Manage inference endpoints.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
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.curl "https://apis.io/api/v1/apis/hugging-face-transformers-inference-endpoints-api"curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Hub API Endpoints agentic-provisioning Inference Endpoints API
version: 0.0.1
description: 'We have open endpoints that you can use to retrieve information from the Hub as well as perform certain actions such as creating model, dataset or Space repos. We offer a wrapper Python client, [`huggingface_hub`](https://github.com/huggingface/huggingface_hub), and a JS client, [`huggingface.js`](https://github.com/huggingface/huggingface.js), that allow easy access to these endpoints. We also provide [webhooks](https://huggingface.co/docs/hub/webhooks) to receive real-time incremental info about repos. Enjoy!
The base URL for those endpoints below is `https://huggingface.co`. For example, to construct the `/api/models` call below, one can call the URL [https://huggingface.co/api/models](https://huggingface.co/api/models).
If you''re an Agent, you might prefer the [markdown version OpenAPI spec](https://huggingface.co/.well-known/openapi.md).
'
servers:
- url: https://huggingface.co
description: Hub
security:
- bearerAuth: []
tags:
- name: inference-endpoints
x-displayName: Inference Endpoints
description: Manage inference endpoints.
paths:
/api/inference-endpoints/{namespace}/auth-check/{perms}:
post:
description: Check if the user has access to the inference endpoint
summary: Check access
tags:
- inference-endpoints
responses:
'200':
content:
application/json:
schema:
$schema: https://json-schema.org/draft/2020-12/schema
type: object
properties:
namespace:
type: object
properties:
id:
type: string
name:
type: string
required:
- id
- name
additionalProperties: false
user:
type: object
properties:
id:
type: string
name:
type: string
hasHfLevelAccess:
type: boolean
required:
- id
- name
additionalProperties: false
required:
- namespace
- user
additionalProperties: false
description: The user has access to the inference endpoint/resource
'207':
content:
application/json:
schema:
$schema: https://json-schema.org/draft/2020-12/schema
type: object
properties:
namespace:
type: object
properties:
id:
type: string
name:
type: string
required:
- id
- name
additionalProperties: false
user:
type: object
properties:
id:
type: string
name:
type: string
hasHfLevelAccess:
type: boolean
required:
- id
- name
additionalProperties: false
patternRestrictions:
type: array
items:
type: string
required:
- namespace
- user
- patternRestrictions
additionalProperties: false
description: The user has access to the resource, but the endpoint name is restricted by pattern restrictions. Can only be returned if `endpoint` is not provided in the path
parameters:
- name: namespace
in: path
required: true
schema:
type: string
- name: perms
in: path
required: true
schema:
type: string
enum:
- read
- write
- infer
- name: own
in: query
schema: {}
required: false
- name: is_creator
in: query
schema: {}
required: false
- name: creator_id
in: query
schema:
type: string
minLength: 24
maxLength: 24
pattern: ^[0-9a-fA-F]{24}$
required: false
- name: incur_cost
in: query
schema: {}
required: false
- name: resource_group_id
in: query
schema:
type: string
minLength: 24
maxLength: 24
pattern: ^[0-9a-fA-F]{24}$
required: false
- name: repo_id
in: query
schema:
type: string
required: false
/api/inference-endpoints/{namespace}/{endpoint}/auth-check/{perms}:
post:
description: Check if the user has access to the inference endpoint
summary: Check access
tags:
- inference-endpoints
responses:
'200':
content:
application/json:
schema:
$schema: https://json-schema.org/draft/2020-12/schema
type: object
properties:
namespace:
type: object
properties:
id:
type: string
name:
type: string
required:
- id
- name
additionalProperties: false
user:
type: object
properties:
id:
type: string
name:
type: string
hasHfLevelAccess:
type: boolean
required:
- id
- name
additionalProperties: false
required:
- namespace
- user
additionalProperties: false
description: The user has access to the inference endpoint/resource
'207':
content:
application/json:
schema:
$schema: https://json-schema.org/draft/2020-12/schema
type: object
properties:
namespace:
type: object
properties:
id:
type: string
name:
type: string
required:
- id
- name
additionalProperties: false
user:
type: object
properties:
id:
type: string
name:
type: string
hasHfLevelAccess:
type: boolean
required:
- id
- name
additionalProperties: false
patternRestrictions:
type: array
items:
type: string
required:
- namespace
- user
- patternRestrictions
additionalProperties: false
description: The user has access to the resource, but the endpoint name is restricted by pattern restrictions. Can only be returned if `endpoint` is not provided in the path
parameters:
- name: namespace
in: path
required: true
schema:
type: string
- name: endpoint
in: path
required: true
schema:
type: string
- name: perms
in: path
required: true
schema:
type: string
enum:
- read
- write
- infer
- name: own
in: query
schema: {}
required: false
- name: is_creator
in: query
schema: {}
required: false
- name: creator_id
in: query
schema:
type: string
minLength: 24
maxLength: 24
pattern: ^[0-9a-fA-F]{24}$
required: false
- name: incur_cost
in: query
schema: {}
required: false
- name: resource_group_id
in: query
schema:
type: string
minLength: 24
maxLength: 24
pattern: ^[0-9a-fA-F]{24}$
required: false
- name: repo_id
in: query
schema:
type: string
required: false
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer