Open Responses Provider

The Open Responses 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

pnpm add @ai-sdk/open-responses

Provider Instance

Create an Open Responses provider instance using createOpenResponses:

1
import { createOpenResponses } from '@ai-sdk/open-responses';
2

3
const openResponses = createOpenResponses({
4
  name: 'aProvider',
5
  url: 'http://localhost:1234/v1/responses',
6
});

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<string,string>

  Custom headers to include in the requests.

• fetch (input: RequestInfo, init?: RequestInit) => Promise<Response>

  Custom 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:

1
const model = openResponses('mistralai/ministral-3-14b-reasoning');

You can use Open Responses models with the generateText, streamText, generateObject, and streamObject functions (see AI SDK Core).

Example

1
import { createOpenResponses } from '@ai-sdk/open-responses';
2
import { generateText } from 'ai';
3

4
const openResponses = createOpenResponses({
5
  name: 'aProvider',
6
  url: 'http://localhost:1234/v1/responses',
7
});
8

9
const { text } = await generateText({
10
  model: openResponses('mistralai/ministral-3-14b-reasoning'),
11
  prompt: 'Invent a new holiday and describe its traditions.',
12
});

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.