v1

latestOpenAPI 3.1.02026-07-26142186376.1 KB
Evals

List Evaluation Runs

Retrieve paginated evaluation runs with filtering and sorting options. Filter by agent, team, workflow, model, or evaluation type.

get/eval-runs

Query parameters

agent_idstring nullable

Agent ID

Agent ID

team_idstring nullable

Team ID

Team ID

workflow_idstring nullable

Workflow ID

Workflow ID

model_idstring nullable

Model ID

Model ID

type'agent' | 'team' | 'workflow'

Filter type

limitinteger nullable

Number of eval runs to return

Number of eval runs to return

pageinteger nullable

Page number

Page number

sort_bystring nullable

Field to sort by

Field to sort by

sort_order'asc' | 'desc'

Sort order (asc or desc)

db_idstring nullable

The ID of the database to use

The ID of the database to use

tablestring nullable

The database table to use

The database table to use

eval_typesstring nullable

Comma-separated eval types (accuracy,agent_as_judge,performance,reliability)

Example:accuracy,agent_as_judge,performance,reliability

Comma-separated eval types (accuracy,agent_as_judge,performance,reliability)

Response

Evaluation runs retrieved successfully