ai/docs/07-reference/01-ai-sdk-core/70-is-step-count.mdx

AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.

---
title: isStepCount
description: API Reference for isStepCount.
---

# `isStepCount()`

Creates a stop condition that stops when the number of completed steps equals a specified count.

This function is used with `stopWhen` in `generateText` and `streamText` to control when a tool-calling loop should stop based on the number of steps executed.

```ts
import { generateText, isStepCount } from 'ai';
__PROVIDER_IMPORT__;

const result = await generateText({
  model: __MODEL__,
  tools: {
    // your tools
  },
  // Stop after 5 steps
  stopWhen: isStepCount(5),
});
```

## Import

<Snippet text={`import { isStepCount } from "ai"`} prompt={false} />

## API Signature

### Parameters

<PropertiesTable
  content={[
    {
      name: 'stepCount',
      type: 'number',
      description:
        'The number of completed steps that should trigger the stop condition.',
    },
  ]}
/>

### Returns

A `StopCondition` function that returns `true` when the number of completed steps equals the specified number. The function can be used with the `stopWhen` parameter in `generateText` and `streamText`.

## Examples

### Basic Usage

Stop after 3 steps:

```ts
import { generateText, isStepCount } from 'ai';

const result = await generateText({
  model: yourModel,
  tools: yourTools,
  stopWhen: isStepCount(3),
});
```

### Combining with Other Conditions

You can combine multiple stop conditions in an array:

```ts
import { generateText, isStepCount, hasToolCall } from 'ai';

const result = await generateText({
  model: yourModel,
  tools: yourTools,
  // Stop after 10 steps OR when finalAnswer tool is called
  stopWhen: [isStepCount(10), hasToolCall('finalAnswer')],
});
```

## See also

- [`hasToolCall()`](/docs/reference/ai-sdk-core/has-tool-call)
- [`generateText()`](/docs/reference/ai-sdk-core/generate-text)
- [`streamText()`](/docs/reference/ai-sdk-core/stream-text)