@ai-sdk/open-responses/docs/06-open-responses.mdx

The **[Open Responses provider](https://ai-sdk.dev/providers/ai-sdk-providers/open-responses)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for [Open Responses](https://www.openresponses.org/) compatible APIs.

---
title: Open Responses
description: Learn how to use the Open Responses provider for the AI SDK.
---

# Open Responses Provider

The [Open Responses](https://www.openresponses.org/) provider contains language model support for Open Responses compatible APIs.

## Setup

The Open Responses provider is available in the `@ai-sdk/open-responses` module. You can install it with

<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
  <Tab>
    <Snippet text="pnpm add @ai-sdk/open-responses" dark />
  </Tab>
  <Tab>
    <Snippet text="npm install @ai-sdk/open-responses" dark />
  </Tab>
  <Tab>
    <Snippet text="yarn add @ai-sdk/open-responses" dark />
  </Tab>
  <Tab>
    <Snippet text="bun add @ai-sdk/open-responses" dark />
  </Tab>
</Tabs>

## Provider Instance

Create an Open Responses provider instance using `createOpenResponses`:

```ts
import { createOpenResponses } from '@ai-sdk/open-responses';

const openResponses = createOpenResponses({
  name: 'aProvider',
  url: 'http://localhost:1234/v1/responses',
});
```

The `name` and `url` options are required:

- **name** _string_

  Provider name. Used as the key for provider options and metadata.

- **url** _string_

  URL for the Open Responses API POST endpoint.

You can use the following optional settings to customize the Open Responses provider instance:

- **apiKey** _string_

  API key that is being sent using the `Authorization` header.

- **headers** _Record&lt;string,string&gt;_

  Custom headers to include in the requests.

- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_

  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
  Defaults to the global `fetch` function.

## Language Models

The Open Responses provider instance is a function that you can invoke to create a language model:

```ts
const model = openResponses('mistralai/ministral-3-14b-reasoning');
```

You can use Open Responses models with the `generateText` and `streamText` functions,
and they support structured data generation with [`Output`](/docs/reference/ai-sdk-core/output)
(see [AI SDK Core](/docs/ai-sdk-core)).

### Example

```ts
import { createOpenResponses } from '@ai-sdk/open-responses';
import { generateText } from 'ai';

const openResponses = createOpenResponses({
  name: 'aProvider',
  url: 'http://localhost:1234/v1/responses',
});

const { text } = await generateText({
  model: openResponses('mistralai/ministral-3-14b-reasoning'),
  prompt: 'Invent a new holiday and describe its traditions.',
});
```

## Notes

- Stop sequences, `topK`, and `seed` are not supported and are ignored with warnings.
- Image inputs are supported for user messages with `file` parts using image media types.