Skip to main content
GET
Export a metric revision as a document

Authorizations

Authorization
string
header
required

API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (gsk_*) and legacy (gsk-) API keys are accepted, e.g. Authorization: Bearer gsk_... or Authorization: Bearer gsk-....

Path Parameters

id
string
required

Metric revision ID

Example:

"metric_123"

Response

Metric export

metricId
string
required
metricGroupId
string
required

Shared by every revision of this metric.

name
string
required
source
enum<string> | null
required
Available options:
SELF_HOSTED,
FULL_PROMPT,
PARTIAL_PROMPT,
HUMAN_EVALUATION,
GEVAL,
DEEPEVAL,
DETERMINISTIC,
null
definition
string | null
required

Selects the evaluator implementation. Reaches the evaluator as metric_name.

judgePrompt
string | null
required

As stored. A legacy full-prompt metric ignores it in favour of its own built-in criteria.

evaluationParams
string[]
required
areEvalParamsTop
boolean | null
required

Whether the parameters block precedes the judge prompt. Unset reads as true.

evaluatorModelName
string | null
required

As stored. gatewayModelName is the spelling the LLM gateway receives.

Example:

"GPT-4.1"

gatewayModelName
string | null
required

The model name the judge is called with.

Example:

"gpt-4.1"

judgeGenerationSettings
object | null
required
prompts
object[]
required
createdAt
string<date-time> | null
required