How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

LocalAI Monitoring API

The monitoring API from LocalAI — 16 operation(s) for monitoring.

LocalAI Monitoring API is one of 26 APIs that LocalAI publishes on the APIs.io network, described by a machine-readable OpenAPI specification and an AsyncAPI event-driven specification.

Tagged areas include Monitoring. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, authentication docs, and an AsyncAPI specification.

This API exposes 16 operations across 16 paths, and defines 13 schemas. It is described by OpenAPI 3.2.0, at version 2.0.0.

Requests are made against a single base URL, /.

16 operations 16 paths 13 schemas 11 GET5 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
2.0.0
Base URL
http://{localai-host}:8080
Authentication
API Key
Contact
License
Resource Areas
1

Authentication & Security 1

LocalAI Monitoring API declares 1 security scheme for authenticating requests. An API key is passed in the header as Authorization (BearerAuth).

Paths & Operations 16

Across 16 paths, the API surfaces 16 operations — 11 GET, 5 POST. Each is listed below with its method, path, parameters, and response codes.

monitoring 16
GET
/api/backend-logs
List models with backend logs
→ 200
GET
/api/backend-logs/{modelId}
Get backend logs for a model
1 param → 200
POST
/api/backend-logs/{modelId}/clear
Clear backend logs for a model
1 param → 204
GET
/api/backend-traces
List backend operation traces
3 params → 200
POST
/api/backend-traces/clear
Clear backend traces
→ 204
GET
/api/backend-traces/{id}
Get one backend operation trace
1 param → 200404
GET
/api/traces
List API request/response traces
3 params → 200
POST
/api/traces/clear
Clear API traces
→ 204
GET
/api/traces/summary
Summarize recent API traces
1 param → 200
GET
/api/traces/{id}
Get one API trace
1 param → 200404
POST
/backend/load
Pre-load a model into memory
body → 200400500
GET
/backend/monitor
Backend monitor endpoint
1 param → 200
POST
/backend/shutdown
Backend shutdown endpoint
body
GET
/metrics
Prometheus metrics endpoint
→ 200
GET
/system
Show the LocalAI instance information
→ 200
GET
/ws/backend-logs/{modelId}
Stream backend logs via WebSocket
1 param

Schemas 13

The contract defines 13 schemas that model the data the API accepts and returns. The most detailed are middleware.TraceSummary (5 properties), schema.APIError (4 properties), middleware.TraceBucket (3 properties), model.BackendLogLine (3 properties). Each schema is shown below with its type and property counts.

proto.StatusResponse_State
integer
middleware.TraceBucket
object
3 properties
schema.SystemInformationResponse
object
2 properties
schema.ModelLoadResponse
object
2 properties
model.BackendLogLine
object
3 properties
proto.MemoryUsageData
object
2 properties
schema.ErrorResponse
object
1 property
schema.APIError
object
4 properties
schema.BackendMonitorRequest
object
1 property
schema.ModelLoadRequest
object
1 property
schema.SysInfoModel
object
2 properties
middleware.TraceSummary
object
5 properties
proto.StatusResponse
object
2 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

localai-monitoring-api-openapi.yml Raw ↑

Other APIs LocalAI publishes across the network.

LocalAI 3d API
LocalAI Agent Jobs API
LocalAI Audio API
LocalAI Backends API
LocalAI Branding API
LocalAI Config API
LocalAI Depth API
LocalAI Detection API
LocalAI Embeddings API
LocalAI Face Recognition API
LocalAI Images API
LocalAI Inference API
Where this information came from

This is an independent, third-party profile of LocalAI Monitoring API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.