RUTY / COMMAND LINE
Stay in your flow.
Models, quotes, generation and task history. All from your terminal, with JSON output that works in your scripts.
Install
Node.js 20 or later. Install the versioned CLI package directly from Ruty.
npm install -g https://ruty.ai/downloads/ruty-cli.tgzMake your first call
Create an API key in the console and set it in your shell.
export RUTY_API_KEY="YOUR_API_KEY"
ruty models --kind image
ruty price --model-id gpt-image-2 --resolution 1K
ruty image --model-id gpt-image-2 \
--prompt "A quiet observatory above the clouds" \
--resolution 1K --idempotency-key "$(uuidgen)"Everyday commands
ruty models --kind video
ruty balance
ruty task --kind image --id TASK_ID
ruty tasks --kind video --limit 10
# Pipe structured JSON into your own tools
ruty models --kind image | jq ".models[].id"
# Call any Ruty MCP tool directly
ruty call ruty_list_models --json '{"kind":"image"}'
# Launch the local stdio MCP bridge
ruty mcpEnvironment
| Variable | Purpose |
|---|---|
RUTY_API_KEY | Required API key. |
RUTY_MCP_URL | Optional endpoint. Defaults to https://ruty.ai/api/mcp. |
RUTY_TEAM_WORKSPACE_ID | Optional team workspace UUID. |
RUTY_TEAM_PROJECT_ID | Optional project UUID; requires a workspace. |
Successful commands write JSON to stdout. Errors go to stderr with a nonzero exit code. The CLI does not automatically retry generation calls.
Configure your MCP client ↗