Run Structured Output

Authentication

AuthorizationBearer

Retrieve your API Key from [Dashboard](dashboard.vapi.ai).

Request

This endpoint expects an object.

callIdslist of stringsRequired

This is the array of callIds that will be updated with the new structured output value. If preview is true, this array must be provided and contain exactly 1 callId. If preview is false, up to 100 callIds may be provided.

previewEnabledbooleanOptionalDefaults to false

This is the preview flag for the re-run. If true, the re-run will be executed and the response will be returned immediately and the call artifact will NOT be updated. If false (default), the re-run will be executed and the response will be updated in the call artifact.

structuredOutputIdstringOptional

This is the ID of the structured output that will be run. This must be provided unless a transient structured output is provided. When the re-run is executed, only the value of this structured output will be replaced with the new value, or added if not present.

structuredOutputobjectOptional

This is the transient structured output that will be run. This must be provided if a structured output ID is not provided. When the re-run is executed, the structured output value will be added to the existing artifact.

Response

idstring

This is the unique identifier for the structured output.

orgIdstring

This is the unique identifier for the org that this structured output belongs to.

createdAtstringformat: "date-time"

This is the ISO 8601 date-time string of when the structured output was created.

updatedAtstringformat: "date-time"

This is the ISO 8601 date-time string of when the structured output was last updated.

namestring>=1 character<=40 characters

This is the name of the structured output.

schemaobject

This is the JSON Schema definition for the structured output.

Defines the structure and validation rules for the data that will be extracted. Supports all JSON Schema features including:

Objects and nested properties
Arrays and array validation
String, number, boolean, and null types
Enums and const values
Validation constraints (min/max, patterns, etc.)
Composition with allOf, anyOf, oneOf

This is the JSON Schema definition for the structured output. Defines the structure and validation rules for the data that will be extracted. Supports all JSON Schema features including: - Objects and nested properties - Arrays and array validation - String, number, boolean, and null types - Enums and const values - Validation constraints (min/max, patterns, etc.) - Composition with allOf, anyOf, oneOf

modelobject or null

This is the model that will be used to extract the structured output. To provide your own custom system and user prompts for structured output extraction, populate the messages array with your system and user messages. You can specify liquid templating in your system and user messages. Between the system or user messages, you must reference either 'transcript' or 'messages' with the '{{}}' syntax to access the conversation history. Between the system or user messages, you must reference a variation of the structured output with the '{{}}' syntax to access the structured output definition. i.e.: {{structuredOutput}} {{structuredOutput.name}} {{structuredOutput.description}} {{structuredOutput.schema}} If model is not specified, GPT-4.1 will be used by default for extraction, utilizing default system and user prompts. If messages or required fields are not specified, the default system and user prompts will be used.

descriptionstring or null

This is the description of what the structured output extracts. Use this to provide context about what data will be extracted and how it will be used.

assistantIdslist of strings or null

These are the assistant IDs that this structured output is linked to. When linked to assistants, this structured output will be available for extraction during those assistant's calls.

workflowIdslist of strings or null

These are the workflow IDs that this structured output is linked to. When linked to workflows, this structured output will be available for extraction during those workflow's execution.

1	curl -X POST https://api.vapi.ai/structured-output/run \
2	-H "Authorization: Bearer <token>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"callIds": [
6	"string"
7	]
8	}'

1	{
2	"id": "string",
3	"orgId": "string",
4	"createdAt": "2024-01-15T09:30:00Z",
5	"updatedAt": "2024-01-15T09:30:00Z",
6	"name": "string",
7	"schema": {
8	"type": "string",
9	"items": {},
10	"properties": {},
11	"description": "string",
12	"pattern": "string",
13	"format": "date-time",
14	"required": [
15	"string"
16	],
17	"enum": [
18	"string"
19	],
20	"title": "string"
21	},
22	"model": {
23	"provider": "openai",
24	"model": "gpt-5",
25	"temperature": 1.1,
26	"maxTokens": 5030
27	},
28	"description": "string",
29	"assistantIds": [
30	"string"
31	],
32	"workflowIds": [
33	"string"
34	]
35	}