Evals

Get an eval run

Get an evaluation run by ID.

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

Path parameters

eval_idstring required

The ID of the evaluation to retrieve runs for.

run_idstring required

The ID of the run to retrieve.

Response

The evaluation run

object'eval.run' required

The type of the object. Always "eval.run".

idstring required

Unique identifier for the evaluation run.

eval_idstring required

The identifier of the associated evaluation.

statusstring required

The status of the evaluation run.

modelstring required

The model that is evaluated, if applicable.

namestring required

The name of the evaluation run.

created_atinteger required

Unix timestamp (in seconds) when the evaluation run was created.

report_urlstring uri required

The URL to the rendered evaluation run report on the UI dashboard.

metadataMetadata nullable required

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Changes

Changed in 10 of the 163 revisions of this API.191649

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/sampling_params/tools/items/oneOf[subschema #6: MCP tool]/connector_id deprecated

      response-property-deprecated

    • ●

      added the new gpt-image-2.5-flare enum value to the /////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new gpt-image-2.5-flare-2026-09-08 enum value to the /////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new gpt-image-2.5-sunburst enum value to the /////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new gpt-image-2.5-sunburst-2026-09-08 enum value to the /////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new max enum value to the ////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new xhigh enum value to the ////// response property for the response status

      response-property-enum-value-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property //////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ///////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property / to the response with the status

      response-optional-property-added

    • ●

      added the new gpt-image-2 enum value to the /////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new gpt-image-2-2026-04-21 enum value to the /////// response property for the response status

      response-property-enum-value-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    This revision also has 1 change that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • ab0c5306e3902418See the full diff
    • ▲

      the ////// response property's minLength was decreased from 1 to 0 for the response status

      response-property-min-length-decreased

    • ▲

      added to the //// response property oneOf list for the response status

      response-property-one-of-added

    • ●

      added the new auto enum value to the /////////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new max enum value to the //// response property for the response status

      response-property-enum-value-added

    • ●

      added the new max enum value to the //// response property for the response status

      response-property-enum-value-added

    • ●

      added the new max enum value to the ///////// response property for the response status

      response-property-enum-value-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property //////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property //////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ///////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property ////// to the response with the status

      response-optional-property-added

    This revision also has 2 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 74cbcf73838f17420See the full diff
    • ▲

      response property data_source/oneOf[subschema #2: CompletionsRunDataSource]/source/oneOf[subschema #3: StoredCompletionsRunDataSource]/created_after list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #2: CompletionsRunDataSource]/source/oneOf[subschema #3: StoredCompletionsRunDataSource]/created_before list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #2: CompletionsRunDataSource]/source/oneOf[subschema #3: StoredCompletionsRunDataSource]/limit list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #2: CompletionsRunDataSource]/source/oneOf[subschema #3: StoredCompletionsRunDataSource]/metadata list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #2: CompletionsRunDataSource]/source/oneOf[subschema #3: StoredCompletionsRunDataSource]/model list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/created_after list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/created_before list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/instructions_search list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/metadata list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/model list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/temperature list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/top_p list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property data_source/oneOf[subschema #3: ResponsesRunDataSource]/source/oneOf[subschema #3: EvalResponsesSource]/users list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property metadata list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      added to the /////// response property oneOf list for the response status

      response-property-one-of-added

    • ▲

      added subschema #1: InputMessagesTemplate subschema #2: InputMessagesItemReference to the // response property oneOf list for the response status

      response-property-one-of-added

    • ▲

      the //// response's property type changed from string to no type for status

      response-property-type-changed

    • ●

      removed the optional property //// from the response with the status

      response-optional-property-removed

    • ●

      removed the optional property //// from the response with the status

      response-optional-property-removed

    • ●

      added the new original enum value to the /////////// response property for the response status

      response-property-enum-value-added

    • ●

      added the new responses enum value to the // response property for the response status

      response-property-enum-value-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /////////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /////// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /// to the response with the status

      response-optional-property-added

    • ○

      added the optional property /// to the response with the status

      response-optional-property-added

    • ○

      added the optional property //// to the response with the status

      response-optional-property-added

    • ○

      added subschema #2 to the //// response property anyOf list for the response status

      response-property-any-of-added

    • ○

      the response's property default value changed from completions to responses for the status

      response-property-default-value-changed

    • ○

      the response's property default value medium was removed for the status

      response-property-default-value-removed

    • ○

      added discriminator to ///////// response property for the response status

      response-property-discriminator-added

    • ○

      removed the completions enum value from the // response property for the response status

      response-property-enum-value-removed

    • ○

      removed the high enum value from the //// response property for the response status

      response-property-enum-value-removed

    • ○

      removed the low enum value from the //// response property for the response status

      response-property-enum-value-removed

    • ○

      removed the medium enum value from the //// response property for the response status

      response-property-enum-value-removed

    • ○

      removed subschema #1: Text input subschema #3: Output text from the /////// response property oneOf list for the response status

      response-property-one-of-removed

    • ○

      removed subschema #1 subschema #2 from the // response property oneOf list for the response status

      response-property-one-of-removed

    This revision also has 40 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

    • ○

      endpoint added

      endpoint-added

    This revision also has 18 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog