Openlayer Data Stream API

Publish production inference data to a pipeline.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/openlayer-data-stream-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openlayer-data-stream-api-openapi.yml Raw ↑
openapi: 3.0.1
info:
  title: Openlayer Commits Data Stream API
  description: The Openlayer REST API for AI evaluation, testing, and observability. Manage projects, commit model versions and datasets, run and evaluate tests, create inference pipelines for production monitoring, and stream production inference data into Openlayer. All requests are authenticated with a Bearer API key.
  termsOfService: https://www.openlayer.com/terms
  contact:
    name: Openlayer Support
    url: https://www.openlayer.com/docs
    email: support@openlayer.com
  version: '1.0'
servers:
- url: https://api.openlayer.com/v1
  description: Openlayer production API
security:
- api_key: []
tags:
- name: Data Stream
  description: Publish production inference data to a pipeline.
paths:
  /inference-pipelines/{inferencePipelineId}/data-stream:
    post:
      operationId: streamData
      tags:
      - Data Stream
      summary: Stream production data
      description: Publish production inference data (rows) to an inference pipeline. The config object maps the columns in each row to Openlayer concepts such as input variables, output, ground truth, latency, cost, and token counts.
      parameters:
      - $ref: '#/components/parameters/InferencePipelineId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DataStreamRequest'
      responses:
        '200':
          description: Data accepted for ingestion.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DataStreamResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
components:
  responses:
    ValidationError:
      description: The request body failed validation.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Authentication failed or the API key is missing or invalid.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    DataStreamRequest:
      type: object
      properties:
        config:
          $ref: '#/components/schemas/DataStreamConfig'
        rows:
          type: array
          description: The rows of production data being published.
          items:
            type: object
            additionalProperties: true
      required:
      - config
      - rows
    DataStreamResponse:
      type: object
      properties:
        success:
          type: string
          description: Indicates the data was accepted (e.g. "success").
    DataStreamConfig:
      type: object
      description: Maps the columns present in each streamed row to Openlayer concepts. The exact fields depend on the project task type (LLM vs tabular).
      properties:
        inputVariableNames:
          type: array
          items:
            type: string
          description: Names of the columns that are input variables to the model.
        outputColumnName:
          type: string
          nullable: true
          description: Name of the column containing the model output.
        groundTruthColumnName:
          type: string
          nullable: true
          description: Name of the column containing ground truth labels.
        numOfTokenColumnName:
          type: string
          nullable: true
          description: Name of the column containing token counts.
        costColumnName:
          type: string
          nullable: true
          description: Name of the column containing the request cost.
        latencyColumnName:
          type: string
          nullable: true
          description: Name of the column containing latency in milliseconds.
        timestampColumnName:
          type: string
          nullable: true
          description: Name of the column containing the UNIX timestamp.
        inferenceIdColumnName:
          type: string
          nullable: true
          description: Name of the column containing a unique inference id for the row.
        contextColumnName:
          type: string
          nullable: true
          description: Name of the column containing retrieved context (for RAG/LLM tasks).
        questionColumnName:
          type: string
          nullable: true
        prompt:
          type: array
          nullable: true
          items:
            type: object
            properties:
              role:
                type: string
              content:
                type: string
    Error:
      type: object
      properties:
        code:
          type: string
        message:
          type: string
      required:
      - message
  parameters:
    InferencePipelineId:
      name: inferencePipelineId
      in: path
      required: true
      description: The unique identifier of the inference pipeline.
      schema:
        type: string
        format: uuid
  securitySchemes:
    api_key:
      type: http
      scheme: bearer
      bearerFormat: apiKey
      description: Pass your Openlayer API key as a Bearer token in the Authorization header.