Portkey Models API

openapi: 3.0.0
info:
  title: Portkey Analytics > Graphs Models 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: Models
  description: List and describe the various models available in the API.
paths:
  /models:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_GATEWAY_URL
      description: Self-Hosted Gateway URL
    get:
      operationId: listModels
      tags:
      - Models
      summary: List Available Models
      description: Lists the currently available models that can be used through Portkey, and provides basic information about each one.
      parameters:
      - in: query
        name: ai_service
        required: false
        description: Filter models by the AI service (e.g., 'openai', 'anthropic').
        schema:
          type: string
      - in: query
        name: provider
        required: false
        description: Filter models by the provider.
        schema:
          type: string
      - in: query
        name: limit
        required: false
        description: The maximum number of models to return.
        schema:
          type: integer
      - in: query
        name: offset
        required: false
        description: The number of models to skip before starting to collect the result set.
        schema:
          type: integer
      - in: query
        name: sort
        required: false
        description: The field to sort the results by.
        schema:
          type: string
          enum:
          - name
          - provider
          - ai_service
          default: name
      - in: query
        name: order
        required: false
        description: The order to sort the results in.
        schema:
          type: string
          enum:
          - asc
          - desc
          default: asc
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListModelsResponse'
              example:
                object: list
                total: 500
                data:
                - id: '@ai-provider-slug/gpt-5'
                  slug: gpt-5
                  canonical_slug: gpt-5
                  object: model
      security:
      - Portkey-Key: []
      x-code-samples:
      - lang: curl
        label: Default
        source: "# Example of sending a query parameter in the URL\ncurl 'https://api.portkey.ai/v1/models?provider=openai' \\\n  -H \"x-portkey-api-key: $PORTKEY_API_KEY\"\n"
      - lang: curl
        label: Self-Hosted
        source: "# Example of sending a query parameter in the URL\ncurl 'https://YOUR_SELF_HOSTED_URL/models?provider=openai' \\\n  -H \"x-portkey-api-key: $PORTKEY_API_KEY\"\n"
      - lang: python
        label: Default
        source: "from portkey_ai import Portkey\n\nclient = Portkey(\n  api_key = \"PORTKEY_API_KEY\"\n)\n\n# Example of sending query parameters via extra_query\nmodels = client.models.list(\n  extra_query={\"provider\": \"openai\"}\n)\nprint(models)\n"
      - lang: python
        label: Self-Hosted
        source: "from portkey_ai import Portkey\n\nclient = Portkey(\n  api_key = \"PORTKEY_API_KEY\",\n  base_url = \"https://YOUR_SELF_HOSTED_URL\"\n)\n\n# Example of sending query parameters via extra_query\nmodels = client.models.list(\n  extra_query={\"provider\": \"openai\"}\n)\nprint(models)\n"
      - lang: javascript
        label: Default
        source: "import Portkey from 'portkey-ai';\n\nconst client = new Portkey({\n  apiKey: 'PORTKEY_API_KEY'\n});\n\nasync function main() {\n  // Example of sending query parameters in the list method\n  const list = await client.models.list({\n    provider: \"openai\"\n  });\n  console.log(list);\n}\nmain();\n"
      - lang: javascript
        label: Self-Hosted
        source: "import Portkey from 'portkey-ai';\n\nconst client = new Portkey({\n  apiKey: 'PORTKEY_API_KEY',\n  baseUrl: 'https://YOUR_SELF_HOSTED_URL'\n});\n\nasync function main() {\n  // Example of sending query parameters in the list method\n  const list = await client.models.list({\n    provider: \"openai\"\n  });\n  console.log(list);\n}\nmain();     \n"
  /models/{model}:
    get:
      operationId: retrieveModel
      tags:
      - Models
      summary: Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
