LLMInferenceProbeResult

Outcome of the optional generation round-trip, reported separately from the model-list probe so "the list opens but inference fails" is legible.

successSuccess (boolean)필수

the completion request returned 2xx

reasonReason (string)필수

ok | auth_failed | http_error | unreachable | invalid_url | model_required

messageMessage (string)필수

Human-readable inference result in English. Clients may localize it using the structured reason value.

latency_msLatency Ms (number)필수

status_code object

upstream HTTP status when a response was received

하나 이상(anyOf)

• integer
• null

integer

probed_url object

completion URL actually requested

하나 이상(anyOf)

• string
• null

string

body object

Upstream response body, masked and length-capped. It is also returned when the request fails, and is null when no response was received.

하나 이상(anyOf)

• string
• null

string

content object

generated text, masked and length-capped

하나 이상(anyOf)

• string
• null

string

reasoning_content object

chain of thought when the endpoint reports one (Anthropic thinking blocks, OpenAI-compatible reasoning_content/reasoning)

하나 이상(anyOf)

• string
• null

string

usage object

token usage block the endpoint reported, as-is

하나 이상(anyOf)

• object
• null

object

finish_reason object

OpenAI finish_reason / Anthropic stop_reason, when reported

하나 이상(anyOf)

• string
• null

string

ttft_ms object

Time to the first token in milliseconds, measured from request start to the first streamed text or thinking delta. It is null unless measure_ttft was requested, and also when the stream carried no delta.

하나 이상(anyOf)

• number
• null

number

LLMInferenceProbeResult

{
  "success": true,
  "reason": "string",
  "message": "string",
  "latency_ms": 0,
  "status_code": 0,
  "probed_url": "string",
  "body": "string",
  "content": "string",
  "reasoning_content": "string",
  "usage": {},
  "finish_reason": "string",
  "ttft_ms": 0
}