Mistral AI · Agentic Access
Mistral AI Agentic Access
x-agentic-access
generated
Mistral AI exposes 21 API operations that an AI agent could call, of which 13 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 and 13 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.
AgentsArtificial IntelligenceBatch ProcessingChatEmbeddingsFine-TuningLarge Language ModelsOCR
Operations: 21
Acting: 13
Human-in-the-loop: 0
Method: generated
By consequence
read 8
write 13
Source
Agentic Access
generated: '2026-07-15'
method: generated
source: openapi/mistral-ai-agents-openapi.yml, openapi/mistral-ai-batch-openapi.yml, openapi/mistral-ai-chat-completions-openapi.yml,
openapi/mistral-ai-embeddings-openapi.yml, openapi/mistral-ai-fine-tuning-openapi.yml, openapi/mistral-ai-forge-openapi.yml,
openapi/mistral-ai-models-openapi.yml, openapi/mistral-ai-ocr-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: 21
by_action_class:
acting: 13
connected: 8
by_consequence:
write: 13
read: 8
human_in_the_loop_required: 0
operations:
- path: /agents/completions
method: post
operationId: createAgentCompletion
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/jobs
method: post
operationId: createBatchJob
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/jobs
method: get
operationId: listBatchJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /batch/jobs/{job_id}
method: get
operationId: getBatchJob
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /batch/jobs/{job_id}/cancel
method: post
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: /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: /embeddings
method: post
operationId: createEmbedding
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: /fine_tuning/jobs
method: post
operationId: createFineTuningJob
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: /fine_tuning/jobs
method: get
operationId: listFineTuningJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /fine_tuning/jobs/{job_id}
method: get
operationId: getFineTuningJob
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /fine_tuning/jobs/{job_id}/cancel
method: post
operationId: cancelFineTuningJob
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: /fine_tuning/jobs/{job_id}/start
method: post
operationId: startFineTuningJob
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: /forge/training/jobs
method: post
operationId: createTrainingJob
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: /forge/training/jobs
method: get
operationId: listTrainingJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /forge/training/jobs/{job_id}
method: get
operationId: getTrainingJob
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /forge/training/jobs/{job_id}/cancel
method: post
operationId: cancelTrainingJob
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_id}
method: get
operationId: getModel
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /models/{model_id}
method: delete
operationId: deleteModel
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: /fine_tuning/models/{model_id}
method: patch
operationId: updateFineTunedModel
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: /ocr
method: post
operationId: processOcr
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