Skip to main content

CHAT

Open an interactive streaming chat session with a deployment.
Arguments Options

CREATE

Create a new model deployment from a JSON request body.
Options

DELETE

Permanently delete a deployment by ID.
Arguments Options

ENDPOINT

Print the inference endpoint, model path, and a runnable curl snippet.
Arguments Options

GENERATE-TEMPLATE

Print a ready-to-edit deployment request body for a deployment type. No API call is made.
Options

GET

Get a deployment by ID.
Arguments Options

HEALTH

Report a deployment’s request and error counts, latency and throughput over a time range.
Arguments Options

INVOKE

Run one inference call against a deployment and print the reply.
Arguments Options

IS-READY

Check whether a deployment has an active replica available to serve inference.
Arguments Options

LIST

List deployments in the project.
Options

LOGS DELETE

Permanently delete inference log entries for a deployment, optionally within a time range.
Arguments Options

LOGS EXPORT

Export a time range of inference logs into a new or existing dataset.
Arguments Options

LOGS GET

Get a single inference log entry by ID, including the full request/response.
Arguments Options

LOGS LIST

List inference log entries for a deployment.
Arguments Options

SUPPORTED-MODELS

List the models this project can deploy, before create/generate-template.
Options

TARGETS LIST

List the inference targets attached to a deployment.
Arguments Options

UPDATE

Change a deployment’s display name, inference logging, or autoscaling.
Arguments Options

WAKE-UP

Send a dummy request to scale a provider-idled deployment back up.
Arguments Options