Portkey Rate Limits Policies API

openapi: 3.0.0
info:
  title: Portkey Analytics > Graphs Rate Limits Policies API
  description: The Portkey REST API. Please see https://portkey.ai/docs/api-reference for more details.
  version: 2.0.0
  termsOfService: https://portkey.ai/terms
  contact:
    name: Portkey Developer Forum
    url: https://portkey.wiki/community
  license:
    name: MIT
    url: https://github.com/Portkey-AI/portkey-openapi/blob/master/LICENSE
servers:
- url: https://api.portkey.ai/v1
  description: Portkey API Public Endpoint
security:
- Portkey-Key: []
tags:
- name: Rate Limits Policies
  description: Manage rate limits policies to control request or token rates
paths:
  /policies/rate-limits:
    post:
      tags:
      - Rate Limits Policies
      summary: Create Rate Limits Policy
      description: Create a new rate limits policy to control the rate of requests or tokens consumed per minute, hour, or day.
      operationId: createRateLimitsPolicy
      security:
      - Portkey-Key: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateRateLimitsPolicyRequest'
            examples:
              requestsPerMinute:
                summary: 100 Requests per Minute per API Key
                value:
                  name: 100 RPM per API Key
                  conditions:
                  - key: workspace_id
                    value: workspace-123
                  group_by:
                  - key: api_key
                  type: requests
                  unit: rpm
                  value: 100
              tokensPerHour:
                summary: 10K Tokens per Hour per User
                value:
                  name: 10K Tokens per Hour per User
                  conditions:
                  - key: workspace_id
                    value: workspace-123
                  group_by:
                  - key: metadata.user_id
                  type: tokens
                  unit: rph
                  value: 10000
      responses:
        '200':
          description: Policy created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreatePolicyResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '500':
          description: Server error
    get:
      tags:
      - Rate Limits Policies
      summary: List Rate Limits Policies
      description: List all rate limits policies with optional filtering.
      operationId: listRateLimitsPolicies
      security:
      - Portkey-Key: []
      parameters:
      - $ref: '#/components/parameters/WorkspaceIdQuery'
      - name: status
        in: query
        description: Filter by status
        required: false
        schema:
          type: string
          enum:
          - active
          - archived
          default: active
      - name: type
        in: query
        description: Filter by policy type
        required: false
        schema:
          type: string
          enum:
          - requests
          - tokens
      - name: unit
        in: query
        description: Filter by rate unit
        required: false
        schema:
          type: string
          enum:
          - rpm
          - rph
          - rpd
      - $ref: '#/components/parameters/PageSize'
      - $ref: '#/components/parameters/CurrentPage'
      responses:
        '200':
          description: List of rate limits policies
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RateLimitsPolicyListResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '404':
          description: Policy not found
        '500':
          description: Server error
  /policies/rate-limits/{rateLimitsPolicyId}:
    get:
      tags:
      - Rate Limits Policies
      summary: Get Rate Limits Policy
      description: Get a single rate limits policy by ID.
      operationId: getRateLimitsPolicy
      security:
      - Portkey-Key: []
      parameters:
      - $ref: '#/components/parameters/RateLimitsPolicyId'
      - name: status
        in: query
        description: Filter by status
        required: false
        schema:
          type: string
          enum:
          - active
          - archived
          default: active
      responses:
        '200':
          description: Rate limits policy details
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RateLimitsPolicyResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '404':
          description: Policy not found
        '500':
          description: Server error
    put:
      tags:
      - Rate Limits Policies
      summary: Update Rate Limits Policy
      description: Update an existing rate limits policy.
      operationId: updateRateLimitsPolicy
      security:
      - Portkey-Key: []
      parameters:
      - $ref: '#/components/parameters/RateLimitsPolicyId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UpdateRateLimitsPolicyRequest'
            example:
              value: 200
              unit: rph
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
              example: {}
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '404':
          description: Policy not found
        '500':
          description: Server error
    delete:
      tags:
      - Rate Limits Policies
      summary: Delete Rate Limits Policy
      description: Delete a rate limits policy.
      operationId: deleteRateLimitsPolicy
      security:
      - Portkey-Key: []
      parameters:
      - $ref: '#/components/parameters/RateLimitsPolicyId'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
              example: {}
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '404':
          description: Policy not found
        '500':
          description: Server error
components:
  schemas:
    RateLimitsPolicyListResponse:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/RateLimitsPolicy'
        total:
          type: integer
          description: Total number of policies
    CreateRateLimitsPolicyRequest:
      type: object
      required:
      - conditions
      - group_by
      - type
      - unit
      - value
      properties:
        name:
          type: string
          maxLength: 255
          description: Policy name
          example: 100 Requests per Minute
        conditions:
          type: array
          minItems: 1
          items:
            $ref: '#/components/schemas/Condition'
          description: Array of conditions that define which requests the policy applies to
        group_by:
          type: array
          minItems: 1
          items:
            $ref: '#/components/schemas/GroupBy'
          description: Array of group by fields that define how usage is aggregated
        type:
          type: string
          enum:
          - requests
          - tokens
          description: Policy type
        unit:
          type: string
          enum:
          - rpm
          - rph
          - rpd
          description: 'Rate unit:

            - `rpm` - Requests/Tokens per minute

            - `rph` - Requests/Tokens per hour

            - `rpd` - Requests/Tokens per day

            '
        value:
          type: number
          description: Rate limit value
        workspace_id:
          type: string
          description: Workspace ID or slug. Required if not using API key authentication.
        organisation_id:
          type: string
          format: uuid
          description: Organization ID. Required if not using API key authentication.
    RateLimitsPolicyResponse:
      allOf:
      - $ref: '#/components/schemas/RateLimitsPolicy'
      - type: object
        properties:
          object:
            type: string
            example: policy_rate_limits
    GroupBy:
      type: object
      required:
      - key
      properties:
        key:
          type: string
          description: 'Group by key. Valid values:

            - `api_key` - Group by API key

            - `organisation_id` - Group by organization

            - `workspace_id` - Group by workspace

            - `metadata.*` - Group by custom metadata fields

            '
          example: api_key
    CreatePolicyResponse:
      type: object
      properties:
        id:
          type: string
          format: uuid
          description: Created policy UUID
        object:
          type: string
          description: Resource type
          example: policy_usage_limits
    Condition:
      type: object
      required:
      - key
      - value
      properties:
        key:
          type: string
          description: 'Condition key. Valid values:

            - `api_key` - Apply to a specific API key

            - `organisation_id` - Apply to an organization

            - `workspace_id` - Apply to a workspace

            - `metadata.*` - Apply based on custom metadata fields (e.g., `metadata.user_id`, `metadata.team`)

