openapi: 3.0.0
info:
  title: Portkey Analytics > Graphs 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: Analytics > Graphs
  description: Get data points for graphical representation.
paths:
  /analytics/graphs/requests:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get requests graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total requests across all data points
                    required:
                    - total
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        total:
                          type: integer
                          description: Total requests for this data point bucket
                      required:
                      - timestamp
                      - total
                      description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/cost:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get cost graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total cost in cents across all data points
                      avg:
                        type: integer
                        description: Average cost per request across all data points
                    required:
                    - total
                    - avg
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        total:
                          type: integer
                          description: Total cost in cents for this data point bucket
                        avg:
                          type: integer
                          description: Average cost per request for this data point bucket
                      required:
                      - timestamp
                      - total
                      - avg
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/latency:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get latency graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      avg:
                        type: integer
                        description: Average latency in ms across all data points
                      p50:
                        type: integer
                        description: 50th percentile latency in ms across all data points
                      p90:
                        type: integer
                        description: 90th percentile latency in ms across all data points
                      p99:
                        type: integer
                        description: 99th percentile latency in ms across all data points
                    required:
                    - avg
                    - p50
                    - p90
                    - p99
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        avg:
                          type: integer
                          description: Average latency in ms for this data point bucket
                        p50:
                          type: integer
                          description: 50th percentile latency in ms for this data point bucket
                        p90:
                          type: integer
                          description: 90th percentile latency in ms for this data point bucket
                        p99:
                          type: integer
                          description: 99th percentile latency in ms for this data point bucket
                      required:
                      - timestamp
                      - avg
                      - p50
                      - p90
                      - p99
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/tokens:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get tokens graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total tokens across all data points
                      avg:
                        type: integer
                        description: Average tokens per request across all data points
                    required:
                    - total
                    - avg
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        total:
                          type: integer
                          description: Total tokens for this data point bucket
                        avg:
                          type: integer
                          description: Average tokens per request for this data point bucket
                      required:
                      - timestamp
                      - avg
                      - total
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/users:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get users graph. Returns unique user count across different time buckets
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total unique users across all data points
                    required:
                    - total
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        total:
                          type: integer
                          description: Total unique users for this data point bucket
                      required:
                      - timestamp
                      - total
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/users/requests:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get users requests graph. Returns average requests per user across different time buckets
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total requests across all data points
                      unique:
                        type: integer
                        description: Total unique users across all data points
                      avg:
                        type: integer
                        description: Average requests per user across all data points
                    required:
                    - total
                    - unique
                    - avg
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        avg:
                          type: integer
                          description: Average requests per user for this data point bucket
                      required:
                      - timestamp
                      - avg
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/errors:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get errors graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total errors across all data points
                    required:
                    - total
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        total:
                          type: integer
                          description: Total errors this data point bucket
                      required:
                      - timestamp
                      - total
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/errors/rate:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get percentage error rate graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      rate:
                        type: integer
                        description: Percentage error rate across all data points
                    required:
                    - rate
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        rate:
                          type: integer
                          description: Percentage error rate for this data point bucket
                      required:
                      - timestamp
                      - rate
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/errors/stacks:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get status code wise stacked error graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total errors across all data points
                    required:
                    - total
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        stats:
                          type: array
                          items:
                            type: object
                            properties:
                              response_status_code:
                                type: integer
                                description: Response status code
                              count:
                                type: integer
                                description: Total occurences of this response status code
                      required:
                      - timestamp
                      - stats
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/errors/status-codes:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get status code wise grouped error graph.
