v1

latestOpenAPI 3.1.0Apache-2.02026-07-17111932.3 KB

Health

Liveness check

Liveness probe (same as Python tt-liveness). Returns 200 with {"status": "alive", ...system status} when the process can respond. model_ready in the body reflects whether any worker has warmed up. Does not return 503 for model not ready; 500 only on unrecoverable failure.

get/tt-liveness

Response

Process is alive; body includes status alive and system status (model_ready, workers, queue)

model_readyboolean

Whether the model is ready for inference

queue_sizeinteger

Current number of requests in queue

max_queue_sizeinteger

Maximum queue capacity

devicestring

Device type

worker_infoobject

Worker status keyed by worker ID (Python-server-compatible format)

runner_in_usestring

Active runner identifier (image services only). Mirrors the Python ModelRunners enum (e.g. 'tt-sdxl-trace', 'tt-sdxl-image-to-image', 'tt-sdxl-edit'). Omitted when the active service does not expose a runner.