# OpenAI Provider

The [OpenAI](https://openai.com/) provider contains language model support for the OpenAI responses, chat, and completion APIs, as well as embedding model support for the OpenAI embeddings API.

## Setup

The OpenAI provider is available in the `@ai-sdk/openai` module. You can install it with

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

## Provider Instance

You can import the default provider instance `openai` from `@ai-sdk/openai`:

```ts
import { openai } from '@ai-sdk/openai';
```

If you need a customized setup, you can import `createOpenAI` from `@ai-sdk/openai` and create a provider instance with your settings:

```ts
import { createOpenAI } from '@ai-sdk/openai';

const openai = createOpenAI({
  // custom settings, e.g.
  compatibility: 'strict', // strict mode, enable when using the OpenAI API
});
```

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

- **baseURL** _string_

  Use a different URL prefix for API calls, e.g. to use proxy servers.
  The default prefix is `https://api.openai.com/v1`.

- **apiKey** _string_

  API key that is being sent using the `Authorization` header.
  It defaults to the `OPENAI_API_KEY` environment variable.

- **name** _string_

  The provider name. You can set this when using OpenAI compatible providers
  to change the model provider property. Defaults to `openai`.

- **organization** _string_

  OpenAI Organization.

- **project** _string_

  OpenAI project.

- **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.
  You can use it as a middleware to intercept requests,
  or to provide a custom fetch implementation for e.g. testing.

- **compatibility** _"strict" | "compatible"_

  OpenAI compatibility mode. Should be set to `strict` when using the OpenAI API,
  and `compatible` when using 3rd party providers. In `compatible` mode, newer
  information such as `streamOptions` are not being sent, resulting in `NaN`
  token usage. Defaults to 'compatible'.

## Language Models

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

```ts
const model = openai('gpt-4-turbo');
```

It automatically selects the correct API based on the model id.
You can also pass additional settings in the second argument:

```ts
const model = openai('gpt-4-turbo', {
  // additional settings
});
```

The available options depend on the API that's automatically chosen for the model (see below).
If you want to explicitly select a specific model API, you can use `.chat` or `.completion`.

### Example

You can use OpenAI language models to generate text with the `generateText` function:

```ts
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const { text } = await generateText({
  model: openai('gpt-4-turbo'),
  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
});
```

OpenAI language models can also be used in the `streamText`, `generateObject`, and `streamObject` functions
(see [AI SDK Core](/docs/ai-sdk-core)).

### Chat Models

You can create models that call the [OpenAI chat API](https://platform.openai.com/docs/api-reference/chat) using the `.chat()` factory method.
The first argument is the model id, e.g. `gpt-4`.
The OpenAI chat models support tool calls and some have multi-modal capabilities.

```ts
const model = openai.chat('gpt-3.5-turbo');
```

OpenAI chat models support also some model specific settings that are not part of the [standard call settings](/docs/ai-sdk-core/settings).
You can pass them as an options argument:

```ts
const model = openai.chat('gpt-3.5-turbo', {
  logitBias: {
    // optional likelihood for specific tokens
    '50256': -100,
  },
  user: 'test-user', // optional unique user identifier
});
```

The following optional settings are available for OpenAI chat models:

- **logitBias** _Record&lt;number, number&gt;_

  Modifies the likelihood of specified tokens appearing in the completion.

  Accepts a JSON object that maps tokens (specified by their token ID in
  the GPT tokenizer) to an associated bias value from -100 to 100. You
  can use this tokenizer tool to convert text to token IDs. Mathematically,
  the bias is added to the logits generated by the model prior to sampling.
  The exact effect will vary per model, but values between -1 and 1 should
  decrease or increase likelihood of selection; values like -100 or 100
  should result in a ban or exclusive selection of the relevant token.

  As an example, you can pass `{"50256": -100}` to prevent the token from being generated.

- **logprobs** _boolean | number_

  Return the log probabilities of the tokens. Including logprobs will increase
  the response size and can slow down response times. However, it can
  be useful to better understand how the model is behaving.

  Setting to true will return the log probabilities of the tokens that
  were generated.

  Setting to a number will return the log probabilities of the top n
  tokens that were generated.

