Changes to Get an eval run

GET /evals/{eval_id}/runs/{run_id}

Every recorded change to this endpoint, newest first. Back to the operation

Changed in 4 of the 31 revisions of this API.1724

  1. e0508a503b84418
  2. 827fa3e74ce91
  3. 737fbb7f6f1734
  4. 1b5c6501b84711

What changed

  • e0508a503b84418See the full diff
    • added the new auto enum value to the data_source/anyOf[subschema #2: CompletionsRunDataSource]/input_messages/anyOf[subschema #1: TemplateInputMessages]/template/items/anyOf[subschema #1: Input message]/content/anyOf[subschema #2: Input item content list]/items/anyOf[subschema #3: Input file]/detail response property for the response status 200

      response-property-enum-value-added

    • added the new max enum value to the data_source/anyOf[subschema #2: CompletionsRunDataSource]/sampling_params/reasoning_effort/anyOf[subschema #1]/ response property for the response status 200

      response-property-enum-value-added

    • added the new max enum value to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/reasoning_effort/anyOf[subschema #1]/ response property for the response status 200

      response-property-enum-value-added

    • added the new max enum value to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/source/anyOf[subschema #3: EvalResponsesSource]/reasoning_effort/anyOf[ReasoningEffort]/anyOf[subschema #1]/ response property for the response status 200

      response-property-enum-value-added

    • added the optional property data_source/anyOf[subschema #2: CompletionsRunDataSource]/input_messages/anyOf[subschema #1: TemplateInputMessages]/template/items/anyOf[subschema #1: Input message]/content/anyOf[subschema #2: Input item content list]/items/anyOf[subschema #1: Input text]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #2: CompletionsRunDataSource]/input_messages/anyOf[subschema #1: TemplateInputMessages]/template/items/anyOf[subschema #1: Input message]/content/anyOf[subschema #2: Input item content list]/items/anyOf[subschema #2: Input image]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #2: CompletionsRunDataSource]/input_messages/anyOf[subschema #1: TemplateInputMessages]/template/items/anyOf[subschema #1: Input message]/content/anyOf[subschema #2: Input item content list]/items/anyOf[subschema #3: Input file]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #2: CompletionsRunDataSource]/input_messages/anyOf[subschema #1: TemplateInputMessages]/template/items/anyOf[subschema #2: EvalItem]/content/anyOf[subschema #1: Eval content item]/anyOf[subschema #2: Input text]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #2: CompletionsRunDataSource]/input_messages/anyOf[subschema #1: TemplateInputMessages]/template/items/anyOf[subschema #2: EvalItem]/content/anyOf[subschema #2: An array of Input text Output text Input image and Input audio]/items/anyOf[subschema #2: Input text]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/input_messages/anyOf[subschema #1: InputMessagesTemplate]/template/items/anyOf[subschema #2: EvalItem]/content/anyOf[subschema #1: Eval content item]/anyOf[subschema #2: Input text]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/input_messages/anyOf[subschema #1: InputMessagesTemplate]/template/items/anyOf[subschema #2: EvalItem]/content/anyOf[subschema #2: An array of Input text Output text Input image and Input audio]/items/anyOf[subschema #2: Input text]/prompt_cache_breakpoint to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #10: Shell tool -> subschema #11: Shell tool]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #11: Custom tool -> subschema #12: Custom tool]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #12: Namespace -> subschema #13: Namespace]/tools/items/anyOf[FunctionToolParam]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #12: Namespace -> subschema #13: Namespace]/tools/items/anyOf[FunctionToolParam]/output_schema to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #12: Namespace -> subschema #13: Namespace]/tools/items/anyOf[subschema #2: Custom tool]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #15: Apply patch tool -> subschema #16: Apply patch tool]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #1: Function]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #1: Function]/output_schema to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #6: MCP tool]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #7: Code interpreter]/allowed_callers to the response with the 200 status

      response-optional-property-added

    • added ProgrammaticToolCallingParam to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/ response property anyOf list for the response status 200

      response-property-any-of-added

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

    • added the optional property data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #6: MCP tool]/tunnel_id to the response with the 200 status

      response-optional-property-added

    • added the new chatgpt-image-latest enum value to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/model/anyOf[subschema #2]/ response property for the response status 200

      response-property-enum-value-added

    • added the new gpt-image-2 enum value to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/model/anyOf[subschema #2]/ response property for the response status 200

      response-property-enum-value-added

    • added the new gpt-image-2-2026-04-21 enum value to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/model/anyOf[subschema #2]/ response property for the response status 200

      response-property-enum-value-added

    • removed the 1024x1024 enum value from the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/size response property for the response status 200

      response-property-enum-value-removed

    • removed the 1024x1536 enum value from the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/size response property for the response status 200

      response-property-enum-value-removed

    • removed the 1536x1024 enum value from the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/size response property for the response status 200

      response-property-enum-value-removed

    • removed the auto enum value from the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/size response property for the response status 200

      response-property-enum-value-removed

    • the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/size response's property type/format changed from string/ to / for status 200

      response-property-type-changed

    • added subschema #1 subschema #2 to the data_source/anyOf[subschema #3: CreateEvalResponsesRunDataSource]/sampling_params/tools/items/anyOf[subschema #8: Image generation tool]/size response property anyOf list for the response status 200

      response-property-any-of-added