Cerebras Systems · Agentic Access

Cerebras Systems Agentic Access

x-agentic-access generated

Cerebras Systems exposes 8 API operations that an AI agent could call, of which 3 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: 5 read and 3 write.

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.

CompanyAi InfrastructureArtificial IntelligenceMachine LearningInferenceLarge Language ModelsDeveloper ToolsCloud ComputingSemiconductors

Operations: 8 Acting: 3 Human-in-the-loop: 0 Method: generated

By consequence

read 5 write 3

Source

Agentic Access

generated: '2026-07-18'
method: generated
source: openapi/cerebras-systems-chat-completions-openapi.yaml, openapi/cerebras-systems-inference-openapi-original.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: 8
  by_action_class:
    acting: 3
    connected: 5
  by_consequence:
    write: 3
    read: 5
  human_in_the_loop_required: 0
operations:
- path: /v1/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: /public/v1/models
  method: get
  operationId: list_public_models_endpoint_public_v1_models_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /public/v1/models/{model_id}
  method: get
  operationId: get_public_model_public_v1_models__model_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v1/chat/completions
  method: post
  operationId: chat_v1_chat_completions_post
  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: /v1/completions
  method: post
  operationId: completions_v1_completions_post
  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: /v1/models
  method: get
  operationId: list_models_v1_models_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v1/models/{model_id}
  method: get
  operationId: get_model_v1_models__model_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v1/tcp_warming
  method: get
  operationId: tcp_warming_v1_tcp_warming_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none