Sign in
OpenAI Evals API - Runs

Get Run

Get a specific run by ID.

Model-based routing (for multi-account support):

  • Pass model via header: x-litellm-model: gpt-4-account-1
  • Pass model via query: ?model=gpt-4-account-1

Example usage:

curl "http://localhost:4000/v1/evals/eval_123/runs/run_456"       -H "Authorization: Bearer your-key"

Returns: Run object with full details

get/v1/evals/{eval_id}/runs/{run_id}

Path parameters

eval_idstring required
run_idstring required

Query parameters

custom_llm_providerstring nullable

Response

Successful Response

idstring required
objectstring
created_atinteger required
status'queued' | 'running' | 'completed' | 'failed' | 'cancelled' required
data_sourceobject required
eval_idstring required
namestring nullable
started_atinteger nullable
completed_atinteger nullable
modelstring nullable
{"stackTrail":"components:schemas:Run:properties:per_model_usage:anyOf","oasType":"schema","type":"unknown","title":"Per Model Usage","nullable":true}
report_urlstring nullable
result_countsobject nullable
shared_with_openaiboolean nullable
metadataobject nullable
errorobject nullable