            '
          example: workspace_id
        value:
          type: string
          description: Condition value
          example: workspace-123
    RateLimitsPolicy:
      type: object
      required:
      - id
      - type
      - unit
      - value
      - status
      - workspace_id
      - organisation_id
      - created_at
      - last_updated_at
      properties:
        id:
          type: string
          format: uuid
          description: Policy UUID
        name:
          type: string
          nullable: true
          description: Policy name
        conditions:
          type: array
          items:
            $ref: '#/components/schemas/Condition'
          description: Array of conditions
        group_by:
          type: array
          items:
            $ref: '#/components/schemas/GroupBy'
          description: Array of group by fields
        type:
          type: string
          enum:
          - requests
          - tokens
          description: Policy type
        unit:
          type: string
          enum:
          - rpm
          - rph
          - rpd
          description: Rate unit
        value:
          type: number
          description: Rate limit value
        status:
          type: string
          enum:
          - active
          - archived
          description: Policy status
        workspace_id:
          type: string
          format: uuid
          description: Workspace UUID
        organisation_id:
          type: string
          format: uuid
          description: Organization UUID
        created_at:
          type: string
          format: date-time
          description: Creation timestamp
        last_updated_at:
          type: string
          format: date-time
          description: Last update timestamp
    UpdateRateLimitsPolicyRequest:
      type: object
      properties:
        name:
          type: string
          maxLength: 255
          description: Policy name
        unit:
          type: string
          enum:
          - rpm
          - rph
          - rpd
          description: Rate unit
        value:
          type: number
          description: Rate limit value
  parameters:
    WorkspaceIdQuery:
      name: workspace_id
      in: query
      required: false
      description: Workspace ID or slug
      schema:
        type: string
    CurrentPage:
      in: query
      name: current_page
      schema:
        type: integer
        minimum: 0
      description: Current page number
    RateLimitsPolicyId:
      name: rateLimitsPolicyId
      in: path
      required: true
      description: Rate limits policy UUID
      schema:
        type: string
        format: uuid
    PageSize:
      in: query
      name: page_size
      schema:
        type: integer
        minimum: 0
      description: Number of items per page
  securitySchemes:
    Portkey-Key:
      type: apiKey
      in: header
      name: x-portkey-api-key
    Virtual-Key:
      type: apiKey
      in: header
      name: x-portkey-virtual-key
    Provider-Auth:
      type: http
      scheme: bearer
    Provider-Name:
      type: apiKey
      in: header
      name: x-portkey-provider
    Config:
      type: apiKey
      in: header
      name: x-portkey-config
    Custom-Host:
      type: apiKey
      in: header
      name: x-portkey-custom-host
x-server-groups:
  ControlPlaneServers:
  - url: https://api.portkey.ai/v1
    description: Portkey API Public Endpoint
  - url: SELF_HOSTED_CONTROL_PLANE_URL
    description: Self-Hosted Control Plane URL
  DataPlaneServers:
  - url: https://api.portkey.ai/v1
    description: Portkey API Public Endpoint
  - url: SELF_HOSTED_GATEWAY_URL
    description: Self-Hosted Gateway URL
  PublicServers:
  - url: https://api.portkey.ai
    description: Portkey Public API (no auth required)
x-mint:
  mcp:
    enabled: true
    name: Portkey MCP
    description: Official MCP Server for Portkey Docs & APIs
x-code-samples:
  navigationGroups:
  - id: endpoints
    title: Endpoints
  - id: assistants
    title: Assistants
  - id: legacy
    title: Legacy
  groups:
  - id: audio
    title: Audio
    description: 'Learn how to turn audio into text or text into audio.


      Related guide: [Speech to text](https://platform.openai.com/docs/guides/speech-to-text)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createSpeech
      path: createSpeech
    - type: endpoint
      key: createTranscription
      path: createTranscription
    - type: endpoint
      key: createTranslation
      path: createTranslation
    - type: object
      key: CreateTranscriptionResponseJson
      path: json-object
    - type: object
      key: CreateTranscriptionResponseVerboseJson
      path: verbose-json-object
  - id: chat
    title: Chat
    description: 'Given a list of messages comprising a conversation, the model will return a response.


      Related guide: [Chat Completions](https://platform.openai.com/docs/guides/text-generation)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createChatCompletion
      path: create
    - type: object
      key: CreateChatCompletionResponse
      path: object
    - type: object
      key: CreateChatCompletionStreamResponse
      path: streaming
  - id: realtime
    title: Realtime
    description: 'WebSocket proxy for provider Realtime APIs (`GET` upgrade). Use `wss://` with the same `/v1` data-plane base as other gateway routes.


      Related guide: [OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: connectRealtime
      path: connect
  - id: embeddings
    title: Embeddings
    description: 'Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.


      Related guide: [Embeddings](https://platform.openai.com/docs/guides/embeddings)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createEmbedding
      path: create
    - type: object
      key: Embedding
      path: object
  - id: rerank
    title: Rerank
    description: 'Rerank a list of documents based on their relevance to a query. Reranking improves search results by scoring documents based on semantic relevance rather than keyword matching.


      Supported providers: Cohere, Voyage, Jina, Pinecone, Bedrock, Azure AI.

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createRerank
      path: create
    - type: object
      key: CreateRerankResponse
      path: object
  - id: fine-tuning
    title: Fine-tuning
    description: 'Manage fine-tuning jobs to tailor a model to your specific training data.


      Related guide: [Fine-tune models](https://platform.openai.com/docs/guides/fine-tuning)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createFineTuningJob
      path: create
    - type: endpoint
      key: listPaginatedFineTuningJobs
      path: list
    - type: endpoint
      key: listFineTuningEvents
      path: list-events
    - type: endpoint
      key: listFineTuningJobCheckpoints
      path: list-checkpoints
    - type: endpoint
      key: retrieveFineTuningJob
      path: retrieve
    - type: endpoint
      key: cancelFineTuningJob
      path: cancel
    - type: object
      key: FinetuneChatRequestInput
      path: chat-input
    - type: object
      key: FinetuneCompletionRequestInput
      path: completions-input
    - type: object
      key: FineTuningJob
      path: object
    - type: object
      key: FineTuningJobEvent
      path: event-object
    - type: object
      key: FineTuningJobCheckpoint
      path: checkpoint-object
  - id: batch
    title: Batch
    description: 'Create large batches of API requests for asynchronous processing. The Batch API returns completions within 24 hours for a 50% discount.


      Related guide: [Batch](https://platform.openai.com/docs/guides/batch)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createBatch
      path: create
    - type: endpoint
      key: retrieveBatch
      path: retrieve
    - type: endpoint
      key: cancelBatch
      path: cancel
    - type: endpoint
      key: listBatches
      path: list
    - type: object
      key: Batch
      path: object
    - type: object
      key: BatchRequestInput
      path: request-input
    - type: object
      key: BatchRequestOutput
      path: request-output
  - id: files
    title: Files
    description: 'Files are used to upload documents that can be used with features like [Assistants](https://platform.openai.com/docs/api-reference/assistants), [Fine-tuning](https://platform.openai.com/docs/api-reference/fine-tuning), and [Batch API](https://platform.openai.com/docs/guides/batch).

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createFile
      path: create
    - type: endpoint
      key: listFiles
      path: list
    - type: endpoint
      key: retrieveFile
      path: retrieve
    - type: endpoint
      key: deleteFile
      path: delete
    - type: endpoint
      key: downloadFile
      path: retrieve-contents
    - type: object
      key: OpenAIFile
      path: object
  - id: images
    title: Images
    description: 'Given a prompt and/or an input image, the model will generate a new image.


      Related guide: [Image generation](https://platform.openai.com/docs/guides/images)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createImage
      path: create
    - type: endpoint
      key: createImageEdit
      path: createEdit
    - type: endpoint
      key: createImageVariation
      path: createVariation
    - type: object
      key: Image
      path: object
  - id: models
    title: Models
    description: 'List and describe the various models available in the API. You can refer to the [Models](https://platform.openai.com/docs/models) documentation to understand what models are available and the differences between them.

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: listModels
      path: list
    - type: endpoint
      key: retrieveModel
      path: retrieve
    - type: endpoint
      key: deleteModel
      path: delete
    - type: object
      key: Model
      path: object
  - id: moderations
    title: Moderations
    description: 'Given some input text, outputs if the model classifies it as potentially harmful across several categories.


      Related guide: [Moderations](https://platform.openai.com/docs/guides/moderation)

      '
    navigationGroup: endpoints
    sections:
    - type: endpoint
      key: createModeration
      path: create
    - type: object
      key: CreateModerationResponse
      path: object
  - id: assistants
    title: Assistants
    beta: true
    description: 'Build assistants that can call models and use tools to perform tasks.


      [Get started with the Assistants API](https://platform.openai.com/docs/assistants)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createAssistant
      path: createAssistant
    - type: endpoint
      key: listAssistants
      path: listAssistants
    - type: endpoint
      key: getAssistant
      path: getAssistant
    - type: endpoint
      key: modifyAssistant
      path: modifyAssistant
    - type: endpoint
      key: deleteAssistant
      path: deleteAssistant
    - type: object
      key: AssistantObject
      path: object
  - id: threads
    title: Threads
    beta: true
    description: 'Create threads that assistants can interact with.


      Related guide: [Assistants](https://platform.openai.com/docs/assistants/overview)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createThread
      path: createThread
    - type: endpoint
      key: getThread
      path: getThread
    - type: endpoint
      key: modifyThread
      path: modifyThread
    - type: endpoint
      key: deleteThread
      path: deleteThread
    - type: object
      key: ThreadObject
      path: object
  - id: messages
    title: Messages
    beta: true
    description: 'Create messages within threads


      Related guide: [Assistants](https://platform.openai.com/docs/assistants/overview)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createMessage
      path: createMessage
    - type: endpoint
      key: listMessages
      path: listMessages
    - type: endpoint
      key: getMessage
      path: getMessage
    - type: endpoint
      key: modifyMessage
      path: modifyMessage
    - type: endpoint
      key: deleteMessage
      path: deleteMessage
    - type: object
      key: MessageObject
      path: object
  - id: runs
    title: Runs
    beta: true
    description: 'Represents an execution run on a thread.


