Ollama Running Models API

openapi: 3.1.0
info:
  title: Ollama Blobs Running Models API
  description: Ollama provides a REST API for running and managing large language models locally. The API supports text generation, chat completions, embeddings, model management, and streaming responses. It serves as the primary interface for interacting with models running on the Ollama inference engine at localhost:11434.
  version: 0.1.0
  contact:
    name: Ollama Team
    url: https://ollama.com
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
  termsOfService: https://ollama.com/terms
servers:
- url: http://localhost:11434
  description: Local Ollama Server
tags:
- name: Running Models
  description: View models currently loaded in memory and their resource usage.
paths:
  /api/ps:
    get:
      operationId: listRunningModels
      summary: Ollama List running models
      description: List models that are currently loaded into memory on the Ollama server, including their VRAM usage, context length, and expiration time.
      tags:
      - Running Models
      responses:
        '200':
          description: Successful response with list of running models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PsResponse'
components:
  schemas:
    PsResponse:
      type: object
      description: Response containing a list of models currently loaded in memory.
      properties:
        models:
          type: array
          description: The list of currently running models.
          items:
            $ref: '#/components/schemas/RunningModel'
    ModelDetails:
      type: object
      description: Detailed metadata about a model's format and architecture.
      properties:
        format:
          type: string
          description: The file format of the model, such as gguf.
        family:
          type: string
          description: The primary model family, such as llama or gemma.
        families:
          type: array
          description: All model families this model belongs to.
          items:
            type: string
        parameter_size:
          type: string
          description: The parameter count label, such as 7B or 13B.
        quantization_level:
          type: string
          description: The quantization method used, such as Q4_0 or Q4_K_M.
    RunningModel:
      type: object
      description: Information about a model currently loaded in memory.
      properties:
        name:
          type: string
          description: The model name identifier.
        model:
          type: string
          description: The model identifier.
        size:
          type: integer
          description: The model size in bytes.
        digest:
          type: string
          description: The SHA256 hash of the model contents.
        details:
          $ref: '#/components/schemas/ModelDetails'
        expires_at:
          type: string
          format: date-time
          description: The timestamp when the model will be unloaded from memory.
        size_vram:
          type: integer
          description: The amount of VRAM consumed by the model in bytes.
        context_length:
          type: integer
          description: The maximum context window length supported.
externalDocs:
  description: Ollama API Documentation
  url: https://docs.ollama.com/api/introduction