Portkey Rerank API

Rerank a list of documents based on their relevance to a query. Supported providers include Cohere, Voyage, Jina, Pinecone, Bedrock, and Azure AI.

OpenAPI Specification

portkey-rerank-api-openapi.yml Raw ↑
openapi: 3.0.0
info:
  title: Portkey Analytics > Graphs Rerank 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: Rerank
  description: Rerank a list of documents based on their relevance to a query. Supported providers include Cohere, Voyage, Jina, Pinecone, Bedrock, and Azure AI.
paths:
  /rerank:
    servers:
    - url: https://api.portkey.ai/v1
      description: Portkey API Public Endpoint
    - url: SELF_HOSTED_GATEWAY_URL
      description: Self-Hosted Gateway URL
    post:
      operationId: createRerank
      tags:
      - Rerank
      summary: Rerank
      description: 'Reranks a list of documents based on their relevance to a query. This endpoint provides a unified interface to reranking models from multiple providers including Cohere, Voyage, Jina, Pinecone, Bedrock, and Azure AI.


        Reranking is useful for improving search results by scoring and sorting documents based on semantic relevance to a query, rather than just keyword matching.

        '
      parameters:
      - $ref: '#/components/parameters/PortkeyTraceId'
      - $ref: '#/components/parameters/PortkeySpanId'
      - $ref: '#/components/parameters/PortkeyParentSpanId'
      - $ref: '#/components/parameters/PortkeySpanName'
      - $ref: '#/components/parameters/PortkeyMetadata'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateRerankRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateRerankResponse'
      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/rerank \\\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    \"model\": \"rerank-v3.5\",\n    \"query\": \"What is the capital of France?\",\n    \"documents\": [\n      \"Paris is the capital of France.\",\n      \"Berlin is the capital of Germany.\",\n      \"Madrid is the capital of Spain.\"\n    ],\n    \"top_n\": 2\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\nresponse = client.post(\n  \"/rerank\",\n  model=\"rerank-v3.5\",\n  query=\"What is the capital of France?\",\n  documents=[\n    \"Paris is the capital of France.\",\n    \"Berlin is the capital of Germany.\",\n    \"Madrid is the capital of Spain.\",\n  ],\n  top_n=2,\n)\n\nprint(response)\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 response = await client.post('/rerank', {\n    model: 'rerank-v3.5',\n    query: 'What is the capital of France?',\n    documents: [\n      'Paris is the capital of France.',\n      'Berlin is the capital of Germany.',\n      'Madrid is the capital of Spain.'\n    ],\n    top_n: 2\n  });\n\n  console.log(response);\n}\n\nmain();\n"
      - lang: curl
        label: Self-Hosted
        source: "curl -X POST \"SELF_HOSTED_GATEWAY_URL/rerank\" \\\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    \"model\": \"rerank-v3.5\",\n    \"query\": \"What is the capital of France?\",\n    \"documents\": [\n      \"Paris is the capital of France.\",\n      \"Berlin is the capital of Germany.\",\n      \"Madrid is the capital of Spain.\"\n    ],\n    \"top_n\": 2\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.post(\n  \"/rerank\",\n  model=\"rerank-v3.5\",\n  query=\"What is the capital of France?\",\n  documents=[\n    \"Paris is the capital of France.\",\n    \"Berlin is the capital of Germany.\",\n    \"Madrid is the capital of Spain.\",\n  ],\n  top_n=2,\n)\n\nprint(response)\n"
      - lang: javascript
        label: Self-Hosted
        source: "import Portkey from 'portkey-ai';\n\nconst client = 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 response = await client.post('/rerank', {\n    model: 'rerank-v3.5',\n    query: 'What is the capital of France?',\n    documents: [\n      'Paris is the capital of France.',\n      'Berlin is the capital of Germany.',\n      'Madrid is the capital of Spain.'\n    ],\n    top_n: 2\n  });\n\n  console.log(response);\n}\n\nmain();\n"
components:
  parameters:
    PortkeyTraceId:
      in: header
      name: x-portkey-trace-id
      schema:
        type: string
      description: An ID you can pass to refer to one or more requests later on. If not provided, Portkey generates a trace ID automatically for each request. [Docs](https://portkey.ai/docs/product/observability/traces)
      required: false
    PortkeySpanName:
      in: header
      name: x-portkey-span-name
      schema:
        type: string
      description: Name for the Span ID
      required: false
    PortkeyMetadata:
      in: header
      name: x-portkey-metadata
      schema:
        type: object
      description: Pass any arbitrary metadata along with your request
      required: false
    PortkeySpanId:
      in: header
      name: x-portkey-span-id
      schema:
        type: string
      description: An ID you can pass to refer to a span under a trace.
      required: false
    PortkeyParentSpanId:
      in: header
      name: x-portkey-parent-span-id
      schema:
        type: string
      description: Link a child span to a parent span
      required: false
  schemas:
    RerankResult:
      type: object
      description: A single reranked document result.
      properties:
        index:
          type: integer
          description: The index of the document in the original input array.
          example: 0
        relevance_score:
          type: number
          format: float
          description: 'The relevance score of the document to the query. Higher scores indicate greater relevance.

