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 (opens in a new tab) registered in the Spice runtime.
Requirements
- Spice runtime must be running
- At least one model defined in
spicepod.yaml and the model is ready
Usage
Interative Chat: Invoke the command without arguments to open a REPL
One-shot Chat: Pass a single message as the argument to send a one-shot chat request and print the response
spice chat [flags] [<message>]
spice chat [flags] [<message>]
Flags
--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.
Examples
When exactly one model is ready, spice chat opens a REPL that uses that model automatically:
> spice chat
Using model: openai
chat> hello
Hello! How can I assist you today?
Time: 0.57s (first token 0.53s). Tokens: 18. Prompt: 8. Completion: 10 (325.04/s).
> spice chat
Using model: openai
chat> hello
Hello! How can I assist you today?
Time: 0.57s (first token 0.53s). Tokens: 18. Prompt: 8. Completion: 10 (325.04/s).
When multiple models are ready, the command prompts for a selection before starting the REPL:
> spice chat
Use the arrow keys to navigate: ↓ ↑ → ←
? Select model:
▸ openai
llama
Using model: openai
chat> hello
Hello! How can I assist you today?
Time: 0.55s (first token 0.43s). Tokens: 18. Prompt: 8. Completion: 10 (80.09/s).
> spice chat
Use the arrow keys to navigate: ↓ ↑ → ←
? Select model:
▸ openai
llama
Using model: openai
chat> hello
Hello! How can I assist you today?
Time: 0.55s (first token 0.43s). Tokens: 18. Prompt: 8. Completion: 10 (80.09/s).
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:
# REPL
spice chat --model openai
chat> hello
Hello! How can I assist you today?
Time: 0.61s (first token 0.58s). Tokens: 18. Prompt: 8. Completion: 10 (285.90/s).
# REPL
spice chat --model openai
chat> hello
Hello! How can I assist you today?
Time: 0.61s (first token 0.58s). Tokens: 18. Prompt: 8. Completion: 10 (285.90/s).
Single prompt:
# One‑shot
spice chat --model openai "hello"
Hello! How can I assist you today?
Time: 1.10s (first token 0.80s). Tokens: 18. Prompt: 8. Completion: 10 (33.74/s).
# One‑shot
spice chat --model openai "hello"
Hello! How can I assist you today?
Time: 1.10s (first token 0.80s). Tokens: 18. Prompt: 8. Completion: 10 (33.74/s).
