v2
latestOpenAPI 3.1.02026-08-05267431678.1 KBList Inference History
List inference history for the authenticated user.
Returns all inference records across all model types (NER, classification, JSON extraction, decoder) sorted by most recent first.
Args: auth: Authentication result with user_id limit: Maximum number of records to return (default 100, max 500) offset: Number of records to skip for pagination model_id: Optional filter by model ID task: Optional filter by task type project_id: Optional filter by project ID training_job_id: Optional filter by training job ID latency_min/latency_max: Inclusive latency window in ms. llmaj_score_min/llmaj_score_max: Inclusive LLMAJ-score window in [0.0, 1.0]. since: Optional inclusive lower bound on created_at (ISO 8601). until: Optional exclusive upper bound on created_at (ISO 8601).
Returns: InferenceListResponse with paginated inference records.
Raises: HTTPException: 422 when min is greater than its paired max — returning an empty page would silently mask the caller's misordered query.
Query parameters
Maximum records to return
Maximum records to return
Number of records to skip
Number of records to skip
Filter by model ID
Filter by model ID
Filter by task type
Filter by task type
Filter by project ID
Filter by project ID
Filter by training job ID
Filter by training job ID
Minimum latency in ms (must be >= 0).
Minimum latency in ms (must be >= 0).
Maximum latency in ms (must be >= 0).
Maximum latency in ms (must be >= 0).
Minimum LLM-as-Judge score in [0.0, 1.0].
Minimum LLM-as-Judge score in [0.0, 1.0].
Maximum LLM-as-Judge score in [0.0, 1.0].
Maximum LLM-as-Judge score in [0.0, 1.0].
Inclusive lower bound on created_at (ISO 8601, UTC).
Inclusive lower bound on created_at (ISO 8601, UTC).
Exclusive upper bound on created_at (ISO 8601, UTC).
Exclusive upper bound on created_at (ISO 8601, UTC).
Response
Successful Response