Vapi · Schema

EvalRun

Artificial IntelligenceVoiceAgentsReal-TimeCPaaS

Properties

Name Type Description
status string This is the status of the eval run. When an eval run is created, the status is 'running'. When the eval run is completed, the status is 'ended'.
endedReason string This is the reason for the eval run to end. When the eval run is completed normally i.e end of mock conversation, the status is 'mockConversation.done'. When the eval fails due to an error like Chat e
eval object This is the transient eval that will be run
target object This is the target that will be run against the eval
id string
orgId string
createdAt string
startedAt string
endedAt string
endedMessage string This is the ended message when the eval run ended for any reason apart from mockConversation.done
results array This is the results of the eval or suite run. The array will have a single item for an eval run, and multiple items each corresponding to the an eval in a suite run in the same order as the evals in t
cost number This is the cost of the eval or suite run in USD.
costs array This is the break up of costs of the eval or suite run.
type string This is the type of the run. Currently it is fixed to `eval`.
evalId string This is the id of the eval that will be run.
View JSON Schema on GitHub

JSON Schema

vapi-evalrun-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/EvalRun",
  "title": "EvalRun",
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "description": "This is the status of the eval run. When an eval run is created, the status is 'running'.\nWhen the eval run is completed, the status is 'ended'.",
      "example": "running",
      "enum": [
        "running",
        "ended",
        "queued"
      ]
    },
    "endedReason": {
      "type": "string",
      "description": "This is the reason for the eval run to end.\nWhen the eval run is completed normally i.e end of mock conversation, the status is 'mockConversation.done'.\nWhen the eval fails due to an error like Chat error or incorrect configuration, the status is 'error'.\nWhen the eval runs for too long, due to model issues or tool call issues, the status is 'timeout'.\nWhen the eval run is cancelled by the user, the status is 'cancelled'.\nWhen the eval run is cancelled by Vapi for any reason, the status is 'aborted'.",
      "example": "mockConversation.done",
      "enum": [
        "mockConversation.done",
        "error",
        "timeout",
        "cancelled",
        "aborted"
      ]
    },
    "eval": {
      "description": "This is the transient eval that will be run",
      "oneOf": [
        {
          "$ref": "#/components/schemas/CreateEvalDTO",
          "title": "CreateEvalDTO"
        }
      ],
      "allOf": [
        {
          "$ref": "#/components/schemas/CreateEvalDTO"
        }
      ]
    },
    "target": {
      "description": "This is the target that will be run against the eval",
      "oneOf": [
        {
          "$ref": "#/components/schemas/EvalRunTargetAssistant",
          "title": "EvalRunTargetAssistant"
        },
        {
          "$ref": "#/components/schemas/EvalRunTargetSquad",
          "title": "EvalRunTargetSquad"
        }
      ]
    },
    "id": {
      "type": "string"
    },
    "orgId": {
      "type": "string"
    },
    "createdAt": {
      "format": "date-time",
      "type": "string"
    },
    "startedAt": {
      "format": "date-time",
      "type": "string"
    },
    "endedAt": {
      "format": "date-time",
      "type": "string"
    },
    "endedMessage": {
      "type": "string",
      "description": "This is the ended message when the eval run ended for any reason apart from mockConversation.done",
      "example": "The Assistant returned an error"
    },
    "results": {
      "description": "This is the results of the eval or suite run.\nThe array will have a single item for an eval run, and multiple items each corresponding to the an eval in a suite run in the same order as the evals in the suite.",
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/EvalRunResult"
      }
    },
    "cost": {
      "type": "number",
      "description": "This is the cost of the eval or suite run in USD.",
      "example": 0.01
    },
    "costs": {
      "description": "This is the break up of costs of the eval or suite run.",
      "example": "[{ type: \"model\", model: \"gpt-4o\", cost: 0.01 }]",
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "type": {
      "type": "string",
      "description": "This is the type of the run.\nCurrently it is fixed to `eval`.",
      "example": "eval",
      "enum": [
        "eval"
      ]
    },
    "evalId": {
      "type": "string",
      "description": "This is the id of the eval that will be run.",
      "example": "123e4567-e89b-12d3-a456-426614174000"
    }
  },
  "required": [
    "status",
    "endedReason",
    "target",
    "id",
    "orgId",
    "createdAt",
    "startedAt",
    "endedAt",
    "results",
    "cost",
    "costs",
    "type"
  ]
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/vapi-evalrun"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.