@@ -965,7 +965,7 @@ paths:
965965 Your input file must be formatted as a [JSONL
966966 file](/docs/api-reference/batch/request-input), and must be
967967 uploaded with the purpose `batch`. The file can contain up
968- to 50,000 requests, and can be up to 100 MB in size.
968+ to 50,000 requests, and can be up to 200 MB in size.
969969 endpoint:
970970 type: string
971971 enum:
@@ -2375,7 +2375,7 @@ paths:
23752375 [completions](/docs/api-reference/fine-tuning/completions-input) models.
23762376
23772377
2378- The Batch API only supports `.jsonl` files up to 100 MB in size. The
2378+ The Batch API only supports `.jsonl` files up to 200 MB in size. The
23792379 input also has a specific required
23802380 [format](/docs/api-reference/batch/request-input).
23812381
@@ -4664,6 +4664,161 @@ paths:
46644664 "archived_at": 1711471533,
46654665 "status": "archived"
46664666 }
4667+ /organization/projects/{project_id}/rate_limits:
4668+ get:
4669+ summary: Returns the rate limits per model for a project.
4670+ operationId: list-project-rate-limits
4671+ tags:
4672+ - Projects
4673+ parameters:
4674+ - name: project_id
4675+ in: path
4676+ description: The ID of the project.
4677+ required: true
4678+ schema:
4679+ type: string
4680+ - name: limit
4681+ in: query
4682+ description: |
4683+ A limit on the number of objects to be returned. The default is 100.
4684+ required: false
4685+ schema:
4686+ type: integer
4687+ default: 100
4688+ - name: after
4689+ in: query
4690+ description: >
4691+ A cursor for use in pagination. `after` is an object ID that defines
4692+ your place in the list. For instance, if you make a list request and
4693+ receive 100 objects, ending with obj_foo, your subsequent call can
4694+ include after=obj_foo in order to fetch the next page of the list.
4695+ required: false
4696+ schema:
4697+ type: string
4698+ - name: before
4699+ in: query
4700+ description: >
4701+ A cursor for use in pagination. `before` is an object ID that
4702+ defines your place in the list. For instance, if you make a list
4703+ request and receive 100 objects, beginning with obj_foo, your
4704+ subsequent call can include before=obj_foo in order to fetch the
4705+ previous page of the list.
4706+ required: false
4707+ schema:
4708+ type: string
4709+ responses:
4710+ "200":
4711+ description: Project rate limits listed successfully.
4712+ content:
4713+ application/json:
4714+ schema:
4715+ $ref: "#/components/schemas/ProjectRateLimitListResponse"
4716+ x-oaiMeta:
4717+ name: List project rate limits
4718+ group: administration
4719+ returns: A list of
4720+ [ProjectRateLimit](/docs/api-reference/project-rate-limits/object)
4721+ objects.
4722+ examples:
4723+ request:
4724+ curl: >
4725+ curl
4726+ https://api.openai.com/v1/organization/projects/proj_abc/rate_limits?after=rl_xxx&limit=20
4727+ \
4728+ -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \
4729+ -H "Content-Type: application/json"
4730+ response: |
4731+ {
4732+ "object": "list",
4733+ "data": [
4734+ {
4735+ "object": "project.rate_limit",
4736+ "id": "rl-ada",
4737+ "model": "ada",
4738+ "max_requests_per_1_minute": 600,
4739+ "max_tokens_per_1_minute": 150000,
4740+ "max_images_per_1_minute": 10
4741+ }
4742+ ],
4743+ "first_id": "rl-ada",
4744+ "last_id": "rl-ada",
4745+ "has_more": false
4746+ }
4747+ error_response: |
4748+ {
4749+ "code": 404,
4750+ "message": "The project {project_id} was not found"
4751+ }
4752+ /organization/projects/{project_id}/rate_limits/{rate_limit_id}:
4753+ post:
4754+ summary: Updates a project rate limit.
4755+ operationId: update-project-rate-limits
4756+ tags:
4757+ - Projects
4758+ parameters:
4759+ - name: project_id
4760+ in: path
4761+ description: The ID of the project.
4762+ required: true
4763+ schema:
4764+ type: string
4765+ - name: rate_limit_id
4766+ in: path
4767+ description: The ID of the rate limit.
4768+ required: true
4769+ schema:
4770+ type: string
4771+ requestBody:
4772+ description: The project rate limit update request payload.
