Jina AI · Agentic Access

Jina AI Agentic Access

x-agentic-access generated

Jina AI exposes 9 API operations that an AI agent could call, of which 5 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: 4 read and 5 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.

AIEmbeddingsMachine LearningRerankingSearch
Operations: 9 Acting: 5 Human-in-the-loop: 0 Method: generated

By consequence

read 4 write 5

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/jina-ai-embeddings-openapi.yml, openapi/jina-ai-reader-openapi.yml, openapi/jina-ai-reranker-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: 9
  by_action_class:
    acting: 5
    connected: 4
  by_consequence:
    write: 5
    read: 4
  human_in_the_loop_required: 0
operations:
- path: /embeddings
  method: post
  operationId: createEmbeddings
  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: /batch/embeddings
  method: post
  operationId: submitBatchEmbeddings
  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: /batch/{batch_id}
  method: get
  operationId: getBatchJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /batch/{batch_id}
  method: delete
  operationId: cancelBatchJob
  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: /batch/{batch_id}/output
  method: get
  operationId: getBatchOutput
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /batch/{batch_id}/errors
  method: get
  operationId: getBatchErrors
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /
  method: post
  operationId: readUrl
  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: /{url}
  method: get
  operationId: readUrlByPath
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /rerank
  method: post
  operationId: rerank
  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