spiceai/docs

trunk

title: 'chat' sidebar_label: 'chat' pagination_prev: null pagination_next: null description: 'spice chat CLI documentation'

Start an interactive or one-shot chat with a model registered in the Spice runtime.

--cloud Send requests to a Spice Cloud instance instead of the local instance. Default: false.
--http-endpoint <string> Runtime HTTP endpoint. Default: http://localhost:8090.
--model <string> Target model for the chat request. When omitted, the CLI uses the single ready model or prompts for a choice if several models are ready.
--temperature <float32> Model temperature used for chat request. Default: 1.
--user-agent <string> Custom User-Agent header sent with every request.

When exactly one model is ready, spice chat opens a REPL that uses that model automatically:

When multiple models are ready, the command prompts for a selection before starting the REPL:

Passing --model skips the prompt and directs the request to the specified model. The flag works both in REPL mode and in one‑shot mode:

Single prompt: