📄 ai-sdk/cookbook/node/stream-object-record-final-object

File: stream-object-record-final-object.md | Updated: 11/15/2025

Source: https://ai-sdk.dev/cookbook/node/stream-object-record-final-object

AI SDK

Menu

Guides

RAG Agent

Multi-Modal Agent

Slackbot Agent Guide

Natural Language Postgres

Get started with Computer Use

Get started with Gemini 2.5

Get started with Claude 4

OpenAI Responses API

Google Gemini Image Generation

Get started with Claude 3.7 Sonnet

Get started with Llama 3.1

Get started with GPT-5

Get started with OpenAI o1

Get started with OpenAI o3-mini

Get started with DeepSeek R1

Next.js

Generate Text

Generate Text with Chat Prompt

Generate Image with Chat Prompt

Stream Text

Stream Text with Chat Prompt

Stream Text with Image Prompt

Chat with PDFs

streamText Multi-Step Cookbook

Markdown Chatbot with Memoization

Generate Object

Generate Object with File Prompt through Form Submission

Stream Object

Call Tools

Call Tools in Multiple Steps

Model Context Protocol (MCP) Tools

Share useChat State Across Components

Human-in-the-Loop Agent with Next.js

Send Custom Body from useChat

Render Visual Interface in Chat

Caching Middleware

Node

Generate Text

Generate Text with Chat Prompt

Generate Text with Image Prompt

Stream Text

Stream Text with Chat Prompt

Stream Text with Image Prompt

Stream Text with File Prompt

Generate Object with a Reasoning Model

Generate Object

Stream Object

Stream Object with Image Prompt

Record Token Usage After Streaming Object

Record Final Object after Streaming Object

Call Tools

Call Tools with Image Prompt

Call Tools in Multiple Steps

Model Context Protocol (MCP) Tools

Manual Agent Loop

Web Search Agent

Embed Text

Embed Text in Batch

Intercepting Fetch Requests

Local Caching Middleware

Retrieval Augmented Generation

Knowledge Base Agent

API Servers

Node.js HTTP Server

Express

Hono

Fastify

Nest.js

React Server Components

Copy markdown

Record Final Object after Streaming Object

============================================================================================================================================================

When you're streaming structured data, you may want to record the final object for logging or other purposes.

onFinish Callback


You can use the onFinish callback to record the final object. It is called when the stream is finished.

The object parameter contains the final object, or undefined if the type validation fails. There is also an error parameter that contains error when e.g. the object does not match the schema.

import { openai } from '@ai-sdk/openai';import { streamObject } from 'ai';import { z } from 'zod';
const result = streamObject({  model: openai('gpt-4.1'),  schema: z.object({    recipe: z.object({      name: z.string(),      ingredients: z.array(z.string()),      steps: z.array(z.string()),    }),  }),  prompt: 'Generate a lasagna recipe.',  onFinish({ object, error }) {    // handle type validation failure (when the object does not match the schema):    if (object === undefined) {      console.error('Error:', error);      return;    }
    console.log('Final object:', JSON.stringify(object, null, 2));  },});

object Promise


The streamObject result contains an object promise that resolves to the final object. The object is fully typed. When the type validation according to the schema fails, the promise will be rejected with a TypeValidationError.

import { openai } from '@ai-sdk/openai';import { streamObject } from 'ai';import { z } from 'zod';
const result = streamObject({  model: openai('gpt-4.1'),  schema: z.object({    recipe: z.object({      name: z.string(),      ingredients: z.array(z.string()),      steps: z.array(z.string()),    }),  }),  prompt: 'Generate a lasagna recipe.',});
result.object  .then(({ recipe }) => {    // do something with the fully typed, final object:    console.log('Recipe:', JSON.stringify(recipe, null, 2));  })  .catch(error => {    // handle type validation failure    // (when the object does not match the schema):    console.error(error);  });
// note: the stream needs to be consumed because of backpressurefor await (const partialObject of result.partialObjectStream) {}

On this page

Record Final Object after Streaming Object

onFinish Callback

object Promise

Deploy and Scale AI Apps with Vercel.

Vercel delivers the infrastructure and developer experience you need to ship reliable AI-powered applications at scale.

Trusted by industry leaders:

  • OpenAI
  • Photoroom
  • leonardo-ai Logoleonardo-ai Logo
  • zapier Logozapier Logo

Talk to an expert