CLI Tool

The tt CLI lets you manage behaviour specs, runs, models, and datasets from the command line — without writing API calls.

Installation

Install globally via npm:

npm install -g @tuned-tensor/cli

Verify the installation with tt --version.

Store your API key so you don't need to pass it on every command:

tt auth login tt_your_api_key

Check your auth status:

tt auth status

Other auth commands:

tt auth logout — Remove stored credentials
tt -k tt_your_api_key <command> — Pass API key inline (overrides stored key)
tt -u https://your-api.example.com <command> — Use a custom base URL (e.g. for local dev)

Command	Description
`tt auth`	Manage authentication (login, logout, status)
`tt specs`	List, create, get, update, delete behaviour specs
`tt runs`	List runs, start a run, get details, cancel, watch
`tt datasets`	List and manage datasets
`tt models`	List fine-tuned models
`tt usage`	Show usage summary and tier info
`tt init`	Create a local behaviour spec file (tunedtensor.json)
`tt push`	Push local spec to the Tuned Tensor API
`tt eval`	Evaluate a model against a behaviour spec locally

tt specs list
tt runs list

tt runs start <spec-id>

Use tt runs watch <run-id> to poll until the run completes.

# Create a local spec template
tt init -n "My Spec" --model meta-llama/Llama-3.2-3B-Instruct

# Edit tunedtensor.json, then push to the API
tt push

-k, --api-key <key> — Override stored API key
-u, --base-url <url> — Custom API base URL (default: https://www.tunedtensor.com)
--json — Output raw JSON
--no-color — Disable colors