- **parallelToolCalls** _boolean_

  Whether to enable parallel function calling during tool use. Defaults to `true`.

- **useLegacyFunctionCalls** _boolean_

  Whether to use legacy function calling. Defaults to false.

  Required by some open source inference engines which do not support the `tools` API. May also
  provide a workaround for `parallelToolCalls` resulting in the provider buffering tool calls,
  which causes `streamObject` to be non-streaming.

  Prefer setting `parallelToolCalls: false` over this option.

- **structuredOutputs** _boolean_

  Whether to use [structured outputs](#structured-outputs).
  Defaults to `false` for normal models, and `true` for reasoning models.

  When enabled, tool calls and object generation will be strict and follow the provided schema.

- **user** _string_

  A unique identifier representing your end-user, which can help OpenAI to
  monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).

- **downloadImages** _boolean_

  Automatically download images and pass the image as data to the model.
  OpenAI supports image URLs for public models, so this is only needed for
  private models or when the images are not publicly accessible.
  Defaults to `false`.

- **simulateStreaming** _boolean_

  Simulates streaming by using a normal generate call and returning it as a stream.
  Enable this if the model that you are using does not support streaming.
  Defaults to `false`.

- **reasoningEffort** _'low' | 'medium' | 'high'_

  Reasoning effort for reasoning models. Defaults to `medium`. If you use
  `providerOptions` to set the `reasoningEffort` option, this
  model setting will be ignored.

#### Reasoning

OpenAI has introduced the `o1`,`o3`, and `o4` series of [reasoning models](https://platform.openai.com/docs/guides/reasoning).
Currently, `o4-mini`, `o3`, `o3-mini`, `o1`, `o1-mini`, and `o1-preview` are available.

Reasoning models currently only generate text, have several limitations, and are only supported using `generateText` and `streamText`.

They support additional settings and response metadata:

- You can use `providerOptions` to set

  - the `reasoningEffort` option (or alternatively the `reasoningEffort` model setting), which determines the amount of reasoning the model performs.

- You can use response `providerMetadata` to access the number of reasoning tokens that the model generated.

```ts highlight="4,7-11,17"
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const { text, usage, providerMetadata } = await generateText({
  model: openai('o3-mini'),
  prompt: 'Invent a new holiday and describe its traditions.',
  providerOptions: {
    openai: {
      reasoningEffort: 'low',
    },
  },
});

console.log(text);
console.log('Usage:', {
  ...usage,
  reasoningTokens: providerMetadata?.openai?.reasoningTokens,
});
```

<Note>
  System messages are automatically converted to OpenAI developer messages for
  reasoning models when supported. For models that do not support developer
  messages, such as `o1-preview`, system messages are removed and a warning is
  added.
</Note>

<Note>
  Reasoning models like `o1-mini` and `o1-preview` require additional runtime
  inference to complete their reasoning phase before generating a response. This
  introduces longer latency compared to other models, with `o1-preview`
  exhibiting significantly more inference time than `o1-mini`.
</Note>

<Note>
  `maxTokens` is automatically mapped to `max_completion_tokens` for reasoning
  models.
</Note>

#### Structured Outputs

You can enable [OpenAI structured outputs](https://openai.com/index/introducing-structured-outputs-in-the-api/) by setting the `structuredOutputs` option to `true`.
Structured outputs are a form of grammar-guided generation.
The JSON schema is used as a grammar and the outputs will always conform to the schema.

```ts highlight="7"
import { openai } from '@ai-sdk/openai';
import { generateObject } from 'ai';
import { z } from 'zod';

const result = await generateObject({
  model: openai('gpt-4o-2024-08-06', {
    structuredOutputs: true,
  }),
  schemaName: 'recipe',
  schemaDescription: 'A recipe for lasagna.',
  schema: z.object({
    name: z.string(),
    ingredients: z.array(
      z.object({
        name: z.string(),
        amount: z.string(),
      }),
    ),
    steps: z.array(z.string()),
  }),
  prompt: 'Generate a lasagna recipe.',
});

console.log(JSON.stringify(result.object, null, 2));
```

<Note type="warning">
  OpenAI structured outputs have several
  [limitations](https://openai.com/index/introducing-structured-outputs-in-the-api),
  in particular around the [supported schemas](https://platform.openai.com/docs/guides/structured-outputs/supported-schemas),
  and are therefore opt-in.

For example, optional schema properties are not supported.
You need to change Zod `.nullish()` and `.optional()` to `.nullable()`.

</Note>

#### PDF support

The OpenAI Chat API supports reading PDF files.
You can pass PDF files as part of the message content using the `file` type:

```ts
const result = await generateText({
  model: openai('gpt-4o'),
  messages: [
    {
      role: 'user',
      content: [
        {
          type: 'text',
          text: 'What is an embedding model?',
        },
        {
          type: 'file',
          data: fs.readFileSync('./data/ai.pdf'),
          mimeType: 'application/pdf',
          filename: 'ai.pdf', // optional
        },
      ],
    },
  ],
});
```

The model will have access to the contents of the PDF file and
respond to questions about it.
The PDF file should be passed using the `data` field,
and the `mimeType` should be set to `'application/pdf'`.

#### Predicted Outputs

OpenAI supports [predicted outputs](https://platform.openai.com/docs/guides/latency-optimization#use-predicted-outputs) for `gpt-4o` and `gpt-4o-mini`.
Predicted outputs help you reduce latency by allowing you to specify a base text that the model should modify.
You can enable predicted outputs by adding the `prediction` option to the `providerOptions.openai` object:

```ts highlight="15-18"
const result = streamText({
  model: openai('gpt-4o'),
  messages: [
    {
      role: 'user',
      content: 'Replace the Username property with an Email property.',
    },
    {
      role: 'user',
      content: existingCode,
    },
  ],
  providerOptions: {
    openai: {
      prediction: {
        type: 'content',
        content: existingCode,
      },
    },
  },
});
```

OpenAI provides usage information for predicted outputs (`acceptedPredictionTokens` and `rejectedPredictionTokens`).
You can access it in the `providerMetadata` object.

```ts highlight="11"
const openaiMetadata = (await result.providerMetadata)?.openai;

const acceptedPredictionTokens = openaiMetadata?.acceptedPredictionTokens;
const rejectedPredictionTokens = openaiMetadata?.rejectedPredictionTokens;
```

<Note type="warning">
  OpenAI Predicted Outputs have several
  [limitations](https://platform.openai.com/docs/guides/predicted-outputs#limitations),
  e.g. unsupported API parameters and no tool calling support.
</Note>

#### Image Detail

You can use the `openai` provider option to set the [image input detail](https://platform.openai.com/docs/guides/images-vision?api-mode=responses#specify-image-input-detail-level) to `high`, `low`, or `auto`:

```ts highlight="13-16"
const result = await generateText({
  model: openai('gpt-4o'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Describe the image in detail.' },
        {
          type: 'image',
          image:
            'https://github.com/vercel/ai/blob/main/examples/ai-core/data/comic-cat.png?raw=true',

          // OpenAI specific options - image detail:
          providerOptions: {
            openai: { imageDetail: 'low' },
          },
        },
      ],
    },
  ],
});
```

<Note type="warning">
  Because the `UIMessage` type (used by AI SDK UI hooks like `useChat`) does not
  support the `providerOptions` property, you can use `convertToCoreMessages`
  first before passing the messages to functions like `generateText` or
  `streamText`. For more details on `providerOptions` usage, see
  [here](/docs/foundations/prompts#provider-options).
</Note>

#### Distillation

OpenAI supports model distillation for some models.
If you want to store a generation for use in the distillation process, you can add the `store` option to the `providerOptions.openai` object.
This will save the generation to the OpenAI platform for later use in distillation.

```typescript highlight="9-16"
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const { text, usage } = await generateText({
    model: openai('gpt-4o-mini'),
    prompt: 'Who worked on the original macintosh?',
    providerOptions: {
      openai: {
        store: true,
        metadata: {
          custom: 'value',
        },
      },
    },
  });

  console.log(text);
  console.log();
  console.log('Usage:', usage);
}

main().catch(console.error);
```

#### Prompt Caching

OpenAI has introduced [Prompt Caching](https://platform.openai.com/docs/guides/prompt-caching) for supported models
including `gpt-4o`, `gpt-4o-mini`, `o1-preview`, and `o1-mini`.

- Prompt caching is automatically enabled for these models, when the prompt is 1024 tokens or longer. It does
  not need to be explicitly enabled.
- You can use response `providerMetadata` to access the number of prompt tokens that were a cache hit.
- Note that caching behavior is dependent on load on OpenAI's infrastructure. Prompt prefixes generally remain in the
  cache following 5-10 minutes of inactivity before they are evicted, but during off-peak periods they may persist for up
  to an hour.

```ts highlight="11"
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const { text, usage, providerMetadata } = await generateText({
  model: openai('gpt-4o-mini'),
  prompt: `A 1024-token or longer prompt...`,
});

console.log(`usage:`, {
  ...usage,
  cachedPromptTokens: providerMetadata?.openai?.cachedPromptTokens,
});
```

#### Audio Input

With the `gpt-4o-audio-preview` model, you can pass audio files to the model.

<Note type="warning">
  The `gpt-4o-audio-preview` model is currently in preview and requires at least
  some audio inputs. It will not work with non-audio data.
</Note>

```ts highlight="12-14"
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const result = await generateText({
  model: openai('gpt-4o-audio-preview'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What is the audio saying?' },
        {
          type: 'file',
          mimeType: 'audio/mpeg',
          data: fs.readFileSync('./data/galileo.mp3'),
        },
      ],
    },
  ],
});
```

### Responses Models

You can use the OpenAI responses API with the `openai.responses(modelId)` factory method.

```ts
const model = openai.responses('gpt-4o-mini');
```

Further configuration can be done using OpenAI provider options.
You can validate the provider options using the `OpenAIResponsesProviderOptions` type.

```ts
import { openai, OpenAIResponsesProviderOptions } from '@ai-sdk/openai';
import { generateText } from 'ai';

const result = await generateText({
  model: openai.responses('gpt-4o-mini'),
  providerOptions: {
    openai: {
      parallelToolCalls: false,
      store: false,
      user: 'user_123',
      // ...
    } satisfies OpenAIResponsesProviderOptions,
  },
  // ...
});
```

The following provider options are available:

- **parallelToolCalls** _boolean_
  Whether to use parallel tool calls. Defaults to `true`.

- **store** _boolean_
  Whether to store the generation. Defaults to `true`.

- **metadata** _Record&lt;string, string&gt;_
  Additional metadata to store with the generation.

- **previousResponseId** _string_
  The ID of the previous response. You can use it to continue a conversation. Defaults to `undefined`.

- **instructions** _string_
  Instructions for the model.
  They can be used to change the system or developer message when continuing a conversation using the `previousResponseId` option.
  Defaults to `undefined`.

- **user** _string_
  A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Defaults to `undefined`.

- **reasoningEffort** _'low' | 'medium' | 'high'_
  Reasoning effort for reasoning models. Defaults to `medium`. If you use `providerOptions` to set the `reasoningEffort` option, this model setting will be ignored.

- **reasoningSummary** _'auto' | 'detailed'_
  Controls whether the model returns its reasoning process. Set to `'auto'` for a condensed summary, `'detailed'` for more comprehensive reasoning. Defaults to `undefined` (no reasoning summaries). When enabled, reasoning summaries appear in the stream as events with type `'reasoning'` and in non-streaming responses within the `reasoning` field.

- **strictSchemas** _boolean_
  Whether to use strict JSON schemas in tools and when generating JSON outputs. Defaults to `true`.

The OpenAI responses provider also returns provider-specific metadata:

```ts
const { providerMetadata } = await generateText({
  model: openai.responses('gpt-4o-mini'),
});

const openaiMetadata = providerMetadata?.openai;
```

The following OpenAI-specific metadata is returned:

- **responseId** _string_
  The ID of the response. Can be used to continue a conversation.

- **cachedPromptTokens** _number_
  The number of prompt tokens that were a cache hit.

- **reasoningTokens** _number_
  The number of reasoning tokens that the model generated.

#### Web Search

The OpenAI responses provider supports web search through the `openai.tools.webSearchPreview` tool.