            Score ranges vary by provider but are typically between 0 and 1.

            '
          example: 0.98
        document:
          type: object
          description: The original document text. Only present if `return_documents` is true.
          properties:
            text:
              type: string
              description: The text content of the document.
          additionalProperties: true
      required:
      - index
      - relevance_score
    RerankUsage:
      type: object
      description: Usage information for the rerank request.
      properties:
        search_units:
          type: integer
          description: 'The number of search units consumed by the request. Billing varies by provider.

            '
    CreateRerankRequest:
      type: object
      description: 'Request body for reranking documents. The unified API supports multiple providers including Cohere, Voyage, Jina, Pinecone, Bedrock, and Azure AI.

        '
      properties:
        model:
          description: 'ID of the model to use for reranking. Model availability depends on the provider:

            - **Cohere**: `rerank-v3.5`, `rerank-english-v3.0`, `rerank-multilingual-v3.0`, `rerank-english-v2.0`, `rerank-multilingual-v2.0`

            - **Voyage**: `rerank-2`, `rerank-2-lite`

            - **Jina**: `jina-reranker-v2-base-multilingual`, `jina-reranker-v1-base-en`, `jina-reranker-v1-turbo-en`, `jina-reranker-v1-tiny-en`

            - **Pinecone**: `bge-reranker-v2-m3`, `pinecone-rerank-v0`

            - **Bedrock**: Model ARN (e.g., `arn:aws:bedrock:us-west-2::foundation-model/cohere.rerank-v3-5:0`)

            - **Azure AI**: Cohere rerank deployments on Azure AI Inference; use the model name from your deployment, typically prefixed with `cohere.` (the gateway strips that prefix for the upstream request)

            '
          type: string
          example: rerank-v3.5
        query:
          description: The search query to compare against the documents.
          type: string
          example: What is the capital of France?
        documents:
          description: 'The list of documents to rerank. Each document can be a string or an object with a `text` field.

            The documents will be scored based on their relevance to the query.

            '
          type: array
          items:
            $ref: '#/components/schemas/RerankDocument'
          minItems: 1
          example:
          - Paris is the capital of France.
          - Berlin is the capital of Germany.
          - Madrid is the capital of Spain.
        top_n:
          description: 'The number of top results to return. If not specified, all documents are returned sorted by relevance.

            For Voyage, the gateway maps this field to the provider''s `top_k` parameter.

            '
          type: integer
          minimum: 1
          example: 3
        return_documents:
          description: 'Whether to return the document text in the response. Supported by Voyage, Jina, and Pinecone.

            '
          type: boolean
          default: false
        max_tokens_per_doc:
          description: 'Maximum number of tokens per document. Documents exceeding this limit will be truncated. Cohere-specific parameter.

            '
          type: integer
          minimum: 1
        priority:
          description: 'Request priority hint. Cohere-specific parameter.

            '
          type: number
        rank_fields:
          description: 'The fields to use for ranking when documents are objects with multiple fields. Pinecone-specific parameter.

            '
          type: array
          items:
            type: string
          example:
          - text
          - title
        truncation:
          description: 'Whether to truncate documents that exceed the model''s maximum context length. Voyage-specific parameter.

            '
          type: boolean
        parameters:
          description: 'Additional provider-specific parameters. Pinecone-specific parameter.

            '
          type: object
          additionalProperties: true
      required:
      - model
      - query
      - documents
    CreateRerankResponse:
      type: object
      description: Response from the rerank endpoint.
      properties:
        id:
          type: string
          description: A unique identifier for the rerank request.
          example: rerank-abc123
        object:
          type: string
          description: The object type, which is always "list".
          enum:
          - list
          example: list
        results:
          type: array
          description: 'The reranked results sorted by relevance score in descending order.

            '
          items:
            $ref: '#/components/schemas/RerankResult'
        model:
          type: string
          description: The model used for reranking.
          example: rerank-v3.5
        usage:
          $ref: '#/components/schemas/RerankUsage'
        provider:
          type: string
          description: The provider that processed the request.
          example: cohere
      required:
      - object
      - results
      - model
    RerankDocument:
      description: 'A document to be reranked. Can be a simple string or an object with a text field and optional metadata.

        '
      oneOf:
      - type: string
        title: string
        description: A simple text string to be reranked.
        example: Paris is the capital of France.
      - type: object
        title: object
        description: An object containing the document text and optional metadata.
        properties:
          text:
            type: string
            description: The text content of the document.
            example: Paris is the capital of France.
        required:
        - text
        additionalProperties: true
  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