{
  "opencollection": "1.0.0",
  "info": {
    "name": "ScalarLM Open AI API",
    "version": "1.151"
  },
  "items": [
    {
      "info": {
        "name": "OpenAI",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "List available models",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://gpt-oss.cray-lm.com/v1/models"
          },
          "docs": "Proxies the upstream vLLM server's /v1/models. Returns the OpenAI model list envelope."
        },
        {
          "info": {
            "name": "Create a completion",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://gpt-oss.cray-lm.com/v1/completions",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "OpenAI-compatible text completion. Proxied to the vLLM server; the request body is a vLLM CompletionRequest (OpenAI completions schema). Responses stream as text/event-stream."
        },
        {
          "info": {
            "name": "Create a chat completion",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://gpt-oss.cray-lm.com/v1/chat/completions",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "OpenAI-compatible chat completion. When stream is true the request is proxied straight to vLLM as an SSE stream; when false it is admitted to the queue-backed path (admission control -> coalescer -> SQLite inference work queue -> worker -> result router) and answered with a whitespace-heartbeat chunked JSON response."
        }
      ]
    }
  ],
  "bundled": true
}