openapi: 3.2.0
info:
  description: The LocalAI Rest API.
  title: LocalAI Nodes API
  contact:
    name: LocalAI
    url: https://localai.io
  license:
    name: MIT
    url: https://raw.githubusercontent.com/mudler/LocalAI/master/LICENSE
  version: 2.0.0
servers:
- url: /
tags:
- name: Nodes
paths:
  /api/nodes/models:
    get:
      tags:
      - Nodes
      summary: List all loaded models cluster-wide
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/nodes.NodeModel'
  /api/nodes/{id}/max-replicas-per-model:
    put:
      tags:
      - Nodes
      summary: Update a node's max replicas per model
      parameters:
      - description: Node ID
        name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                additionalProperties:
                  type: integer
        '400':
          description: value must be >= 1
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '404':
          description: node not found
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/localai.UpdateMaxReplicasPerModelRequest'
        description: New value
        required: true
    delete:
      tags:
      - Nodes
      summary: Reset a node's max replicas per model to the worker default
      parameters:
      - description: Node ID
        name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                additionalProperties:
                  type: boolean
        '404':
          description: node not found
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
  /api/nodes/{id}/vram-budget:
    put:
      tags:
      - Nodes
      summary: Update a node's VRAM allocation budget
      parameters:
      - description: Node ID
        name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                additionalProperties:
                  type: string
        '400':
          description: invalid budget
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '404':
          description: node not found
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/localai.UpdateVRAMBudgetRequest'
        description: New value (\
        required: true
    delete:
      tags:
      - Nodes
      summary: Reset a node's VRAM budget to the worker default
      parameters:
      - description: Node ID
        name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                additionalProperties:
                  type: boolean
        '404':
          description: node not found
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
components:
  schemas:
    localai.UpdateVRAMBudgetRequest:
      type: object
      properties:
        value:
          description: Value is the VRAM cap ("80%" or "12GB"). Empty string clears the cap.
          type: string
    localai.UpdateMaxReplicasPerModelRequest:
      type: object
      properties:
        value:
          description: Value is the new per-model replica cap on this node. Must be >= 1.
          type: integer
    nodes.NodeModel:
      type: object
      properties:
        address:
          description: gRPC address for this replica's backend process
          type: string
        backend_type:
          description: e.g. "llama-cpp"; used by reconciler to replicate loads
          type: string
        cleanup_attempts:
          type: integer
        cleanup_error:
          type: string
        cleanup_next_retry_at:
          type: string
        config_revision:
          type: string
        created_at:
          type: string
        effective_options_hash:
          type: string
        id:
          type: string
        in_flight:
          description: number of active requests on this replica
          type: integer
        last_used:
          type: string
        loading_by:
          description: frontend ID that triggered loading
          type: string
        model_name:
          type: string
        node_id:
          type: string
        replica_index:
          type: integer
        state:
          description: staging, loading, loaded, unloading, idle
          type: string
        updated_at:
          type: string
  securitySchemes:
    BearerAuth:
      type: apiKey
      name: Authorization
      in: header