TensorFlow

TensorFlow is an end-to-end open source machine learning platform developed by Google. It provides a comprehensive ecosystem of tools, libraries, and community resources for building and deploying ML-powered applications, including model training, serving, mobile/edge deployment, and a hub of pre-trained models. TensorFlow Serving exposes REST and gRPC APIs for production model inference.

6 APIs 0 Features

AIDeep LearningJavaScriptMachine LearningModel ServingNeural NetworksOpen SourcePython

APIs

TensorFlow Serving REST API

A flexible, high-performance serving system for machine learning models designed for production environments. Provides REST endpoints for model status, metadata, classification,...

TensorFlow Core API

The foundational Python and C++ API for building and training machine learning models using TensorFlow.

TensorFlow.js API

A JavaScript library for training and deploying ML models in the browser and on Node.js.

TensorFlow Lite API

Lightweight solution for ML inference on mobile and embedded devices, optimized for on-device model execution.

TensorFlow Hub API

A library and repository of reusable pre-trained machine learning modules, enabling transfer learning across text, image, video, and audio domains.

TensorBoard API

TensorFlow's visualization toolkit for experiment tracking, model debugging, and performance profiling via an embedded web server with REST endpoints.

Collections

TensorFlow Serving REST API

OPEN

Pricing Plans

Tensorflow Plans Pricing

1 plans

PLANS

Rate Limits

Tensorflow Rate Limits

1 limits

RATE LIMITS

FinOps

Tensorflow Finops

FINOPS

Semantic Vocabularies

Tensorflow Context

4 classes · 15 properties

JSON-LD

API Governance Rules

TensorFlow API Rules

13 rules · 5 errors 7 warnings

SPECTRAL

JSON Structure

Tensorflow Serving Prediction Request Structure

0 properties

JSON STRUCTURE

Example Payloads

Tensorflow Serving Model Status Example

4 fields

EXAMPLE

Tensorflow Serving Predict Example

4 fields

EXAMPLE

Resources

Sources

opencollection: 1.0.0
info:
  name: TensorFlow Serving REST API
  version: '2.0'
items:
- info:
    name: Models
    type: folder
  items:
  - info:
      name: Get Model Status
      type: http
    http:
      method: GET
      url: http://{host}:{port}/v1/models/:model_name
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
    docs: Returns the status of a model in the ModelServer, including the state and any error status for each version of the
      model.
  - info:
      name: Get Model Version Status
      type: http
    http:
      method: GET
      url: http://{host}:{port}/v1/models/:model_name/versions/:version
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      - name: version
        value: ''
        type: path
        description: The specific version number of the model
    docs: Returns the status of a specific version of a model in the ModelServer.
  - info:
      name: Get Model Label Status
      type: http
    http:
      method: GET
      url: http://{host}:{port}/v1/models/:model_name/labels/:label
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      - name: label
        value: ''
        type: path
        description: The label identifying a specific model version
    docs: Returns the status of a model version identified by label in the ModelServer.
  - info:
      name: Get Model Metadata
      type: http
    http:
      method: GET
      url: http://{host}:{port}/v1/models/:model_name/metadata
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
    docs: Returns the metadata of a model in the ModelServer. If no version is specified, returns metadata for the latest
      available version.
  - info:
      name: Get Model Version Metadata
      type: http
    http:
      method: GET
      url: http://{host}:{port}/v1/models/:model_name/versions/:version/metadata
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      - name: version
        value: ''
        type: path
        description: The specific version number of the model
    docs: Returns the metadata for a specific version of a model in the ModelServer.
- info:
    name: Inference
    type: folder
  items:
  - info:
      name: Classify With Model
      type: http
    http:
      method: POST
      url: http://{host}:{port}/v1/models/:model_name:classify
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      body:
        type: json
        data: '{}'
    docs: Runs classification inference using the specified model. The request follows the PredictionService.Classify gRPC
      API semantics. Returns classification labels and scores.
  - info:
      name: Classify With Model Version
      type: http
    http:
      method: POST
      url: http://{host}:{port}/v1/models/:model_name/versions/:version:classify
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      - name: version
        value: ''
        type: path
        description: The specific version number of the model
      body:
        type: json
        data: '{}'
    docs: Runs classification inference using a specific version of the model.
  - info:
      name: Regress With Model
      type: http
    http:
      method: POST
      url: http://{host}:{port}/v1/models/:model_name:regress
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      body:
        type: json
        data: '{}'
    docs: Runs regression inference using the specified model. The request follows the PredictionService.Regress gRPC API
      semantics. Returns regression values for each input example.
  - info:
      name: Regress With Model Version
      type: http
    http:
      method: POST
      url: http://{host}:{port}/v1/models/:model_name/versions/:version:regress
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      - name: version
        value: ''
        type: path
        description: The specific version number of the model
      body:
        type: json
        data: '{}'
    docs: Runs regression inference using a specific version of the model.
  - info:
      name: Predict With Model
      type: http
    http:
      method: POST
      url: http://{host}:{port}/v1/models/:model_name:predict
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      body:
        type: json
        data: '{}'
    docs: Runs prediction inference using the specified model. Supports both row format (instances array) and column format
      (inputs object). Returns predictions in the corresponding format.
  - info:
      name: Predict With Model Version
      type: http
    http:
      method: POST
      url: http://{host}:{port}/v1/models/:model_name/versions/:version:predict
      params:
      - name: model_name
        value: ''
        type: path
        description: The name of the model
      - name: version
        value: ''
        type: path
        description: The specific version number of the model
      body:
        type: json
        data: '{}'
    docs: Runs prediction inference using a specific version of the model.
bundled: true