Standard: Use this for STARTING a new conversation or one-off tasks. Supports Vision, JSON Schema, and Reasoning. Do not use this for follow-ups if you have a response ID.

Follow-up: Use this ONLY for continuing an existing conversation when you have a previous_response_id. It is faster and preserves context server-side.

Vision: Privacy-focused image analysis using local vision models (Llava, Moondream, etc).

Privacy-First: Reads a local file and queries the local LLM about its contents.

Local RAG: Performs semantic search across a directory using local embeddings.

Generate vector representations of text using a local model.

Check bridge machine and LM Studio host resource usage.

List loaded and available models.

Load a specific model into LM Studio memory.

Unload a model instance to free up memory/VRAM.

Verify LM Studio API connection and health.

Mesh & Network: Display the status of LM Link and discovered devices on the mesh.

Mesh & Network: Enable/Disable LM Link or set the local device name.

Mesh & Network: Set the preferred LM Link device for remote model resolution.

List files in a specific local directory.

Directly read the content of a local file.

Async Vision: Start a background image analysis task. Returns a Task ID.

Check the status and result of a background vision task.

Retrieve current bridge environment and network configuration.

CLI: Show the overall health of the LM Studio daemon and server.

CLI: List models currently available on disk.

CLI: List models currently loaded in memory.

CLI: Search for or download models from LM Studio Hub.

CLI: Import a model file into LM Studio.

CLI: Manage the local inference server.

CLI: Advanced model loading with granular control.

CLI: Capture a snapshot of current logs for a brief duration.

CLI: Manage and update the inference runtime engines.