inference-history
List Inference History
Changed onList inference history for the authenticated user.
Returns all inference records across all model types (NER, classification, JSON extraction, decoder) sorted by most recent first.
get/v1/inferences
Request
- Base URLhttps://api.fastino.ai
- Auth
- API key in header X-API-Key
- or HTTP bearer
- TypeScriptA function with typed inputs. Its response is checked against the schema.
Query parameters
limitinteger
Maximum records to return
offsetinteger
Number of records to skip
model_idstring nullable
Filter by model ID
taskstring nullable
Filter by task type
project_idstring nullable
Filter by project ID
training_job_idstring nullable
Filter by training job ID
latency_minnumber nullable
Minimum latency in ms (must be >= 0).
latency_maxnumber nullable
Maximum latency in ms (must be >= 0).
llmaj_score_minnumber nullable
Minimum LLM-as-Judge score in [0.0, 1.0].
llmaj_score_maxnumber nullable
Maximum LLM-as-Judge score in [0.0, 1.0].
sincestring nullable
Inclusive lower bound on created_at (ISO 8601, UTC).
untilstring nullable
Exclusive upper bound on created_at (ISO 8601, UTC).
Response
Successful Response
Changes
- info
added the optional property
//to the response with the status
- info
- warning
for the
queryrequest parameteroffset, the max was set to10000000.00
- warning