Need help with your APIs? I offer API discovery, governance & evangelism services. Explore services →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

TensorFlow Inference API

Model inference operations including classify, regress, and predict

TensorFlow Inference API is one of 7 APIs that TensorFlow publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Inference. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.

This API exposes 6 operations across 6 paths, and defines 7 schemas. It is described by OpenAPI 3.0.3, at version 2.0.

Requests are made against a single base URL, http://{host}:{port}.

6 operations 6 paths 7 schemas 6 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.0.3
API Version
2.0
Base URL
http://host:8501
License
Resource Areas
1

Paths & Operations 6

Across 6 paths, the API surfaces 6 operations — 6 POST. Each is listed below with its method, path, parameters, and response codes.

Inference 6

Model inference operations including classify, regress, and predict

POST
/v1/models/{model_name}:classify
Classify With Model
classifyModel 1 param body → 200400
POST
/v1/models/{model_name}/versions/{version}:classify
Classify With Model Version
classifyModelVersion 2 params body → 200400
POST
/v1/models/{model_name}:regress
Regress With Model
regressModel 1 param body → 200400
POST
/v1/models/{model_name}/versions/{version}:regress
Regress With Model Version
regressModelVersion 2 params body → 200400
POST
/v1/models/{model_name}:predict
Predict With Model
predictModel 1 param body → 200400
POST
/v1/models/{model_name}/versions/{version}:predict
Predict With Model Version
predictModelVersion 2 params body → 200400

Schemas 7

The contract defines 7 schemas that model the data the API accepts and returns. The most detailed are RegressRequest (3 properties), ClassifyRequest (3 properties), PredictRequest (3 properties), PredictResponse (2 properties). Each schema is shown below with its type and property counts.

PredictRequest
object
Request body for prediction inference. Supports row format (instances) or column format (inputs).
3 properties
RegressResponse
object
Response from regression inference
1 property
ErrorResponse
object
Error response returned when a request fails
1 property
ClassifyRequest
object
Request body for classification inference
3 properties
ClassifyResponse
object
Response from classification inference
1 property
RegressRequest
object
Request body for regression inference
3 properties
PredictResponse
object
Response from prediction inference. Returns predictions in row format or outputs in column format depending on the request.
2 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

tensorflow-inference-api-openapi.yml Raw ↑

Other APIs TensorFlow publishes across the network.

TensorFlow Core API
TensorFlow.js API
TensorFlow Lite API
TensorFlow Hub API
TensorBoard API
TensorFlow Models API