Usage
Examples
Inspect serverless readiness before sending a request.
Send a serverless chat-completions request with an explicit inference API key.
List models from the default serverless host.
Subcommands
tm infer chat: Call POST /v1/chat/completions on serverless inference.tm infer completions: Call POST /v1/completions on serverless inference.tm infer detokenize: Call POST /detokenize on serverless inference.tm infer doctor: Inspect serverless inference readiness for the next request.tm infer health: Call GET /health on serverless inference.tm infer models: Call GET /v1/models on serverless inference.tm infer responses: Call POST /v1/responses on serverless inference.tm infer tokenize: Call POST /tokenize on serverless inference.tm infer version: Call GET /version on serverless inference.

