`generateObject()`

Generates a typed, structured object for a given prompt and schema using a language model.

It can be used to force the language model to return structured data, e.g. for information extraction, synthetic data generation, or classification tasks.

Example: generate an object using a schema

import { generateObject } from 'ai';
import { z } from 'zod';

const { object } = await generateObject({
  model: "anthropic/claude-sonnet-4.5",
  schema: z.object({
    recipe: z.object({
      name: z.string(),
      ingredients: z.array(z.string()),
      steps: z.array(z.string()),
    }),
  }),
  prompt: 'Generate a lasagna recipe.',
});

console.log(JSON.stringify(object, null, 2));

Example: generate an array using a schema

For arrays, you specify the schema of the array items.

import { generateObject } from 'ai';
import { z } from 'zod';

const { object } = await generateObject({
  model: "anthropic/claude-sonnet-4.5",
  output: 'array',
  schema: z.object({
    name: z.string(),
    class: z
      .string()
      .describe('Character class, e.g. warrior, mage, or thief.'),
    description: z.string(),
  }),
  prompt: 'Generate 3 hero descriptions for a fantasy role playing game.',
});

Example: generate an enum

When you want to generate a specific enum value, you can set the output strategy to enum and provide the list of possible values in the enum parameter.

import { generateObject } from 'ai';

const { object } = await generateObject({
  model: "anthropic/claude-sonnet-4.5",
  output: 'enum',
  enum: ['action', 'comedy', 'drama', 'horror', 'sci-fi'],
  prompt:
    'Classify the genre of this movie plot: ' +
    '"A group of astronauts travel through a wormhole in search of a ' +
    'new habitable planet for humanity."',
});

Example: generate JSON without a schema

import { generateObject } from 'ai';

const { object } = await generateObject({
  model: "anthropic/claude-sonnet-4.5",
  output: 'no-schema',
  prompt: 'Generate a lasagna recipe.',
});

To see generateObject in action, check out the additional examples.

Import

import { generateObject } from "ai"

API Signature

Parameters

model:

LanguageModel

output:

'object' | 'array' | 'enum' | 'no-schema' | undefined

schema:

Zod Schema | JSON Schema

schemaName:

string | undefined

schemaDescription:

string | undefined

enum:

string[]

system:

string

prompt:

string | Array<SystemModelMessage | UserModelMessage | AssistantModelMessage | ToolModelMessage>

messages:

Array<SystemModelMessage | UserModelMessage | AssistantModelMessage | ToolModelMessage>

SystemModelMessage

role:

'system'

content:

string

UserModelMessage

role:

'user'

content:

string | Array<TextPart | ImagePart | FilePart>

TextPart

type:

'text'

text:

string

ImagePart

type:

'image'

image:

string | Uint8Array | Buffer | ArrayBuffer | URL

mediaType?:

string

FilePart

type:

'file'

data:

string | Uint8Array | Buffer | ArrayBuffer | URL

mediaType:

string

AssistantModelMessage

role:

'assistant'

content:

string | Array<TextPart | FilePart | ReasoningPart | ToolCallPart>

TextPart

type:

'text'

text:

string

ReasoningPart

type:

'reasoning'

text:

string

FilePart

type:

'file'

data:

string | Uint8Array | Buffer | ArrayBuffer | URL

mediaType:

string

filename?:

string

ToolCallPart

type:

'tool-call'

toolCallId:

string

toolName:

string

args:

object based on zod schema

ToolModelMessage

role:

'tool'

content:

Array<ToolResultPart>

ToolResultPart

type:

'tool-result'

toolCallId:

string

toolName:

string

result:

unknown

isError?:

boolean

maxOutputTokens?:

number

temperature?:

number

topP?:

number

topK?:

number

presencePenalty?:

number

frequencyPenalty?:

number

seed?:

number

maxRetries?:

number

abortSignal?:

AbortSignal

headers?:

Record<string, string>

experimental_repairText?:

(options: RepairTextOptions) => Promise<string>

RepairTextOptions

text:

string

error:

JSONParseError | TypeValidationError

experimental_download?:

(requestedDownloads: Array<{ url: URL; isUrlSupportedByModel: boolean }>) => Promise<Array<null | { data: Uint8Array; mediaType?: string }>>

experimental_telemetry?:

TelemetrySettings

isEnabled?:

boolean

recordInputs?:

boolean

recordOutputs?:

boolean

functionId?:

string

metadata?:

providerOptions?:

Record<string,Record<string,JSONValue>> | undefined

Returns

object:

based on the schema

finishReason:

usage:

LanguageModelUsage

inputTokens:

number | undefined

outputTokens:

number | undefined

totalTokens:

number | undefined

reasoningTokens?:

number | undefined

cachedInputTokens?:

number | undefined

request?:

LanguageModelRequestMetadata

body:

string

response?:

LanguageModelResponseMetadata

id:

string

modelId:

string

timestamp:

Date

headers?:

Record<string, string>

body?:

unknown

reasoning:

string | undefined

warnings:

CallWarning[] | undefined

providerMetadata:

ProviderMetadata | undefined

toJsonResponse:

(init?: ResponseInit) => Response

More Examples

Learn to generate structured data using a language model in Next.js

Learn to generate structured data using a language model in Node.js