Node

Record Token Usage After Streaming Object

Learn how to record token usage when streaming structured data using the AI SDK and Node

When you're streaming structured data with streamText and Output, you may want to record the token usage for billing purposes.

`onEnd` Callback

You can use the onEnd callback to record token usage. It is called when the stream is finished.

index.ts

import { streamText, Output } from 'ai';
import { z } from 'zod';

const result = streamText({
  model: 'openai/gpt-6-astra',
  output: Output.object({
    schema: z.object({
      recipe: z.object({
        name: z.string(),
        ingredients: z.array(z.string()),
        steps: z.array(z.string()),
      }),
    }),
  }),
  prompt: 'Generate a lasagna recipe.',
  onEnd({ usage }) {
    console.log('Token usage:', usage);
  },
});

`usage` Promise

The streamText result contains a usage promise that resolves to the total token usage.

index.ts

import { streamText, Output, LanguageModelUsage } from 'ai';
import { z } from 'zod';

const result = streamText({
  model: 'openai/gpt-6-astra',
  output: Output.object({
    schema: z.object({
      recipe: z.object({
        name: z.string(),
        ingredients: z.array(z.string()),
        steps: z.array(z.string()),
      }),
    }),
  }),
  prompt: 'Generate a lasagna recipe.',
});

function recordUsage({
  inputTokens,
  outputTokens,
  totalTokens,
}: LanguageModelUsage) {
  console.log('Prompt tokens:', inputTokens);
  console.log('Completion tokens:', outputTokens);
  console.log('Total tokens:', totalTokens);
}

// use as promise:
result.usage.then(recordUsage);

// or use with async/await:
recordUsage(await result.usage);

for await (const partialObject of result.partialOutputStream) {
}

PreviousStream Object with Image Prompt NextRecord Final Object after Streaming Object