aggregated number of audio output tokens used.

108 136 

137 - `output_image_tokens: optional number`

138 

139 The aggregated number of image output tokens used.

140 

141 - `output_text_tokens: optional number`

142 

143 The aggregated number of text output tokens used.

144 

109 - `project_id: optional string`145 - `project_id: optional string`

110 146 

111 When `group_by=project_id`, this field provides the project ID of the grouped usage result.147 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

431 "api_key_id": "api_key_id",467 "api_key_id": "api_key_id",

432 "batch": true,468 "batch": true,

433 "input_audio_tokens": 0,469 "input_audio_tokens": 0,

470 "input_cache_write_tokens": 0,

471 "input_cached_audio_tokens": 0,

472 "input_cached_image_tokens": 0,

473 "input_cached_text_tokens": 0,

434 "input_cached_tokens": 0,474 "input_cached_tokens": 0,

475 "input_image_tokens": 0,

476 "input_text_tokens": 0,

477 "input_uncached_tokens": 0,

435 "model": "model",478 "model": "model",

436 "output_audio_tokens": 0,479 "output_audio_tokens": 0,

480 "output_image_tokens": 0,

481 "output_text_tokens": 0,

437 "project_id": "project_id",482 "project_id": "project_id",

438 "service_tier": "service_tier",483 "service_tier": "service_tier",

439 "user_id": "user_id"484 "user_id": "user_id"

50 50 

51 - `object: "bucket"`51 - `object: "bucket"`

52 52 

53 - `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`53 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

54 54 

55 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`55 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

56 56 

57 The aggregated completions usage details of the specific time bucket.57 The aggregated completions usage details of the specific time bucket.

58 58 

59 - `input_tokens: number`59 - `input_tokens: number`

60 60 

61 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.61 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

62 62 

63 - `num_model_requests: number`63 - `num_model_requests: number`

64 64 

68 68 

69 - `output_tokens: number`69 - `output_tokens: number`

70 70 

71 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.71 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

72 72 

73 - `api_key_id: optional string`73 - `api_key_id: optional string`

74 74 

80 80 

81 - `input_audio_tokens: optional number`81 - `input_audio_tokens: optional number`

82 82 

83 The aggregated number of audio input tokens used, including cached tokens.83 The aggregated number of uncached audio input tokens used.

84 

85 - `input_cache_write_tokens: optional number`

86 

87 The aggregated number of input tokens written to the cache.

88 

89 - `input_cached_audio_tokens: optional number`

90 

91 The aggregated number of cached audio input tokens used.

92 

93 - `input_cached_image_tokens: optional number`

94 

95 The aggregated number of cached image input tokens used.

96 

97 - `input_cached_text_tokens: optional number`

98 

99 The aggregated number of cached text input tokens used.

84 100 

85 - `input_cached_tokens: optional number`101 - `input_cached_tokens: optional number`

86 102 

87 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.103 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

104 

105 - `input_image_tokens: optional number`

106 

107 The aggregated number of uncached image input tokens used.

108 

109 - `input_text_tokens: optional number`

110 

111 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

112 

113 - `input_uncached_tokens: optional number`

114 

115 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

88 116 

89 - `model: optional string`117 - `model: optional string`

90 118 

94 122 

95 The aggregated number of audio output tokens used.123 The aggregated number of audio output tokens used.

96 124 

125 - `output_image_tokens: optional number`

126 

127 The aggregated number of image output tokens used.

128 

129 - `output_text_tokens: optional number`

130 

131 The aggregated number of text output tokens used.

132 

97 - `project_id: optional string`133 - `project_id: optional string`

98 134 

99 When `group_by=project_id`, this field provides the project ID of the grouped usage result.135 When `group_by=project_id`, this field provides the project ID of the grouped usage result.

419 "api_key_id": "api_key_id",455 "api_key_id": "api_key_id",

420 "batch": true,456 "batch": true,

421 "input_audio_tokens": 0,457 "input_audio_tokens": 0,

458 "input_cache_write_tokens": 0,

459 "input_cached_audio_tokens": 0,

460 "input_cached_image_tokens": 0,

461 "input_cached_text_tokens": 0,

422 "input_cached_tokens": 0,462 "input_cached_tokens": 0,

463 "input_image_tokens": 0,

464 "input_text_tokens": 0,

465 "input_uncached_tokens": 0,

423 "model": "model",466 "model": "model",

424 "output_audio_tokens": 0,467 "output_audio_tokens": 0,

468 "output_image_tokens": 0,

469 "output_text_tokens": 0,

425 "project_id": "project_id",470 "project_id": "project_id",

426 "service_tier": "service_tier",471 "service_tier": "service_tier",

427 "user_id": "user_id"472 "user_id": "user_id"

66 66 

67 - `object: "bucket"`67 - `object: "bucket"`

68 68 

69 - `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`69 - `results: array of object { input_tokens, num_model_requests, object, 19 more } or object { input_tokens, num_model_requests, object, 4 more } or object { input_tokens, num_model_requests, object, 4 more } or 8 more`

70 70 

71 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 10 more }`71 - `organization.usage.completions.result: object { input_tokens, num_model_requests, object, 19 more }`

72 72 

73 The aggregated completions usage details of the specific time bucket.73 The aggregated completions usage details of the specific time bucket.

74 74 

75 - `input_tokens: number`75 - `input_tokens: number`

76 76 

77 The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens.77 The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

78 78 

79 - `num_model_requests: number`79 - `num_model_requests: number`

80 80 

84 84 

85 - `output_tokens: number`85 - `output_tokens: number`

86 86 

87 The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens.87 The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

88 88 

89 - `api_key_id: optional string`89 - `api_key_id: optional string`

90 90 

96 96 

97 - `input_audio_tokens: optional number`97 - `input_audio_tokens: optional number`

98 98 

99 The aggregated number of audio input tokens used, including cached tokens.99 The aggregated number of uncached audio input tokens used.

100 

101 - `input_cache_write_tokens: optional number`

102 

103 The aggregated number of input tokens written to the cache.

104 

105 - `input_cached_audio_tokens: optional number`

106 

107 The aggregated number of cached audio input tokens used.

108 

109 - `input_cached_image_tokens: optional number`

110 

111 The aggregated number of cached image input tokens used.

112 

113 - `input_cached_text_tokens: optional number`

114 

115 The aggregated number of cached text input tokens used.

100 116 

101 - `input_cached_tokens: optional number`117 - `input_cached_tokens: optional number`

102 118 

103 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.119 The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens.

120 

121 - `input_image_tokens: optional number`

122 

123 The aggregated number of uncached image input tokens used.

124 

125 - `input_text_tokens: optional number`

126 

127 The aggregated number of uncached text input tokens used, excluding cache-write tokens.

128 

129 - `input_uncached_tokens: optional number`

130 

131 The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens.

104 132 

105 - `model: optional string`133 - `model: optional string`

106 134 

110 138 

111 The aggregated number of audio output tokens used.139 The aggregated number of audio output tokens used.

112 140 

141 - `output_image_tokens: optional number`

142 

143 The aggregated number of image output tokens used.

144 

145 - `output_text_tokens: optional number`

146 

147 The aggregated number of text output tokens used.

148 

113 - `project_id: optional string`149 - `project_id: optional string`