v1

latestOpenAPI 3.1.0raw.githubusercontent.com2026-06-2682245.2 KB
inference-history

List inference history

Paginated list of past inference records for the authenticated user's team. Supports filtering by model, project, task type, latency range, and LLM-as-Judge score.

get/inferences

Query parameters

limitinteger

Maximum records to return.

offsetinteger

Records to skip for pagination.

model_idstring

Filter by model ID.

project_idstring

Filter by project ID.

training_job_idstring

Filter by training job UUID.

taskstring

Filter by task type (extract_entities, classify_text, extract_json, generate).

latency_minnumber

Minimum latency in ms.

latency_maxnumber

Maximum latency in ms.

llmaj_score_minnumber

Minimum LLM-as-Judge score [0.0, 1.0].

llmaj_score_maxnumber

Maximum LLM-as-Judge score [0.0, 1.0].

sincestring date-time

Return records created at or after this ISO 8601 timestamp.

untilstring date-time

Return records created at or before this ISO 8601 timestamp.

Response

Paginated list of inference records.

totalinteger required

Total matching records (for pagination).

limitinteger required
offsetinteger required