      Related guide: [Assistants](https://platform.openai.com/docs/assistants/overview)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createRun
      path: createRun
    - type: endpoint
      key: createThreadAndRun
      path: createThreadAndRun
    - type: endpoint
      key: listRuns
      path: listRuns
    - type: endpoint
      key: getRun
      path: getRun
    - type: endpoint
      key: modifyRun
      path: modifyRun
    - type: endpoint
      key: submitToolOuputsToRun
      path: submitToolOutputs
    - type: endpoint
      key: cancelRun
      path: cancelRun
    - type: object
      key: RunObject
      path: object
  - id: run-steps
    title: Run Steps
    beta: true
    description: 'Represents the steps (model and tool calls) taken during the run.


      Related guide: [Assistants](https://platform.openai.com/docs/assistants/overview)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: listRunSteps
      path: listRunSteps
    - type: endpoint
      key: getRunStep
      path: getRunStep
    - type: object
      key: RunStepObject
      path: step-object
  - id: vector-stores
    title: Vector Stores
    beta: true
    description: 'Vector stores are used to store files for use by the `file_search` tool.


      Related guide: [File Search](https://platform.openai.com/docs/assistants/tools/file-search)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createVectorStore
      path: create
    - type: endpoint
      key: listVectorStores
      path: list
    - type: endpoint
      key: getVectorStore
      path: retrieve
    - type: endpoint
      key: modifyVectorStore
      path: modify
    - type: endpoint
      key: deleteVectorStore
      path: delete
    - type: object
      key: VectorStoreObject
      path: object
  - id: vector-stores-files
    title: Vector Store Files
    beta: true
    description: 'Vector store files represent files inside a vector store.


      Related guide: [File Search](https://platform.openai.com/docs/assistants/tools/file-search)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createVectorStoreFile
      path: createFile
    - type: endpoint
      key: listVectorStoreFiles
      path: listFiles
    - type: endpoint
      key: getVectorStoreFile
      path: getFile
    - type: endpoint
      key: deleteVectorStoreFile
      path: deleteFile
    - type: object
      key: VectorStoreFileObject
      path: file-object
  - id: vector-stores-file-batches
    title: Vector Store File Batches
    beta: true
    description: 'Vector store file batches represent operations to add multiple files to a vector store.


      Related guide: [File Search](https://platform.openai.com/docs/assistants/tools/file-search)

      '
    navigationGroup: assistants
    sections:
    - type: endpoint
      key: createVectorStoreFileBatch
      path: createBatch
    - type: endpoint
      key: getVectorStoreFileBatch
      path: getBatch
    - type: endpoint
      key: cancelVectorStoreFileBatch
      path: cancelBatch
    - type: endpoint
      key: listFilesInVectorStoreBatch
      path: listBatchFiles
    - type: object
      key: VectorStoreFileBatchObject
      path: batch-object
  - id: assistants-streaming
    title: Streaming
    beta: true
    description: 'Stream the result of executing a Run or resuming a Run after submitting tool outputs.


      You can stream events from the [Create Thread and Run](https://platform.openai.com/docs/api-reference/runs/createThreadAndRun),

      [Create Run](https://platform.openai.com/docs/api-reference/runs/createRun), and [Submit Tool Outputs](https://platform.openai.com/docs/api-reference/runs/submitToolOutputs)

      endpoints by passing `"stream": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream.


      Our Node and Python SDKs provide helpful utilities to make streaming easy. Reference the

      [Assistants API quickstart](https://platform.openai.com/docs/assistants/overview) to learn more.

      '
    navigationGroup: assistants
    sections:
    - type: object
      key: MessageDeltaObject
      path: message-delta-object
    - type: object
      key: RunStepDeltaObject
      path: run-step-delta-object
    - type: object
      key: AssistantStreamEvent
      path: events
  - id: completions
    title: Completions
    legacy: true
    navigationGroup: legacy
    description: 'Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our [Chat Completions API](https://platform.openai.com/docs/guides/text-generation/text-generation-models) to leverage our best and newest models.

      '
    sections:
    - type: endpoint
      key: createCompletion
      path: create
    - type: object
      key: CreateCompletionResponse
      path: object