CentML · Agentic Access

CentML Agentic Access

x-agentic-access generated

CentML exposes 14 API operations that an AI agent could call, of which 6 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 8 read, 2 write, and 4 physical.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

AILLMInferenceServerlessGPU

Operations: 14 Acting: 6 Human-in-the-loop: 0 Method: generated

By consequence

read 8 write 2 physical 4

Highest-consequence actions

The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.

Method	Path	Consequence	Human-in-loop
POST	/deployments/compute	physical	conditional
POST	/deployments/inference	physical	conditional
PUT	/deployments/inference	physical	conditional
PUT	/deployments/status/{deployment_id}	physical	conditional

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/centml-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 14
  by_action_class:
    acting: 6
    connected: 8
  by_consequence:
    write: 2
    read: 8
    physical: 4
  human_in_the_loop_required: 0
operations:
- path: /chat/completions
  method: post
  operationId: createChatCompletion
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /completions
  method: post
  operationId: createCompletion
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /models
  method: get
  operationId: listModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /models/{model}
  method: get
  operationId: retrieveModel
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /deployments
  method: get
  operationId: listDeployments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /deployments/inference
  method: post
  operationId: createInferenceDeployment
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /deployments/inference
  method: put
  operationId: updateInferenceDeployment
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /deployments/inference/{deployment_id}
  method: get
  operationId: getInferenceDeployment
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /deployments/compute
  method: post
  operationId: createComputeDeployment
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /deployments/status/{deployment_id}
  method: get
  operationId: getDeploymentStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /deployments/status/{deployment_id}
  method: put
  operationId: updateDeploymentStatus
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /deployments/logs/{deployment_id}
  method: get
  operationId: getDeploymentLogs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /clusters
  method: get
  operationId: getClusters
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /capacity
  method: get
  operationId: listCapacity
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none