      parameters:
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total_errors:
                        type: integer
                        description: Total errors across all data points
                      unique_error_codes:
                        type: integer
                        description: Unique error codes across all data points
                    required:
                    - total_errors
                    - unique_error_codes
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        status_code:
                          type: integer
                          description: Response status code
                        count:
                          type: integer
                          description: Occurences of this response status code
                      required:
                      - status_code
                      - count
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/requests/rescued:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get retry and fallback rescued requests graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      retry:
                        type: integer
                        description: Total requests rescued using retries across all data points
                      fallback:
                        type: integer
                        description: Total requests rescued using fallback across all data points
                    required:
                    - retry
                    - fallback
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        retry:
                          type: array
                          items:
                            type: object
                            properties:
                              retry_success_count:
                                type: integer
                                description: Retry attempt count at which the request was rescued
                              count:
                                type: integer
                                description: Total requests rescued at this retry attempt
                        fallback:
                          type: integer
                          description: Total requests rescued using fallback for this data point bucket
                      required:
                      - timestamp
                      - retry
                      - fallback
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/cache/hit-rate:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get cache hit rate graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total cache hits across all data points
                      rate:
                        type: integer
                        description: Percentage cache hit rate across all data points
                    required:
                    - total
                    - rate
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        simple_hits:
                          type: integer
                          description: Total simple cache hits for this data point bucket
                        semantic_hits:
                          type: integer
                          description: Total semantic cache hits for this data point bucket
                        rate:
                          type: integer
                          description: Percentage cache hit rate for this data point bucket
                        cumulative_simple_cache_savings:
                          type: integer
                          description: Cumulative simple cache cost savings in cents based on all previous data point buckets and this bucket
                        cumulative_semantic_cache_savings:
                          type: integer
                          description: Cumulative semantic cache cost savings in cents based on all previous data point buckets and this bucket
                      required:
                      - timestamp
                      - simple_hits
                      - semantic_hits
                      - rate
                      - cumulative_simple_cache_savings
                      - cumulative_semantic_cache_savings
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/cache/latency:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get cache hit latency graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        avg:
                          type: integer
                          description: Average latency (in ms) for cache hit for this data point bucket
                      required:
                      - timestamp
                      - avg
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/feedbacks:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get feedbacks graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total feedbacks across all data points
                    required:
                    - total
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        total:
                          type: integer
                          description: Total feedbacks for this data point bucket
                      required:
                      - timestamp
                      - total
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/feedbacks/scores:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get score-wise feedbacks distribution graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      total:
                        type: integer
                        description: Total feedbacks across all data points
                    required:
                    - total
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        score:
                          type: integer
                          description: Feedback value for which total is calculated
                        total:
                          type: integer
                          description: Total feedbacks for this feedback score
                      required:
                      - score
                      - total
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/feedbacks/weighted:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get weighted feedbacks graph. Weighted feedback is (value * score)
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                    properties:
                      avg:
                        type: integer
                        description: Average weighted feedback across all data points
                    required:
                    - avg
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        timestamp:
                          type: string
                          format: date-time
                          description: The timestamp for the data point bucket
                        avg:
                          type: integer
                          description: Average weighted feedback for this data point bucket
                      required:
                      - timestamp
                      - avg
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
  /analytics/graphs/feedbacks/ai-models:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_CONTROL_PLANE_URL
      description: Self-Hosted Control Plane URL
    get:
      tags:
      - Analytics > Graphs
      summary: Get feedbacks per ai_models graph
      parameters:
      - $ref: '#/components/parameters/WorkspaceSlug'
      - $ref: '#/components/parameters/TimeOfGenerationMin'
      - $ref: '#/components/parameters/TimeOfGenerationMax'
      - $ref: '#/components/parameters/TotalUnitsMin'
      - $ref: '#/components/parameters/TotalUnitsMax'
      - $ref: '#/components/parameters/CostMin'
      - $ref: '#/components/parameters/CostMax'
      - $ref: '#/components/parameters/PromptTokenMin'
      - $ref: '#/components/parameters/PromptTokenMax'
      - $ref: '#/components/parameters/CompletionTokenMin'
      - $ref: '#/components/parameters/CompletionTokenMax'
      - $ref: '#/components/parameters/StatusCode'
      - $ref: '#/components/parameters/WeightedFeedbackMin'
      - $ref: '#/components/parameters/WeightedFeedbackMax'
      - $ref: '#/components/parameters/VirtualKeys'
      - $ref: '#/components/parameters/Configs'
      - $ref: '#/components/parameters/ApiKeyIds'
      - $ref: '#/components/parameters/Metadata'
      - $ref: '#/components/parameters/AiOrgModel'
      - $ref: '#/components/parameters/TraceId'
      - $ref: '#/components/parameters/SpanId'
      - $ref: '#/components/parameters/PromptSlug'
      responses:
        '200':
          description: OK
          headers:
            Content-Type:
              schema:
                type: string
                example: application/json
          content:
            application/json:
              schema:
                type: object
                properties:
                  summary:
                    type: object
                  data_points:
                    type: array
                    items:
                      type: object
                      properties:
                        ai_model:
                          type: string
                          description: AI model for which feedback data is calculated
                        total:
                          type: integer
                          description: Total feedbacks for this ai_model requests
                        avg_weighted_feedback:
                          type: integer
                          description: Average weighted feedback for this ai_model requests
                      required:
                      - ai_model
                      - total
                      - avg_weighted_feedback
                    description: An array of data points, each with a timestamp and metrics
                  object:
                    type: string
                    description: The type of object being returned
                    enum:
                    - analytics-graph
                required:
                - summary
                - data_points
                - object
components:
  parameters:
    PromptTokenMin:
      in: query
      name: prompt_token_min
      schema:
        type: integer
        minimum: 0
      description: Minimum number of prompt tokens
    WeightedFeedbackMax:
      in: query
      name: weighted_feedback_max
      schema:
        type: number
        minimum: -10
        maximum: 10
      description: Maximum weighted feedback score
    TotalUnitsMax:
      in: query
      name: total_units_max
      schema:
        type: integer
        minimum: 0
      description: Maximum total units (tokens)
    Metadata:
      in: query
      name: metadata
      schema:
        type: string
      description: Stringifed json object with key value metadata pairs
      example: '{"_user":"user_1", "env": "staging"}'
    VirtualKeys:
      in: query
      name: virtual_keys
      schema:
        type: string
      description: Comma separated virtual key slugs
      example: vk-slug-1,vk-slug-2
    WeightedFeedbackMin:
      in: query
      name: weighted_feedback_min
      schema:
        type: number
        minimum: -10
        maximum: 10
      description: Minimum weighted feedback score
    TimeOfGenerationMax:
      in: query
      name: time_of_generation_max
      required: true
      schema:
        type: string
        format: date-time
        example: '2026-02-24T14:20:31+05:30'
      description: Maximum time of generation in ISO8601 format (YYYY-MM-DDTHH:MM:SS±HH:MM).
    CompletionTokenMax:
      in: query
      name: completion_token_max
      schema:
        type: integer
        minimum: 0
      description: Maximum number of completion tokens
    ApiKeyIds:
      in: query
      name: api_key_ids
      schema:
        type: string
      description: Comma separated API key UUIDs
      example: 765768a9-b4ec-4694-962c-d55f40cdb0dc,7c22af5a-8119-46b8-8d9b-bad3ad382387
    StatusCode:
      in: query
      name: status_code
      schema:
        type: string
      description: Comma separated response status codes
      example: 401,403
    Configs:
      in: query
      name: configs
      schema:
        type: string
      description: Comma separated config slugs
      example: pc-config-slug-1,pc-config-slug-2
    TraceId:
      in: query
      name: trace_id
      schema:
        type: string
      description: Comma separated trace IDs
      example: my-unique-trace-1,my-unique-trace-2
    CompletionTokenMin:
      in: query
      name: completion_token_min
      schema:
        type: integer
        minimum: 0
      description: Minimum number of completion tokens
    PromptSlug:
      in: query
      name: prompt_slug
      schema:
        type: string
      description: Comma separated prompt slugs
      example: prompt-slug-1,prompt-slug-2
    TotalUnitsMin:
      in: query
      name: total_units_min
      schema:
        type: integer
        minimum: 0
      description: Minimum total units (tokens)
    SpanId:
      in: query
      name: span_id
      schema:
        type: string
      description: Comma separated span IDs
      example: my-unique-span-1,my-unique-span-2
    WorkspaceSlug:
      in: query
      name: workspace_slug
      required: true
      schema:
        type: string
      description: Workspace slug filter. If a workspace API key is being used, this filter will not be taken into consideration. If an organisation API key is used and no workspace slug is passed, default workspace will be used.
    TimeOfGenerationMin:
      in: query
      name: time_of_generation_min
      required: true
      schema:
        type: string
        format: date-time
        example: '2026-02-23T14:20:31+05:30'
      description: Minimum time of generation in ISO8601 format (YYYY-MM-DDTHH:MM:SS±HH:MM).
    AiOrgModel:
      in: query
      name: ai_org_model
      schema:
        type: string
      description: Comma separated ai provider and model combination. Double underscore (__) should be used as a separator for each provider and model combination
      example: openai__gpt-3.5-turbo,azure-openai__gpt-35-turbo
    CostMax:
      in: query
      name: cost_max
      schema:
        type: number
        minimum: 0
      description: Maximum cost (in cents)
    CostMin:
      in: query
      name: cost_min
      schema:
        type: number
        minimum: 0
      description: Minimum cost (in cents)
    PromptTokenMax:
      in: query
      name: prompt_token_max
      schema:
        type: integer
        minimum: 0
      description: Maximum number of prompt tokens
  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