The OpenAPI spec details the endpoints for NVIDIA NIM for LLMs:

• /v1/health/ready - Health endpoint

• /v1/models - Show available models

• /v1/chat/completions - Chat Completions Endpoint

• /v1/completions - Completions Endpoint

The /v1/completions and /v1/chat/completions endpoints can be found in the NIM OpenAPI Schema.

Experimental support for Llama Stack (LS) API

• /experimental/ls/inference/chat_completion

• /experimental/ls/inference/completion

The /experimental/ls/inference/chat_completion and /experimental/ls/inference/completion endpoints can be found in the NIM OpenAPI Schema.