`generateText()`

Generates text and calls tools for a given prompt using a language model.

It is ideal for non-interactive use cases such as automation tasks where you need to write text (e.g. drafting email or summarizing web pages) and for agents that use tools.

import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const { text } = await generateText({
  model: openai('gpt-4o'),
  prompt: 'Invent a new holiday and describe its traditions.',
});

console.log(text);

To see generateText in action, check out these examples.

Import

import { generateText } from "ai"

API Signature

Parameters

model:

LanguageModel

system:

string

prompt:

string

messages:

Array<CoreSystemMessage | CoreUserMessage | CoreAssistantMessage | CoreToolMessage> | Array<UIMessage>

CoreSystemMessage

role:

'system'

content:

string

CoreUserMessage

role:

'user'

content:

string | Array<TextPart | ImagePart | FilePart>

TextPart

type:

'text'

text:

string

ImagePart

type:

'image'

image:

string | Uint8Array | Buffer | ArrayBuffer | URL

mimeType?:

string

FilePart

type:

'file'

data:

string | Uint8Array | Buffer | ArrayBuffer | URL

mimeType:

string

CoreAssistantMessage

role:

'assistant'

content:

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

TextPart

type:

'text'

text:

string

ReasoningPart

type:

'reasoning'

text:

string

signature?:

string

RedactedReasoningPart

type:

'redacted-reasoning'

data:

string

ToolCallPart

type:

'tool-call'

toolCallId:

string

toolName:

string

args:

object based on zod schema

CoreToolMessage

role:

'tool'

content:

Array<ToolResultPart>

ToolResultPart

type:

'tool-result'

toolCallId:

string

toolName:

string

result:

unknown

isError?:

boolean

tools:

ToolSet

Tool

description?:

string

parameters:

Zod Schema | JSON Schema

execute?:

async (parameters: T, options: ToolExecutionOptions) => RESULT

ToolExecutionOptions

toolCallId:

string

messages:

CoreMessage[]

abortSignal:

AbortSignal

toolChoice?:

"auto" | "none" | "required" | { "type": "tool", "toolName": string }

maxTokens?:

number

temperature?:

number

topP?:

number

topK?:

number

presencePenalty?:

number

frequencyPenalty?:

number

stopSequences?:

string[]

seed?:

number

maxRetries?:

number

abortSignal?:

AbortSignal

headers?:

Record<string, string>

maxSteps?:

number

experimental_generateMessageId?:

() => string

experimental_continueSteps?:

boolean

experimental_telemetry?:

TelemetrySettings

isEnabled?:

boolean

recordInputs?:

boolean

recordOutputs?:

boolean

functionId?:

string

metadata?:

providerOptions?:

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

experimental_activeTools?:

Array<TOOLNAME> | undefined

experimental_repairToolCall?:

(options: ToolCallRepairOptions) => Promise<LanguageModelV1FunctionToolCall | null>

ToolCallRepairOptions

system:

string | undefined

messages:

CoreMessage[]

toolCall:

LanguageModelV1FunctionToolCall

tools:

TOOLS

parameterSchema:

(options: { toolName: string }) => JSONSchema7

error:

NoSuchToolError | InvalidToolArgumentsError

experimental_output?:

Output

Output.text():

Output

Output.object():

Output

Options

schema:

Schema<OBJECT>

onStepFinish?:

(result: OnStepFinishResult) => Promise<void> | void

OnStepFinishResult

stepType:

"initial" | "continue" | "tool-result"

finishReason:

usage:

TokenUsage

promptTokens:

number

completionTokens:

number

totalTokens:

number

text:

string

toolCalls:

ToolCall[]

toolResults:

ToolResult[]

warnings:

Warning[] | undefined

response?:

Response

id:

string

model:

string

timestamp:

Date

headers?:

Record<string, string>

body?:

unknown

isContinued:

boolean

providerMetadata?:

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

Returns

text:

string

reasoning:

string | undefined

reasoningDetails:

Array<ReasoningDetail>

ReasoningDetail

type:

'text'

text:

string

signature?:

string

ReasoningDetail

type:

'redacted'

data:

string

sources:

Array<Source>

Source

sourceType:

'url'

id:

string

url:

string

title?:

string

providerMetadata?:

LanguageModelV1ProviderMetadata

files:

Array<GeneratedFile>

GeneratedFile

base64:

string

uint8Array:

Uint8Array

mimeType:

string

toolCalls:

array

toolResults:

array

finishReason:

usage:

CompletionTokenUsage

promptTokens:

number

completionTokens:

number

totalTokens:

number

request?:

RequestMetadata

body:

string

response?:

ResponseMetadata

id:

string

model:

string

timestamp:

Date

headers?:

Record<string, string>

body?:

unknown

messages:

Array<ResponseMessage>

warnings:

Warning[] | undefined

providerMetadata:

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

experimental_output?:

Output

steps:

Array<StepResult>

StepResult

stepType:

"initial" | "continue" | "tool-result"

text:

string

reasoning:

string | undefined

reasoningDetails:

Array<ReasoningDetail>

ReasoningDetail

type:

'text'

text:

string

signature?:

string

ReasoningDetail

type:

'redacted'

data:

string

sources:

Array<Source>

Source

sourceType:

'url'

id:

string

url:

string

title?:

string

providerMetadata?:

LanguageModelV1ProviderMetadata

files:

Array<GeneratedFile>

GeneratedFile

base64:

string

uint8Array:

Uint8Array

mimeType:

string

toolCalls:

array

toolResults:

array

finishReason:

usage:

CompletionTokenUsage

promptTokens:

number

completionTokens:

number

totalTokens:

number

request?:

RequestMetadata

body:

string

response?:

ResponseMetadata

id:

string

model:

string

timestamp:

Date

headers?:

Record<string, string>

body?:

unknown

messages:

Array<ResponseMessage>

warnings:

Warning[] | undefined

isContinued:

boolean

providerMetadata?:

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

Examples

Learn to generate text using a language model in Next.js

Learn to generate a chat completion using a language model in Next.js

Learn to call tools using a language model in Next.js

Learn to render a React component as a tool call using a language model in Next.js

Learn to generate text using a language model in Node.js

Learn to generate chat completions using a language model in Node.js