Prompt sends a prompt to an upstream LLM and returns the model's completion.
Usage:
tare api prompt <prompt> [flags]
Flags:
--customer string Customer the prompt is billed/scoped against.
--key-id string Optional client_keys / api_keys row id (UUID) to bind this request to a specific customer-owned key for per-key ratelimit + fallback accounting on the dataplane.
--model string Model selector in provider/model form, e.g.
--project string Project the prompt is logged against.
Global Flags:
--base-url string override the active profile's base URL for this invocation
-o, --output string output format: json (default "json")
-p, --profile string credential profile (overrides AGENTROUTER_PROFILE / active)
-q, --quiet Suppress progress output; only errors and the final summary go to stderr
-v, --verbose Verbose output: plain-mode progress lines plus full per-blob chunk logs to stderr