LocalAI

LocalAI is the open-source, self-hosted AI inference engine that acts as a drop-in replacement for the OpenAI and Anthropic REST APIs. A single Go binary (or container) exposes 123 HTTP operations across chat completions, completions, embeddings, image and video generation, 3D generation, text-to-speech, speech-to-text, audio classification and diarization, object detection, depth estimation, reranking, moderation, tokenization, face and voice recognition, and the OpenAI Realtime API over WebSocket and WebRTC — all running locally on CPU or GPU with no external API calls and no data leaving the host. Beyond OpenAI parity, LocalAI ships its own management surface: a model and backend gallery, P2P and federated distributed inference, an agent/job runtime with a Skills system and Agent Hub, request middleware for NER-based PII redaction and policy-based intelligent model routing, tracing, per-user usage accounting, and a first-party stdio MCP server (`local-ai mcp-server`) that exposes the admin surface as agent tools. Authentication spans legacy shared API keys through a full user system with roles, sessions, GitHub OAuth and OIDC single sign-on. Distributed under the MIT licence by Ettore Di Giacinto (mudler) and community contributors.

LocalAI publishes 1 API on the APIs.io network. Tagged areas include Artificial Intelligence, Machine Learning, Large Language Models, Inference, and Self-Hosted.

The LocalAI catalog on APIs.io includes 1 event-driven AsyncAPI specification.

LocalAI’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, changelog, authentication, and 27 more developer resources.

1 APIs 1 MCP Servers
Artificial IntelligenceMachine LearningLarge Language ModelsInferenceSelf-HostedOpen SourceAgentsModel Context ProtocolSpeechComputer VisionEmbeddingsEdge Computing

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

LocalAI API

The LocalAI REST API — an OpenAI- and Anthropic-compatible HTTP surface plus LocalAI's own model, backend, agent, middleware, P2P and monitoring management endpoints. 123 operat...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Pricing Plans 1

Published pricing tiers and plan structures.

Localai Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Localai Rate Limits

0 limits

RATE LIMITS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

LocalAI Realtime API

The LocalAI Realtime API — an OpenAI Realtime-compatible, low-latency, multi-modal (voice and text) conversation surface carried over WebSocket, with an alternative WebRTC trans...

