DeepL · Agentic Access

DeepL Agentic Access

x-agentic-access generated

DeepL exposes 15 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: 9 read and 6 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.

Artificial IntelligenceDeep LearningGlossariesLocalizationMachine LearningMachine TranslationTranslation

Operations: 15 Acting: 6 Human-in-the-loop: 0 Method: generated

By consequence

read 9 write 6

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/deepl-translation-api-openapi.yml, openapi/deepl-voice-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: 15
  by_action_class:
    acting: 6
    connected: 9
  by_consequence:
    write: 6
    read: 9
  human_in_the_loop_required: 0
operations:
- path: /translate
  method: post
  operationId: translateText
  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: /document
  method: post
  operationId: uploadDocument
  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: /document/{documentId}
  method: get
  operationId: getDocumentStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /document/{documentId}/result
  method: get
  operationId: downloadDocument
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /glossaries
  method: get
  operationId: listGlossaries
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /glossaries
  method: post
  operationId: createGlossary
  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: /glossaries/{glossaryId}
  method: get
  operationId: getGlossary
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /glossaries/{glossaryId}
  method: delete
  operationId: deleteGlossary
  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: /glossaries/{glossaryId}/entries
  method: get
  operationId: getGlossaryEntries
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /glossary-language-pairs
  method: get
  operationId: listGlossaryLanguagePairs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /languages
  method: get
  operationId: listLanguages
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /usage
  method: get
  operationId: getUsage
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /write/rephrase
  method: post
  operationId: rephraseText
  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: /voice/realtime
  method: post
  operationId: requestVoiceSession
  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: /voice/realtime
  method: get
  operationId: reconnectVoiceSession
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none