Taalas · Agentic Access

Taalas Agentic Access

x-agentic-access generated

Taalas exposes 6 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: 3 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.

Companyartificial-intelligenceai-inferencesemiconductorsai-acceleratorlarge-language-modelsllamainference-apiopenai-compatiblehardwaredeep-tech
Operations: 6 Acting: 3 Human-in-the-loop: 0 Method: generated

By consequence

read 3 write 3

Source

Agentic Access

Raw ↑ 
generated: '2026-08-02'
method: generated
source: openapi/taalas-inference-api-openapi.yml, openapi/taalas-inference-v1-api-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: 6
  by_action_class:
    connected: 3
    acting: 3
  by_consequence:
    read: 3
    write: 3
  human_in_the_loop_required: 0
operations:
- path: /health
  method: get
  operationId: health_health_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /models
  method: get
  operationId: models_models_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /generate
  method: post
  operationId: generate_generate_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: /models
  method: get
  operationId: models_models_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /completions
  method: post
  operationId: completions_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: /chat/completions
  method: post
  operationId: chat_completions_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