Eval

Create Eval

post/eval

Request body

namestring

This is the name of the eval. It helps identify what the eval is checking for.

descriptionstring

This is the description of the eval. This helps describe the eval and its purpose in detail. It will not be used to evaluate the flow of the conversation.

type'chat.mockConversation' required

This is the type of the eval. Currently it is fixed to chat.mockConversation.

Example request

{
  "messages": [
    {
      "content": "The weather in San Francisco is sunny.",
      "toolCalls": [
        {
          "name": "get_weather"
        }
      ]
    }
  ],
  "name": "Verified User Flow Eval",
  "description": "This eval checks if the user flow is verified.",
  "type": "chat.mockConversation"
}

Response

idstring required
orgIdstring required
createdAtstring date-time required
updatedAtstring date-time required
namestring

This is the name of the eval. It helps identify what the eval is checking for.

descriptionstring

This is the description of the eval. This helps describe the eval and its purpose in detail. It will not be used to evaluate the flow of the conversation.

type'chat.mockConversation' required

This is the type of the eval. Currently it is fixed to chat.mockConversation.

Example response

{
  "messages": [
    {
      "content": "The weather in San Francisco is sunny.",
      "toolCalls": [
        {
          "name": "get_weather"
        }
      ]
    }
  ],
  "name": "Verified User Flow Eval",
  "description": "This eval checks if the user flow is verified.",
  "type": "chat.mockConversation"
}

Changes

Changed in 10 of the 57 revisions of this API.9577

    • added the new gemini-3-flash-preview enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #3: EvalGoogleModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gemini-3-flash-preview enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #3: EvalGoogleModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gemini-3-flash-preview enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #3: EvalGoogleModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gemini-3-flash-preview enum value to the request property messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #3: EvalGoogleModel]/model

      request-property-enum-value-added

    • added the new gemini-3-flash-preview enum value to the request property messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #3: EvalGoogleModel]/model

      request-property-enum-value-added

    • added the new gemini-3-flash-preview enum value to the request property messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #3: EvalGoogleModel]/model

      request-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:germanywestcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:germanywestcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:germanywestcentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:polandcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:polandcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:polandcentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:spaincentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:spaincentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:spaincentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:westeurope enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:westeurope enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-2025-04-14:westeurope enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:germanywestcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:germanywestcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:germanywestcentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:polandcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:polandcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:polandcentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:spaincentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:spaincentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:spaincentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:westeurope enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:westeurope enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4.1-mini-2025-04-14:westeurope enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:germanywestcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:germanywestcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:germanywestcentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:polandcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:polandcentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:polandcentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:spaincentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:spaincentral enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:spaincentral enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:westeurope enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:westeurope enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-4o-2024-11-20:westeurope enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5-chat-latest enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5-chat-latest enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5-chat-latest enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.2 enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.2 enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.2 enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.2-chat-latest enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.2-chat-latest enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.2-chat-latest enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    This revision's changelog hit the recording limit, so it may not list every change to this endpoint.

    • added the new gpt-5.1 enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.1 enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.1 enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.1-chat-latest enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/allOf[AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.1-chat-latest enum value to the messages/items/oneOf[subschema #4: ChatEvalToolResponseMessageEvaluation]/judgePlan/oneOf[subschema #1: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new gpt-5.1-chat-latest enum value to the messages/items/oneOf[subschema #6: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #1: EvalOpenAIModel]/model response property for the response status 201

      response-property-enum-value-added

    This revision's changelog hit the recording limit, so it may not list every change to this endpoint.

  • acbf00c4a7f911See the full diff
    • added ChatEvalToolResponseMessageEvaluation to the messages/items/ response property oneOf list for the response status 201

      response-property-one-of-added

    • added ChatEvalToolResponseMessageEvaluation to the messages/items/ request property oneOf list

      request-property-one-of-added

  • 8474b743bad6112See the full diff
    • the description response property's minLength was decreased from 1 to 0 for the response status 201

      response-property-min-length-decreased

    • added the new claude-haiku-4-5-20251001 enum value to the messages/items/oneOf[subschema #5: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #2: EvalAnthropicModel]/model response property for the response status 201

      response-property-enum-value-added

    • added the new claude-haiku-4-5-20251001 enum value to the request property messages/items/oneOf[subschema #5: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #2: EvalAnthropicModel]/model

      request-property-enum-value-added

    • the description request property's minLength was decreased from 1 to 0

      request-property-min-length-decreased

  • 2b9e82960b2b21See the full diff
    • the messages/items/oneOf[subschema #2: ChatEvalSystemMessageMock]/content response property's maxLength was unset from 100000000 for the response status 201

      response-property-max-length-unset

    • the messages/items/oneOf[subschema #3: ChatEvalToolResponseMessageMock]/content response property's maxLength was unset from 1000 for the response status 201

      response-property-max-length-unset

    • added the new claude-sonnet-4-5-20250929 enum value to the messages/items/oneOf[subschema #5: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #2: EvalAnthropicModel]/model response property for the response status 201

      response-property-enum-value-added

    This revision's changelog hit the recording limit, so it may not list every change to this endpoint.

    This revision also has 3 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

    • removed the enum value claude-sonnet-4-5-20250929 of the request property messages/items/oneOf[subschema #5: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #2: EvalAnthropicModel]/model

      request-property-enum-value-removed

    This revision's changelog hit the recording limit, so it may not list every change to this endpoint.

    • added the new claude-sonnet-4-5-20250929 enum value to the messages/items/oneOf[subschema #5: ChatEvalAssistantMessageEvaluation]/judgePlan/oneOf[subschema #3: AssistantMessageJudgePlanAI]/model/oneOf[subschema #2: EvalAnthropicModel]/model response property for the response status 201

      response-property-enum-value-added

    This revision's changelog hit the recording limit, so it may not list every change to this endpoint.

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

    • added the new required request property messages

      new-required-request-property

    • added the new required request property type

      new-required-request-property

    • removed CreateEvalDTO from the request body oneOf list

      request-body-one-of-removed

    • the request's body type/format changed from / to object/

      request-body-type-changed

    This revision's changelog hit the recording limit, so it may not list every change to this endpoint.

    • endpoint added

      endpoint-added

Of the 57 revisions, 2 have no diff computed and 9 have a changelog that could not be searched.