HUD Inference API
The inference API from HUD — 1 operation(s) for inference.
The inference API from HUD — 1 operation(s) for inference.
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/hud-ai:hud-ai-inference-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
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: HUD Platform Inference API
version: 2.0.0
tags:
- name: Inference
paths:
/v2/inference/usage:
get:
tags:
- Inference
summary: Get Inference Usage
description: Get the team's inference usage over a window, with summary and paged requests.
operationId: get_inference_usage_v2_inference_usage_get
parameters:
- name: days
in: query
required: false
schema:
type: integer
maximum: 365
minimum: 1
default: 7
title: Days
- name: user_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: User Id
- name: api_key_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Api Key Id
- name: byok_credential_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Byok Credential Id
- name: model_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Model Id
- name: request_type
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Request Type
- name: limit
in: query
required: false
schema:
type: integer
maximum: 200
minimum: 1
default: 50
title: Limit
- name: offset
in: query
required: false
schema:
type: integer
maximum: 2147483647
minimum: 0
default: 0
title: Offset
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/InferenceUsageResponse'
'400':
description: Invalid or malformed request
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
description: Missing or invalid credentials
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'403':
description: Caller may not access this resource
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'404':
description: Referenced entity does not exist
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'409':
description: Resource already exists
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
'429':
description: Rate limit exceeded; wait at least Retry-After seconds
headers:
Retry-After:
description: Seconds until the request budget has room
schema:
type: integer
minimum: 0
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'503':
description: The server is at capacity; retry after Retry-After seconds
headers:
Retry-After:
description: Seconds to wait before retrying
schema:
type: integer
minimum: 0
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
components:
schemas:
InferenceUsageLog:
properties:
id:
type: string
format: uuid
title: Id
created_at:
type: string
format: date-time
title: Created At
model:
type: string
title: Model
qa_analysis:
type: boolean
title: Qa Analysis
default: false
cost:
type: number
title: Cost
type:
type: string
title: Type
model_checkpoint_id:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Model Checkpoint Id
checkpoint:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Checkpoint
metadata:
additionalProperties: true
type: object
title: Metadata
user_id:
anyOf:
- type: string
format: uuid
- type: 'null'
title: User Id
user_name:
anyOf:
- type: string
- type: 'null'
title: User Name
user_email:
anyOf:
- type: string
- type: 'null'
title: User Email
api_key_id:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Api Key Id
api_key_name:
anyOf:
- type: string
- type: 'null'
title: Api Key Name
byok:
type: boolean
title: Byok
default: false
byok_credential_id:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Byok Credential Id
type: object
required:
- id
- created_at
- model
- cost
- type
title: InferenceUsageLog
description: One inference request; QA analysis requests report ``model`` as the HUD QA label.
ErrorResponse:
properties:
error:
type: string
title: Error
source:
$ref: '#/components/schemas/ErrorSource'
detail:
type: string
title: Detail
type: object
required:
- error
- source
- detail
title: ErrorResponse
description: The uniform `{error, source, detail}` envelope returned for every 4xx/5xx.
InferenceUsageResponse:
properties:
logs:
items:
$ref: '#/components/schemas/InferenceUsageLog'
type: array
title: Logs
total_count:
type: integer
title: Total Count
team_id:
type: string
format: uuid
title: Team Id
type: object
required:
- logs
- total_count
- team_id
title: InferenceUsageResponse
description: 'Raw log listing for the request table.
Aggregates (totals, group-bys) live on ``GET /v2/usage/inference``.'
ErrorSource:
type: string
enum:
- user
- platform
- provider
title: ErrorSource
description: 'Who is at fault for a failure.
``user``: the customer''s input, account, environment, or agent code.
``platform``: HUD infrastructure or a broken platform invariant.
``provider``: a third-party dependency (cloud runtime, upstream LLM API).'
HTTPValidationError:
title: HTTPValidationError
type: object
properties:
error:
type: string
const: validation_error
title: Error
source:
type: string
enum:
- user
- platform
- provider
title: Source
detail:
type: string
title: Detail
errors:
type: array
items:
$ref: '#/components/schemas/ValidationError'
title: Errors
required:
- error
- source
- detail
- errors
ValidationError:
title: ValidationError
type: object
properties:
type:
type: string
title: Error Type
loc:
type: array
items:
anyOf:
- type: string
- type: integer
title: Location
msg:
type: string
title: Message
required:
- type
- loc
- msg
x-hud-contract-scope: platform_public