How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Hugging Face Endpoints API

Manage dedicated inference endpoints

Hugging Face Endpoints API is one of 21 APIs that Hugging Face publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

The published artifact set on APIs.io includes an OpenAPI specification, API documentation, authentication docs, a getting-started guide, rate-limit docs, and pricing.

This API exposes 10 operations across 7 paths, and defines 5 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against a single base URL, https://api.endpoints.huggingface.cloud/v2.

10 operations 7 paths 5 schemas 1 DELETE4 GET4 POST1 PUT

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.0.0
Base URL
https://api-inference.huggingface.co
Authentication
HTTP Bearer
License
Terms of Service
Resource Areas
1

Authentication & Security 1

Hugging Face Endpoints API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (HF Token) (bearerAuth). By default, every request must be authenticated.

  • bearerAuth — Hugging Face user access token with Inference Endpoints permissions.

Paths & Operations 10

Across 7 paths, the API surfaces 10 operations — 1 DELETE, 4 GET, 4 POST, 1 PUT. Each is listed below with its method, path, parameters, and response codes.

Endpoints 10

Manage dedicated inference endpoints

GET
/endpoint/{namespace}
List All Endpoints
listEndpoints 1 param → 200401
POST
/endpoint/{namespace}
Create a New Endpoint
createEndpoint 1 param body → 201400401409
GET
/endpoint/{namespace}/{endpoint_name}
Get Endpoint Details
getEndpoint 2 params → 200404
PUT
/endpoint/{namespace}/{endpoint_name}
Update an Endpoint
updateEndpoint 2 params body → 200400404
DELETE
/endpoint/{namespace}/{endpoint_name}
Delete an Endpoint
deleteEndpoint 2 params → 200404
POST
/endpoint/{namespace}/{endpoint_name}/pause
Pause an Endpoint
pauseEndpoint 2 params → 200404
POST
/endpoint/{namespace}/{endpoint_name}/resume
Resume an Endpoint
resumeEndpoint 2 params → 200404
POST
/endpoint/{namespace}/{endpoint_name}/scale-to-zero
Scale Endpoint to Zero
scaleToZero 2 params → 200404
GET
/endpoint/{namespace}/{endpoint_name}/logs
Get Endpoint Logs
getEndpointLogs 2 params → 200404
GET
/endpoint/{namespace}/{endpoint_name}/metrics
Get Endpoint Metrics
getEndpointMetrics 2 params → 200

Schemas 5

The contract defines 5 schemas that model the data the API accepts and returns. The most detailed are Endpoint (8 properties), CreateEndpointRequest (5 properties), EndpointMetrics (4 properties), UpdateEndpointRequest (3 properties). Each schema is shown below with its type and property counts.

UpdateEndpointRequest
object
3 properties
Error
object
2 properties
CreateEndpointRequest
object
5 properties 5 required
Endpoint
object
8 properties
EndpointMetrics
object
4 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

hugging-face-endpoints-api-openapi.yml Raw ↑

Other APIs Hugging Face publishes across the network.

Hugging Face Audio API
Hugging Face Chat API
Hugging Face Chat Completions API
Hugging Face Computer Vision API
Hugging Face Data Access API
Hugging Face Dataset Info API
Hugging Face Datasets API
Hugging Face Embeddings API
Hugging Face Files & Metadata API
Hugging Face Image Generation API
Hugging Face Info API
Hugging Face Models API
Where this information came from

This is an independent, third-party profile of Hugging Face Endpoints API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.