You can force the use of the web search tool by setting the `toolChoice` parameter to `{ type: 'tool', toolName: 'web_search_preview' }`.

```ts
const result = await generateText({
  model: openai.responses('gpt-4o-mini'),
  prompt: 'What happened in San Francisco last week?',
  tools: {
    web_search_preview: openai.tools.webSearchPreview({
      // optional configuration:
      searchContextSize: 'high',
      userLocation: {
        type: 'approximate',
        city: 'San Francisco',
        region: 'California',
      },
    }),
  },
  // Force web search tool:
  toolChoice: { type: 'tool', toolName: 'web_search_preview' },
});

// URL sources
const sources = result.sources;
```

#### Reasoning Summaries

For reasoning models like `o3-mini`, `o3`, and `o4-mini`, you can enable reasoning summaries to see the model's thought process. Different models support different summarizers—for example, `o4-mini` supports detailed summaries. Set `reasoningSummary: "auto"` to automatically receive the richest level available.

```ts highlight="8-9,16"
import { openai } from '@ai-sdk/openai';
import { streamText } from 'ai';

const result = streamText({
  model: openai.responses('o4-mini'),
  prompt: 'Tell me about the Mission burrito debate in San Francisco.',
  providerOptions: {
    openai: {
      reasoningSummary: 'detailed', // 'auto' for condensed or 'detailed' for comprehensive
    },
  },
});

for await (const part of result.fullStream) {
  if (part.type === 'reasoning') {
    console.log(`Reasoning: ${part.textDelta}`);
  } else if (part.type === 'text-delta') {
    process.stdout.write(part.textDelta);
  }
}
```

For non-streaming calls with `generateText`, the reasoning summaries are available in the `reasoning` field of the response:

```ts highlight="8-9,13"
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const result = await generateText({
  model: openai.responses('o3-mini'),
  prompt: 'Tell me about the Mission burrito debate in San Francisco.',
  providerOptions: {
    openai: {
      reasoningSummary: 'auto',
    },
  },
});
console.log('Reasoning:', result.reasoning);
```

Learn more about reasoning summaries in the [OpenAI documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#reasoning-summaries).

#### PDF support

The OpenAI Responses API supports reading PDF files.
You can pass PDF files as part of the message content using the `file` type:

```ts
const result = await generateText({
  model: openai.responses('gpt-4o'),
  messages: [
    {
      role: 'user',
      content: [
        {
          type: 'text',
          text: 'What is an embedding model?',
        },
        {
          type: 'file',
          data: fs.readFileSync('./data/ai.pdf'),
          mimeType: 'application/pdf',
          filename: 'ai.pdf', // optional
        },
      ],
    },
  ],
});
```

The model will have access to the contents of the PDF file and
respond to questions about it.
The PDF file should be passed using the `data` field,
and the `mimeType` should be set to `'application/pdf'`.

#### Structured Outputs

The OpenAI Responses API supports structured outputs. You can enforce structured outputs using `generateObject` or `streamObject`, which expose a `schema` option. Additionally, you can pass a Zod or JSON Schema object to the `experimental_output` option when using `generateText` or `streamText`.

```ts
// Using generateObject
const result = await generateObject({
  model: openai.responses('gpt-4.1'),
  schema: z.object({
    recipe: z.object({
      name: z.string(),
      ingredients: z.array(
        z.object({
          name: z.string(),
          amount: z.string(),
        }),
      ),
      steps: z.array(z.string()),
    }),
  }),
  prompt: 'Generate a lasagna recipe.',
});

// Using generateText
const result = await generateText({
  model: openai.responses('gpt-4.1'),
  prompt: 'How do I make a pizza?',
  experimental_output: Output.object({
    schema: z.object({
      ingredients: z.array(z.string()),
      steps: z.array(z.string()),
    }),
  }),
});
```

### Completion Models

You can create models that call the [OpenAI completions API](https://platform.openai.com/docs/api-reference/completions) using the `.completion()` factory method.
The first argument is the model id.
Currently only `gpt-3.5-turbo-instruct` is supported.

```ts
const model = openai.completion('gpt-3.5-turbo-instruct');
```

OpenAI completion models support also some model specific settings that are not part of the [standard call settings](/docs/ai-sdk-core/settings).
You can pass them as an options argument:

```ts
const model = openai.completion('gpt-3.5-turbo-instruct', {
  echo: true, // optional, echo the prompt in addition to the completion
  logitBias: {
    // optional likelihood for specific tokens
    '50256': -100,
  },
  suffix: 'some text', // optional suffix that comes after a completion of inserted text
  user: 'test-user', // optional unique user identifier
});
```

The following optional settings are available for OpenAI completion models:

- **echo**: _boolean_

  Echo back the prompt in addition to the completion.