      parameters:
      - in: path
        name: model
        required: true
        schema:
          type: string
          example: gpt-3.5-turbo
        description: The ID of the model to use for this request
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Model'
      security:
      - Portkey-Key: []
        Virtual-Key: []
      - Portkey-Key: []
        Provider-Auth: []
        Provider-Name: []
      - Portkey-Key: []
        Config: []
      - Portkey-Key: []
        Provider-Auth: []
        Provider-Name: []
        Custom-Host: []
      x-code-samples:
      - lang: curl
        source: "curl https://api.portkey.ai/v1/models/VAR_model_id \\\n  -H \"x-portkey-api-key: $PORTKEY_API_KEY\" \\\n  -H \"x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY\" \\\n"
      - lang: python
        source: "from portkey_ai import Portkey\n\nclient = Portkey(\n  api_key = \"PORTKEY_API_KEY\",\n  virtual_key = \"PROVIDER_VIRTUAL_KEY\"\n)\n\nclient.models.retrieve(\"VAR_model_id\")\n"
      - lang: javascript
        source: "import Portkey from 'portkey-ai';\n\nconst client = new Portkey({\n  apiKey: 'PORTKEY_API_KEY',\n  virtualKey: 'PROVIDER_VIRTUAL_KEY'\n});\n\nasync function main() {\n  const model = await client.models.retrieve(\"VAR_model_id\");\n\n  console.log(model);\n}\n\nmain();\n"
    delete:
      operationId: deleteModel
      tags:
      - Models
      summary: Delete a fine-tuned model. You must have the Owner role in your organization to delete a model.
      parameters:
      - in: path
        name: model
        required: true
        schema:
          type: string
          example: ft:gpt-3.5-turbo:acemeco:suffix:abc123
        description: The model to delete
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeleteModelResponse'
      security:
      - Portkey-Key: []
        Virtual-Key: []
      - Portkey-Key: []
        Provider-Auth: []
        Provider-Name: []
      - Portkey-Key: []
        Config: []
      - Portkey-Key: []
        Provider-Auth: []
        Provider-Name: []
        Custom-Host: []
      x-code-samples:
      - lang: curl
        source: "curl https://api.portkey.ai/v1/models/ft:gpt-3.5-turbo:acemeco:suffix:abc123 \\\n  -X DELETE \\\n  -H \"x-portkey-api-key: $PORTKEY_API_KEY\" \\\n  -H \"x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY\"\n"
      - lang: python
        source: "from portkey_ai import Portkey\n\nclient = Portkey(\n  api_key = \"PORTKEY_API_KEY\",\n  virtual_key = \"PROVIDER_VIRTUAL_KEY\"\n)\n\nclient.models.delete(\"ft:gpt-3.5-turbo:acemeco:suffix:abc123\")\n"
      - lang: javascript
        source: "import Portkey from 'portkey-ai';\n\nconst client = new Portkey({\n  apiKey: 'PORTKEY_API_KEY',\n  virtualKey: 'PROVIDER_VIRTUAL_KEY'\n});\n\nasync function main() {\n  const model = await client.models.del(\"ft:gpt-3.5-turbo:acemeco:suffix:abc123\");\n\n  console.log(model);\n}\nmain();\n"
components:
  schemas:
    Model:
      title: Model
      description: Describes an OpenAI model offering that can be used with the API.
      properties:
        id:
          type: string
          description: The model identifier, which can be referenced in the API endpoints.
        created:
          type: integer
          description: The Unix timestamp (in seconds) when the model was created.
        object:
          type: string
          description: The object type, which is always "model".
          enum:
          - model
        owned_by:
          type: string
          description: The organization that owns the model.
      required:
      - id
      - object
      - created
      - owned_by
    DeleteModelResponse:
      type: object
      properties:
        id:
          type: string
        deleted:
          type: boolean
        object:
          type: string
      required:
      - id
      - object
      - deleted
    ListModelsResponse:
      type: object
      properties:
        object:
          type: string
          enum:
          - list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
      required:
      - object
      - data
  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