workflow/docs/errors/fetch-in-workflow.mdx

Workflow SDK - Build durable, resilient, and observable workflows

---
title: fetch-in-workflow
description: Make HTTP requests from step functions instead of workflow functions.
type: troubleshooting
summary: Resolve the fetch-in-workflow error by moving HTTP requests into a step function.
prerequisites:
  - /docs/foundations/workflows-and-steps
related:
  - /docs/api-reference/workflow/fetch
---

<CopyPrompt
  text="Fix `fetch` usage inside workflow functions. Search workflow files for direct global `fetch(...)` calls and libraries such as AI SDK calls that use fetch. For basic HTTP calls inside a `&quot;use workflow&quot;` function, import `{ fetch }` from `workflow` and replace the global call. For SDK/client calls that need normal Node.js or provider behavior, move the call into a helper function with `&quot;use step&quot;` and call that step from the workflow. Keep all step inputs and outputs serializable. Verify the workflow starts and replays without the fetch-in-workflow error."
/>

This error occurs when you try to use `fetch()` directly in a workflow function, or when a library (like the AI SDK) tries to call `fetch()` under the hood.

## Error message

```text
Global "fetch" is unavailable in workflow functions. Use the "fetch" step function from "workflow" to make HTTP requests.
```

## Why this happens

Workflow functions run in a sandboxed environment without direct access to `fetch()`.

Many libraries make HTTP requests under the hood. For example, the AI SDK's `generateText()` function calls `fetch()` to make HTTP requests to AI providers. When these libraries run inside a workflow function, they fail because the global `fetch` is not available.

## Quick fix

Move the code that makes the request into a step function, and call that step from the workflow. Steps have full Node.js access, so `fetch()` and libraries that call it work as usual.

**Before:**

```typescript lineNumbers title="workflows/ai.ts"
import { generateText } from "ai";

export async function chatWorkflow(prompt: string) {
  "use workflow";

  // Error - generateText() calls fetch() under the hood
  const result = await generateText({ // [!code highlight]
    model: "spacexai/grok-4.6", // [!code highlight]
    prompt, // [!code highlight]
  }); // [!code highlight]

  return result.text;
}
```

**After:**

```typescript lineNumbers title="workflows/ai.ts"
import { generateText } from "ai";

async function generate(prompt: string) {
  "use step"; // [!code highlight]

  // generateText calls fetch() under the hood
  const result = await generateText({
    model: "spacexai/grok-4.6",
    prompt,
  });

  return result.text;
}

export async function chatWorkflow(prompt: string) {
  "use workflow";

  return await generate(prompt); // [!code highlight]
}
```

## Common scenarios

### AI SDK integration

For agents, use AI SDK's [`WorkflowAgent`](https://ai-sdk.dev/v7/docs/agents/workflow-agent#workflowagent) or [`HarnessAgent`](https://ai-sdk.dev/v7/docs/ai-sdk-harnesses/workflow-utilities), which run model calls as steps.

For single AI SDK calls, use a step function as shown above.

### Direct API calls

For simple requests, you can use the `fetch` step function from `workflow` directly:

```typescript lineNumbers
import { fetch } from "workflow";

export async function dataWorkflow() {
  "use workflow";

  // Use fetch directly for HTTP requests
  const response = await fetch("https://api.example.com/data"); // [!code highlight]
  const data = await response.json();

  return data;
}
```

For more details on the `fetch` step function, see the [fetch API reference](/docs/api-reference/workflow/fetch).