4773+ required: true
4774+ content:
4775+ application/json:
4776+ schema:
4777+ $ref: "#/components/schemas/ProjectRateLimitUpdateRequest"
4778+ responses:
4779+ "200":
4780+ description: Project rate limit updated successfully.
4781+ content:
4782+ application/json:
4783+ schema:
4784+ $ref: "#/components/schemas/ProjectRateLimit"
4785+ "400":
4786+ description: Error response for various conditions.
4787+ content:
4788+ application/json:
4789+ schema:
4790+ $ref: "#/components/schemas/ErrorResponse"
4791+ x-oaiMeta:
4792+ name: Modify project rate limit
4793+ group: administration
4794+ returns: The updated
4795+ [ProjectRateLimit](/docs/api-reference/project-rate-limits/object)
4796+ object.
4797+ examples:
4798+ request:
4799+ curl: >
4800+ curl -X POST
4801+ https://api.openai.com/v1/organization/projects/proj_abc/rate_limits/rl_xxx
4802+ \
4803+ -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \
4804+ -H "Content-Type: application/json" \
4805+ -d '{
4806+ "max_requests_per_1_minute": 500
4807+ }'
4808+ response: |
4809+ {
4810+ "object": "project.rate_limit",
4811+ "id": "rl-ada",
4812+ "model": "ada",
4813+ "max_requests_per_1_minute": 600,
4814+ "max_tokens_per_1_minute": 150000,
4815+ "max_images_per_1_minute": 10
4816+ }
4817+ error_response: |
4818+ {
4819+ "code": 404,
4820+ "message": "The project {project_id} was not found"
4821+ }
46674822 /organization/projects/{project_id}/service_accounts:
46684823 get:
46694824 summary: Returns a list of service accounts in the project.
@@ -10288,6 +10443,44 @@ components:
1028810443 id:
1028910444 type: string
1029010445 description: The project ID.
10446+ rate_limit.updated:
10447+ type: object
10448+ description: The details for events with this `type`.
10449+ properties:
10450+ id:
10451+ type: string
10452+ description: The rate limit ID
10453+ changes_requested:
10454+ type: object
10455+ description: The payload used to update the rate limits.
10456+ properties:
10457+ max_requests_per_1_minute:
10458+ type: int
10459+ description: The maximum requests per minute.
10460+ max_tokens_per_1_minute:
10461+ type: int
10462+ description: The maximum tokens per minute.
10463+ max_images_per_1_minute:
10464+ type: int
10465+ description: The maximum images per minute. Only relevant for certain models.
10466+ max_audio_megabytes_per_1_minute:
10467+ type: int
10468+ description: The maximum audio megabytes per minute. Only relevant for certain
10469+ models.
10470+ max_requests_per_1_day:
10471+ type: int
10472+ description: The maximum requests per day. Only relevant for certain models.
10473+ batch_1_day_max_input_tokens:
10474+ type: int
10475+ description: The maximum batch input tokens per day. Only relevant for certain
10476+ models.
10477+ rate_limit.deleted:
10478+ type: object
10479+ description: The details for events with this `type`.
10480+ properties:
10481+ id:
10482+ type: string
10483+ description: The rate limit ID
1029110484 service_account.created:
1029210485 type: object
1029310486 description: The details for events with this `type`.
@@ -10469,6 +10662,8 @@ components:
1046910662 - service_account.created
1047010663 - service_account.updated
1047110664 - service_account.deleted
10665+ - rate_limit.updated
10666+ - rate_limit.deleted
1047210667 - user.added
1047310668 - user.updated
1047410669 - user.deleted
@@ -12021,7 +12216,7 @@ components:
1202112216 x-oaiExpandable: true
1202212217 description: >
1202312218 Configuration for a [Predicted
12024- Output](/docs/guides/latency-optimization#use- predicted-outputs),
12219+ Output](/docs/guides/predicted-outputs),
1202512220
1202612221 which can greatly improve response times when large parts of the
1202712222 model
@@ -17322,6 +17517,104 @@ components:
1732217517 - first_id
1732317518 - last_id
1732417519 - has_more
17520+ ProjectRateLimit:
17521+ type: object
17522+ description: Represents a project rate limit config.
17523+ properties:
17524+ object:
17525+ type: string
17526+ enum:
17527+ - project.rate_limit
17528+ description: The object type, which is always `project.rate_limit`
17529+ id:
17530+ type: string
17531+ description: The identifier, which can be referenced in API endpoints.
17532+ model:
17533+ type: string
17534+ description: The model this rate limit applies to.
17535+ max_requests_per_1_minute:
17536+ type: int
17537+ description: The maximum requests per minute.
17538+ max_tokens_per_1_minute:
17539+ type: int
17540+ description: The maximum tokens per minute.
17541+ max_images_per_1_minute:
17542+ type: int
17543+ description: The maximum images per minute. Only present for relevant models.
17544+ max_audio_megabytes_per_1_minute:
17545+ type: int
17546+ description: The maximum audio megabytes per minute. Only present for relevant
17547+ models.
17548+ max_requests_per_1_day:
17549+ type: int
17550+ description: The maximum requests per day. Only present for relevant models.
17551+ batch_1_day_max_input_tokens:
17552+ type: int
17553+ description: The maximum batch input tokens per day. Only present for relevant
17554+ models.
17555+ required:
17556+ - object
17557+ - id
17558+ - model
17559+ - max_requests_per_1_minute
17560+ - max_tokens_per_1_minute
17561+ x-oaiMeta:
17562+ name: The project rate limit object
17563+ example: |
17564+ {
17565+ "object": "project.rate_limit",
17566+ "id": "rl_ada",
17567+ "model": "ada",
17568+ "max_requests_per_1_minute": 600,
17569+ "max_tokens_per_1_minute": 150000,
17570+ "max_images_per_1_minute": 10
17571+ }
17572+ ProjectRateLimitListResponse:
17573+ type: object
17574+ properties:
17575+ object:
17576+ type: string
17577+ enum:
17578+ - list
17579+ data:
17580+ type: array
17581+ items:
17582+ $ref: "#/components/schemas/ProjectRateLimit"
17583+ first_id:
17584+ type: string
17585+ last_id:
17586+ type: string
17587+ has_more:
17588+ type: boolean
17589+ required:
17590+ - object
17591+ - data
17592+ - first_id
17593+ - last_id
17594+ - has_more
17595+ ProjectRateLimitUpdateRequest:
17596+ type: object
17597+ properties:
17598+ max_requests_per_1_minute:
17599+ type: int
17600+ description: The maximum requests per minute.
17601+ max_tokens_per_1_minute:
17602+ type: int
17603+ description: The maximum tokens per minute.
17604+ max_images_per_1_minute:
17605+ type: int
17606+ description: The maximum images per minute. Only relevant for certain models.
17607+ max_audio_megabytes_per_1_minute:
17608+ type: int
17609+ description: The maximum audio megabytes per minute. Only relevant for certain
17610+ models.
17611+ max_requests_per_1_day:
17612+ type: int
17613+ description: The maximum requests per day. Only relevant for certain models.
17614+ batch_1_day_max_input_tokens:
17615+ type: int
17616+ description: The maximum batch input tokens per day. Only relevant for certain
17617+ models.
1732517618 ProjectServiceAccount:
1732617619 type: object
1732717620 description: Represents an individual service account in a project.
@@ -18991,9 +19284,13 @@ components:
1899119284 "input_tokens":127,
1899219285 "output_tokens":148,
1899319286 "input_token_details": {
18994- "cached_tokens":0 ,
19287+ "cached_tokens":384 ,
1899519288 "text_tokens":119,
18996- "audio_tokens":8
19289+ "audio_tokens":8,
19290+ "cached_tokens_details": {
19291+ "text_tokens": 128,
19292+ "audio_tokens": 256
19293+ }
1899719294 },
1899819295 "output_token_details": {
1899919296 "text_tokens":36,
@@ -22265,6 +22562,22 @@ x-oaiMeta:
2226522562 - type: object
2226622563 key: ProjectApiKey
2226722564 path: object
22565+ - id: project-rate-limits
22566+ title: Project rate limits
22567+ description: >
22568+ Manage rate limits per model for projects. Rate limits may be configured
22569+ to be equal to or lower than the organization's rate limits.
22570+ navigationGroup: administration
22571+ sections:
22572+ - type: endpoint
22573+ key: list-project-rate-limits
22574+ path: list
22575+ - type: endpoint
22576+ key: update-project-rate-limits
22577+ path: update
22578+ - type: object
22579+ key: ProjectRateLimit
22580+ path: object
2226822581 - id: audit-logs
2226922582 title: Audit logs
2227022583 description: >
0 commit comments