Package Exports

@cianfrani/lmstudio
@cianfrani/lmstudio/dist/index.js
@cianfrani/lmstudio/dist/index.mjs

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@cianfrani/lmstudio) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

@cianfrani/lm-studio

LM Studio provider for the AI SDK.

Installation

npm install @cianfrani/lmstudio

Usage

Chat API

import { lmstudio } from '@cianfrani/lmstudio';
import { generateText } from 'ai';

const { text } = await generateText({
  model: lmstudio('qwen2.5-7b-instruct'),
  prompt: 'Hello, how are you?',
});

Responses API (Beta)

The responses API provides access to reasoning traces and structured outputs from models that support reasoning.

Installation

npm install @cianfrani/lmstudio@responses

Usage

import { lmstudio } from '@cianfrani/lmstudio';
import { generateText } from 'ai';

const { text } = await generateText({
  model: lmstudio('gpt-oss', { api: 'responses', reasoningEffort: 'medium' }),
  prompt: 'Solve this complex problem...',
});

API

createLMStudio(options?)

Creates an LM Studio provider instance.

Options

baseURL?: string - Base URL for LM Studio API. Defaults to http://localhost:1234/v1.
apiKey?: string - API key for authentication. LM Studio typically doesn't require this.
headers?: Record<string, string> - Custom headers to include in requests.
fetch?: FetchFunction - Custom fetch function.
api?: 'chat' | 'responses' - API to use. Defaults to 'chat'. (Responses API requires beta version)
reasoningEffort?: 'low' | 'medium' | 'high' - Reasoning effort for responses API.

lmstudio

Default LM Studio provider instance.

lmstudio(modelId, settings?)

Creates a chat model instance.

lmstudio.textEmbeddingModel(modelId, settings?)

Creates an embedding model instance.

Model IDs

Chat Models

qwen2.5-7b-instruct
gpt-oss
Any other model ID supported by LM Studio

Embedding Models

text-embedding-nomic-embed-text-v1.5
all-MiniLM-L6-v2
Any other embedding model supported by LM Studio

License

MIT