Nodes/LMStudio Remote Nodes/LMStudio - Connect
ComfyUI Node

LMStudio - Connect

Creates a reusable LMStudio connection for downstream nodes. Set the Server URL, then click 'Refresh Models' to load and pick a model. 'Test Connection' verifies the server is reachable.

By glonlas·Created 5 months ago·Updated 28 days ago· 1
LMStudio - Connect
    • Connection
    • Status
    server_urlhttp://127.0.0.1:1234
    model<refresh models>
    thinkingauto
    api_token-
    use_tooling_mcpfalse
    max_tokens1024
    temperature0.70
    timeout_seconds600
    test_connectivitytrue
    CategoryLMStudio

    Inputs (9)

    NameTypeDefaultDescription
    server_urlSTRINGhttp://127.0.0.1:1234LMStudio server address, e.g. http://127.0.0.1:1234 (no /v1).
    modelCOMBO<refresh models>Loaded model to use. Click 'Refresh Models' to populate this dropdown from the server, then pick one.
    thinkingCOMBOautoControls the model's reasoning phase. • auto — let the model decide; Gemma-family models are nudged on (they stay silent otherwise). • on — force reasoning on (enable_thinking:true). • off — suppress reasoning so the model answers directly, saving tokens.
    api_tokenSTRING-Bearer token for the LMStudio OpenAI-compatible API. Leave '-' for local servers.
    use_tooling_mcpBOOLEANfalseSignal intent to use MCP tooling. Only useful when the target model/session is configured for tool-enabled responses.
    max_tokensINT10241–1000000Max output tokens for downstream generation nodes.
    temperatureFLOAT0.700–2Sampling temperature for downstream generation nodes.
    timeout_secondsINT6001–3600HTTP request timeout for all LMStudio calls.
    test_connectivityBOOLEANtrueWhen enabled, validate server reachability and model availability during execution.

    Outputs (2)

    NameTypeDescription
    ConnectionLMSTUDIO_CONNECTIONReusable LMStudio connection payload for text/image nodes.
    StatusSTRINGConnection status summary.