For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
WebsiteStatusSupportDashboard
DocumentationAPI ReferenceMCPSDKsCLI (new)What's New?
DocumentationAPI ReferenceMCPSDKsCLI (new)What's New?
  • Assistants
    • GETList Assistants
    • POSTCreate Assistant
    • GETGet Assistant
    • DELDelete Assistant
    • PATCHUpdate Assistant
  • Squads
    • GETList Squads
    • POSTCreate Squad
    • GETGet Squad
    • DELDelete Squad
    • PATCHUpdate Squad
  • Calls
    • GETList Calls
    • POSTCreate Call
    • GETGet Call
    • DELDelete Call
    • PATCHUpdate Call
  • Chats
    • GETList Chats
    • POSTCreate Chat
    • GETGet Chat
    • DELDelete Chat
    • POSTCreate Chat (OpenAI Compatible)
  • Campaigns
    • GETList Campaigns
    • POSTCreate Campaign
    • GETGet Campaign
    • DELDelete Campaign
    • PATCHUpdate Campaign
  • Sessions
    • GETList Sessions
    • POSTCreate Session
    • GETGet Session
    • DELDelete Session
    • PATCHUpdate Session
  • Phone Numbers
    • GETList Phone Numbers
    • POSTCreate Phone Number
    • GETList Phone Numbers
    • GETGet Phone Number
    • DELDelete Phone Number
    • PATCHUpdate Phone Number
  • Tools
    • GETList Tools
    • POSTCreate Tool
    • GETGet Tool
    • DELDelete Tool
    • PATCHUpdate Tool
  • Files
    • GETList Files
    • POSTUpload File
    • GETGet File
    • DELDelete File
    • PATCHUpdate File
  • Structured Outputs
    • GETList Structured Outputs
    • POSTCreate Structured Output
    • GETGet Structured Output
    • DELDelete Structured Output
    • PATCHUpdate Structured Output
    • POSTRun Structured Output
  • Insight
    • GETGet Insights
    • POSTCreate Insight
    • GETGet Insight
    • DELDelete Insight
    • PATCHUpdate Insight
    • POSTRun Insight
    • POSTPreview Insight
  • Eval
    • GETList Evals
    • POSTCreate Eval
    • GETGet Eval
    • DELDelete Eval
    • PATCHUpdate Eval
    • GETGet Eval Run
    • DELDelete Eval Run
    • GETList Eval Runs
    • POSTCreate Eval Run
  • Observability Scorecard
    • GETGet Scorecard
    • DELDelete Scorecard
    • PATCHUpdate Scorecard
    • GETList Scorecards
    • POSTCreate Scorecard
  • Provider Resources
    • GETList Provider Resources
    • POSTCreate Provider Resource
    • GETGet Provider Resource
    • DELDelete Provider Resource
    • PATCHUpdate Provider Resource
  • Analytics
    • POSTCreate Analytics Queries
  • Webhooks
    • POSTServer Message
    • POSTClient Message
    • Swagger
    • OpenAPI
LogoLogo
WebsiteStatusSupportDashboard
Eval

Get Eval

GET
https://api.vapi.ai/eval/:id
GET
/eval/:id
$curl https://api.vapi.ai/eval/id \
> -H "Authorization: Bearer <token>" \
> -H "Content-Type: application/json"
200Retrieved
1{
2 "messages": [
3 {
4 "role": "assistant",
5 "content": "Welcome to the verified user flow. How can I assist you today?",
6 "toolCalls": [
7 {
8 "name": "verify_user_status",
9 "arguments": {
10 "userId": "12345"
11 }
12 }
13 ]
14 }
15 ],
16 "id": "a3f1c9e2-7b4d-4f8a-9c3e-2d5f6b7a8c9d",
17 "orgId": "org_987654321",
18 "createdAt": "2024-01-15T09:30:00Z",
19 "updatedAt": "2024-01-15T09:30:00Z",
20 "type": "chat.mockConversation",
21 "name": "Verified User Flow Eval",
22 "description": "This eval checks if the user flow is verified."
23}
Was this page helpful?
Previous

Delete Eval

Next
Built with

Authentication

AuthorizationBearer
See More

Retrieve your API Key from Dashboard.

Path parameters

idstringRequired

Response

messageslist of objects
This is the mock conversation that will be used to evaluate the flow of the conversation. Mock Messages are used to simulate the flow of the conversation Evaluation Messages are used as checkpoints in the flow where the model's response to previous conversation needs to be evaluated to check the content and tool calls
idstring
orgIdstring
createdAtdatetime
updatedAtdatetime
typeenum

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

Allowed values:
namestring1-80 characters
This is the name of the eval. It helps identify what the eval is checking for.
descriptionstring<=500 characters
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.