Portkey Embeddings API

openapi: 3.0.0
info:
  title: Portkey Analytics > Graphs Embeddings 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: Embeddings
  description: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
paths:
  /embeddings:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_GATEWAY_URL
      description: Self-Hosted Gateway URL
    post:
      operationId: createEmbedding
      tags:
      - Embeddings
      summary: Embeddings
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateEmbeddingRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateEmbeddingResponse'
      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
        label: Default
        source: "curl https://api.portkey.ai/v1/embeddings \\\n  -H \"x-portkey-api-key: $PORTKEY_API_KEY\" \\\n  -H \"x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"input\": \"The food was delicious and the waiter...\",\n    \"model\": \"text-embedding-ada-002\",\n    \"encoding_format\": \"float\"\n  }'\n"
      - lang: python
        label: Default
        source: "from portkey_ai import Portkey\n\nclient = Portkey(\n  api_key = \"PORTKEY_API_KEY\",\n  virtual_key = \"PROVIDER_VIRTUAL_KEY\"\n)\n\nclient.embeddings.create(\n  model=\"text-embedding-ada-002\",\n  input=\"The food was delicious and the waiter...\",\n  encoding_format=\"float\"\n)\n"
      - lang: javascript
        label: Default
        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 embedding = await client.embeddings.create({\n    model: \"text-embedding-ada-002\",\n    input: \"The quick brown fox jumped over the lazy dog\",\n    encoding_format: \"float\",\n  });\n\n  console.log(embedding);\n}\n\nmain();\n"
      - lang: curl
        label: Self-Hosted
        source: "curl -X POST \"SELF_HOSTED_GATEWAY_URL/embeddings\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"x-portkey-api-key: $PORTKEY_API_KEY\" \\\n  -H \"x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY\" \\\n  -d '{\n    \"input\": \"The food was delicious and the waiter...\",\n    \"model\": \"text-embedding-ada-002\",\n    \"encoding_format\": \"float\"\n  }'\n"
      - lang: python
        label: Self-Hosted
        source: "from portkey_ai import Portkey\n\nclient = Portkey(\n    api_key=\"PORTKEY_API_KEY\",\n    virtual_key=\"PROVIDER_VIRTUAL_KEY\",\n    base_url=\"SELF_HOSTED_GATEWAY_URL\"\n)\n\nresponse = client.embeddings.create(\n    model=\"text-embedding-ada-002\",\n    input=\"The food was delicious and the waiter...\",\n    encoding_format=\"float\"\n)\n\nprint(response.data)\n"
      - lang: javascript
        label: Self-Hosted
        source: "import fs from \"fs\";\nimport Portkey from 'portkey-ai';\n\nconst portkey = new Portkey({\n  apiKey: 'PORTKEY_API_KEY',\n  virtualKey: 'PROVIDER_VIRTUAL_KEY',\n  baseURL: 'SELF_HOSTED_GATEWAY_URL'\n});\n\nasync function main() {\n  const embedding = await portkey.embeddings.create({\n    model: \"text-embedding-ada-002\",\n    input: \"The quick brown fox jumped over the lazy dog\",\n    encoding_format: \"float\",\n  });\n\n  console.log(embedding);\n}\n\nmain();\n"
components:
  schemas:
    CreateEmbeddingRequest:
      type: object
      additionalProperties: false
      properties:
        input:
          description: 'Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.

            '
          example: The quick brown fox jumped over the lazy dog
          oneOf:
          - type: string
            title: string
            description: The string that will be turned into an embedding.
            default: ''
            example: This is a test.
          - type: array
            title: array
            description: The array of strings that will be turned into an embedding.
            minItems: 1
            maxItems: 2048
            items:
              type: string
              default: ''
              example: '[''This is a test.'']'
          - type: array
            title: array
            description: The array of integers that will be turned into an embedding.
            minItems: 1
            maxItems: 2048
            items:
              type: integer
            example: '[1212, 318, 257, 1332, 13]'
          - type: array
            title: array
            description: The array of arrays containing integers that will be turned into an embedding.
            minItems: 1
            maxItems: 2048
            items:
              type: array
              minItems: 1
              items:
                type: integer
            example: '[[1212, 318, 257, 1332, 13]]'
          x-oaiExpandable: true
        model:
          description: 'ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models/overview) for descriptions of them.

            '
          example: text-embedding-3-small
          anyOf:
          - type: string
          - type: string
            enum:
            - text-embedding-ada-002
            - text-embedding-3-small
            - text-embedding-3-large
          x-oaiTypeLabel: string
        encoding_format:
          description: The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/).
          example: float
          default: float
          type: string
          enum:
          - float
          - base64
        dimensions:
          description: 'The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models.

            '
          type: integer
          minimum: 1
        user:
          type: string
          example: user-1234
          description: 'A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).

            '
      required:
      - model
      - input
    CreateEmbeddingResponse:
      type: object
      properties:
        data:
          type: array
          description: The list of embeddings generated by the model.
          items:
            $ref: '#/components/schemas/Embedding'
        model:
          type: string
          description: The name of the model used to generate the embedding.
        object:
          type: string
          description: The object type, which is always "list".
          enum:
          - list
        usage:
          type: object
          description: The usage information for the request.
          properties:
            prompt_tokens:
              type: integer
              description: The number of tokens used by the prompt.
            total_tokens:
              type: integer
              description: The total number of tokens used by the request.
          required:
          - prompt_tokens
          - total_tokens
      required:
      - object
      - model
      - data
      - usage
    Embedding:
      type: object
      description: 'Represents an embedding vector returned by embedding endpoint.

        '
      properties:
        index:
          type: integer
          description: The index of the embedding in the list of embeddings.
        embedding:
          type: array
          description: 'The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](https://platform.openai.com/docs/guides/embeddings).

            '
          items:
            type: number
        object:
          type: string
          description: The object type, which is always "embedding".
          enum:
          - embedding
      required:
      - index
      - object
      - embedding
      x-code-samples:
        name: The embedding object
        example: "{\n  \"object\": \"embedding\",\n  \"embedding\": [\n    0.0023064255,\n    -0.009327292,\n    .... (1536 floats total for ada-002)\n    -0.0028842222,\n  ],\n  \"index\": 0\n}\n"
  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