LM Studio

LM Studio OpenAI Compatibility API

OpenAI-compatible endpoints for reuse of existing OpenAI clients.

GitHub OpenAPI

Operations 5

GET /v1/models List models (OpenAI-compatible) #
POST /v1/chat/completions Create chat completion (OpenAI-compatible) #
POST /v1/completions Create text completion (OpenAI-compatible) #
POST /v1/embeddings Create embeddings (OpenAI-compatible) #
POST /v1/responses Create a response (OpenAI Responses API compatible) #

Documentation

📖
Authentication
https://artifacts.apis.io/lm-studio/authentication/lm-studio-authentication.yml

Specifications

⚙
OpenAPI
https://artifacts.apis.io/lm-studio/openapi/lm-studio-openai-compatibility-api-openapi.yml

Other Resources

🔗
Conventions
https://artifacts.apis.io/lm-studio/conventions/lm-studio-conventions.yml
🔗
ErrorCatalog
https://artifacts.apis.io/lm-studio/errors/lm-studio-problem-types.yml
🔗
DataModel
https://artifacts.apis.io/lm-studio/data-model/lm-studio-data-model.yml
🔗
Conformance
https://artifacts.apis.io/lm-studio/conformance/lm-studio-conformance.yml
🔗
Lifecycle
https://artifacts.apis.io/lm-studio/lifecycle/lm-studio-lifecycle.yml

Work with this as data

Every API 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 apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • 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 API 
curl "https://apis.io/api/v1/apis/lm-studio:lm-studio-openai-compatibility-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

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

OpenAPI Specification

lm-studio-openai-compatibility-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: LM Studio Local Server OpenAI Compatibility API
  version: 1.0.0-beta
  description: 'LM Studio runs large language models locally and exposes a local HTTP server with three families of endpoints: the native LM Studio REST API (beta) under `/api/v1`, an OpenAI-compatible surface under `/v1`, and an Anthropic-compatible surface (`/v1/messages`).'
  contact:
    name: LM Studio
    url: https://lmstudio.ai/docs
  license:
    name: Proprietary (LM Studio application)
    url: https://lmstudio.ai/terms
  x-provenance:
    method: generated
    source: https://lmstudio.ai/docs/app/api/endpoints/rest
    generated: '2026-07-20'
servers:
- url: http://localhost:1234
  description: Default local LM Studio server (bind host/port configurable)
tags:
- name: OpenAI Compatibility
  description: OpenAI-compatible endpoints for reuse of existing OpenAI clients.
paths:
  /v1/models:
    get:
      tags:
      - OpenAI Compatibility
      operationId: openaiListModels
      summary: List models (OpenAI-compatible)
      responses:
        '200':
          description: OpenAI-style model list.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
  /v1/chat/completions:
    post:
      tags:
      - OpenAI Compatibility
      operationId: openaiChatCompletions
      summary: Create chat completion (OpenAI-compatible)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatRequest'
      responses:
        '200':
          description: OpenAI-style chat completion.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
  /v1/completions:
    post:
      tags:
      - OpenAI Compatibility
      operationId: openaiCompletions
      summary: Create text completion (OpenAI-compatible)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                model:
                  type: string
                prompt:
                  type: string
                stream:
                  type: boolean
              required:
              - model
              - prompt
      responses:
        '200':
          description: OpenAI-style completion.
        '400':
          $ref: '#/components/responses/BadRequest'
  /v1/embeddings:
    post:
      tags:
      - OpenAI Compatibility
      operationId: openaiEmbeddings
      summary: Create embeddings (OpenAI-compatible)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                model:
                  type: string
                input:
                  oneOf:
                  - type: string
                  - type: array
                    items:
                      type: string
              required:
              - model
              - input
      responses:
        '200':
          description: Embedding vectors.
        '400':
          $ref: '#/components/responses/BadRequest'
  /v1/responses:
    post:
      tags:
      - OpenAI Compatibility
      operationId: openaiResponses
      summary: Create a response (OpenAI Responses API compatible)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                model:
                  type: string
                input: {}
              required:
              - model
              - input
      responses:
        '200':
          description: Response object.
components:
  schemas:
    ModelList:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
    Message:
      type: object
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
        content:
          type: string
      required:
      - role
      - content
    ChatRequest:
      type: object
      properties:
        model:
          type: string
          description: Identifier of a loaded model.
        messages:
          type: array
          items:
            $ref: '#/components/schemas/Message'
        stream:
          type: boolean
          default: false
        temperature:
          type: number
        max_tokens:
          type: integer
        tools:
          type: array
          items:
            type: object
        response_format:
          type: object
          description: Structured-output enforcement via JSON schema.
      required:
      - model
      - messages
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string
    ChatResponse:
      type: object
      properties:
        id:
          type: string
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                $ref: '#/components/schemas/Message'
              finish_reason:
                type: string
        stats:
          $ref: '#/components/schemas/GenerationStats'
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            completion_tokens:
              type: integer
            total_tokens:
              type: integer
    Model:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
        type:
          type: string
          enum:
          - llm
          - embeddings
          - vlm
        arch:
          type: string
        state:
          type: string
          enum:
          - loaded
          - not-loaded
        max_context_length:
          type: integer
    GenerationStats:
      type: object
      description: LM Studio generation performance metrics.
      properties:
        tokens_per_second:
          type: number
        time_to_first_token:
          type: number
        generation_time:
          type: number
        stop_reason:
          type: string
  responses:
    BadRequest:
      description: The request was malformed or referenced an unavailable model.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    ApiToken:
      type: http
      scheme: bearer
      description: Optional API token. The native `/api/v1` server can be configured to require a bearer token; by default the local server accepts unauthenticated requests from the loopback interface.