ASYNCAPI

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Localai Authentication

apiKey/http/oauth2/openIdConnect · 1 scheme

SECURITY

Localai Domain Security

TLSv1.3

SECURITY

Localai Vulnerability Disclosure

contact published

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 3

Reference material describing how the API behaves

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Build 5

SDKs, sample code, and the tooling you integrate with

Access & Security 4

Authentication, authorization, and security posture

Operate 5

Status, limits, changes, and where to get help

Commercial 2

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Other 2

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: localai
name: LocalAI
description: 'LocalAI is the open-source, self-hosted AI inference engine that acts as a drop-in replacement for the OpenAI
  and Anthropic REST APIs. A single Go binary (or container) exposes 123 HTTP operations across chat completions, completions,
  embeddings, image and video generation, 3D generation, text-to-speech, speech-to-text, audio classification and diarization,
  object detection, depth estimation, reranking, moderation, tokenization, face and voice recognition, and the OpenAI Realtime
  API over WebSocket and WebRTC — all running locally on CPU or GPU with no external API calls and no data leaving the host.
  Beyond OpenAI parity, LocalAI ships its own management surface: a model and backend gallery, P2P and federated distributed
  inference, an agent/job runtime with a Skills system and Agent Hub, request middleware for NER-based PII redaction and policy-based
  intelligent model routing, tracing, per-user usage accounting, and a first-party stdio MCP server (`local-ai mcp-server`)
  that exposes the admin surface as agent tools. Authentication spans legacy shared API keys through a full user system with
  roles, sessions, GitHub OAuth and OIDC single sign-on. Distributed under the MIT licence by Ettore Di Giacinto (mudler)
  and community contributors.'
url: https://raw.githubusercontent.com/api-evangelist/localai/refs/heads/main/apis.yml
x-type: company
x-source: harvest:self-hosted-agent-stack
specificationVersion: '0.20'
created: '2026-08-27'
modified: '2026-08-27'
image: https://raw.githubusercontent.com/mudler/LocalAI/master/core/http/static/logo_horizontal.png
tags:
- Artificial Intelligence
- Machine Learning
- Large Language Models
- Inference
- Self-Hosted
- Open Source
- Agents
- Model Context Protocol
- Speech
- Computer Vision
- Embeddings
- Edge Computing
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: localai:localai-api
  name: LocalAI API
  description: The LocalAI REST API — an OpenAI- and Anthropic-compatible HTTP surface plus LocalAI's own model, backend,
    agent, middleware, P2P and monitoring management endpoints. 123 operations over 114 paths, described by a Swagger 2.0
    document generated from the Go source and published in the project repository. LocalAI is self-hosted, so the base URL
    is the address of your own instance (the documented default is http://localhost:8080).
  humanURL: https://localai.io/docs/reference/
  baseURL: http://{localai-host}:8080
  tags:
  - Inference
  - Models
  - Audio
  - Images
  - Agents
  - Monitoring
  properties:
  - type: OpenAPI
    url: openapi/localai-api-openapi.yml
  - type: Swagger
    url: openapi/_original/localai-openapi.json
  - type: Overlay
    url: overlays/localai-api-overlay.yaml
  - type: Documentation
    url: https://localai.io/docs/
  - type: APIReference
    url: https://localai.io/docs/reference/
  - type: Authentication
    url: authentication/localai-authentication.yml
  - type: ErrorCatalog
    url: errors/localai-problem-types.yml
  - type: DataModel
    url: data-model/localai-data-model.yml
  - type: AsyncAPI
    url: asyncapi/localai-realtime-asyncapi.yml
  - type: Protobuf
    url: grpc/localai-backend.proto
common:
- type: Website
  url: https://localai.io/
- type: DeveloperPortal
  url: https://localai.io/docs/
- type: Documentation
  url: https://localai.io/docs/
- type: APIReference
  url: https://localai.io/docs/reference/
- type: GettingStarted
  url: https://localai.io/basics/getting_started/
- type: Support
  url: https://github.com/mudler/LocalAI/discussions
- type: Blog
  url: https://localai.io/blog/
- type: GitHubOrganization
  url: https://github.com/mudler/LocalAI
- type: SourceCode
  url: https://github.com/mudler/LocalAI
- type: License
  url: https://github.com/mudler/LocalAI/blob/master/LICENSE
- type: Security
  url: https://github.com/mudler/LocalAI/blob/master/SECURITY.md
- type: ChangeLog
  url: changelog/localai-changelog.yml
- type: Releases
  url: https://github.com/mudler/LocalAI/releases
- type: Packages
  url: packages/localai-packages.yml
- type: MCPServer
  url: mcp/localai-mcp.yml
- type: ToolCrosswalk
  url: mcp/localai-tool-crosswalk.yml
- type: LLMsTxt
  url: llms/localai-llms.txt
- type: Conformance
  url: conformance/localai-conformance.yml
- type: Lifecycle
  url: lifecycle/localai-lifecycle.yml
- type: Deprecation
  url: lifecycle/localai-lifecycle.yml
- type: Authentication
  url: authentication/localai-authentication.yml
- type: DomainSecurity
  url: security/localai-domain-security.yml
- type: VulnerabilityDisclosure
  url: security/localai-vulnerability-disclosure.yml
- type: Conventions
  url: conventions/localai-conventions.yml
- type: CLI
  url: cli/localai-cli.yml
- type: DataModel
  url: data-model/localai-data-model.yml
- type: ErrorCatalog
  url: errors/localai-problem-types.yml
- type: Sandbox
  url: sandbox/localai-sandbox.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Plans
  url: plans/localai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/localai-rate-limits.yml
- type: AsyncAPI
  url: asyncapi/localai-realtime-asyncapi.yml
- type: Protobuf
  url: grpc/localai-backend.proto
- type: gRPC
  url: grpc/localai-backend-proto.yml
x-enrichment:
  date: '2026-08-27'
  status: enriched
  artifacts_added: 30
  pass: local-v1

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This provider
curl "https://apis.io/api/v1/providers/localai"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/localai/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/localai/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.