- **logitBias** _Record&lt;number, number&gt;_

  Modifies the likelihood of specified tokens appearing in the completion.

  Accepts a JSON object that maps tokens (specified by their token ID in
  the GPT tokenizer) to an associated bias value from -100 to 100. You
  can use this tokenizer tool to convert text to token IDs. Mathematically,
  the bias is added to the logits generated by the model prior to sampling.
  The exact effect will vary per model, but values between -1 and 1 should
  decrease or increase likelihood of selection; values like -100 or 100
  should result in a ban or exclusive selection of the relevant token.

  As an example, you can pass `{"50256": -100}` to prevent the &lt;|endoftext|&gt;
  token from being generated.

- **logprobs** _boolean | number_

  Return the log probabilities of the tokens. Including logprobs will increase
  the response size and can slow down response times. However, it can
  be useful to better understand how the model is behaving.

  Setting to true will return the log probabilities of the tokens that
  were generated.

  Setting to a number will return the log probabilities of the top n
  tokens that were generated.

- **suffix** _string_

  The suffix that comes after a completion of inserted text.

- **user** _string_

  A unique identifier representing your end-user, which can help OpenAI to
  monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).

### Model Capabilities

| Model                  | Image Input         | Audio Input         | Object Generation   | Tool Usage          |
| ---------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
| `gpt-4.1`              | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4.1-mini`         | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4.1-nano`         | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4o`               | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4o-mini`          | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4o-audio-preview` | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4-turbo`          | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4`                | <Cross size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-3.5-turbo`        | <Cross size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `o1`                   | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `o1-mini`              | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `o1-preview`           | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `o3-mini`              | <Cross size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `o3`                   | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `o4-mini`              | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `chatgpt-4o-latest`    | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `gpt-5`                | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-5-mini`           | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-5-nano`           | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |

<Note>
  The table above lists popular models. Please see the [OpenAI
  docs](https://platform.openai.com/docs/models) for a full list of available
  models. The table above lists popular models. You can also pass any available
  provider model ID as a string if needed.
</Note>

## Embedding Models

You can create models that call the [OpenAI embeddings API](https://platform.openai.com/docs/api-reference/embeddings)
using the `.embedding()` factory method.

```ts
const model = openai.embedding('text-embedding-3-large');
```

OpenAI embedding models support several additional settings.
You can pass them as an options argument:

```ts
const model = openai.embedding('text-embedding-3-large', {
  dimensions: 512 // optional, number of dimensions for the embedding
  user: 'test-user' // optional unique user identifier
})
```

The following optional settings are available for OpenAI embedding models:

- **dimensions**: _number_

  The number of dimensions the resulting output embeddings should have.
  Only supported in text-embedding-3 and later models.

- **user** _string_

  A unique identifier representing your end-user, which can help OpenAI to
  monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).

### Model Capabilities

| Model                    | Default Dimensions | Custom Dimensions   |
| ------------------------ | ------------------ | ------------------- |
| `text-embedding-3-large` | 3072               | <Check size={18} /> |
| `text-embedding-3-small` | 1536               | <Check size={18} /> |
| `text-embedding-ada-002` | 1536               | <Cross size={18} /> |

## Image Models

You can create models that call the [OpenAI image generation API](https://platform.openai.com/docs/api-reference/images)
using the `.image()` factory method.

```ts
const model = openai.image('dall-e-3');
```

<Note>
  Dall-E models do not support the `aspectRatio` parameter. Use the `size`
  parameter instead.
</Note>

### Model Capabilities

| Model         | Sizes                           |
| ------------- | ------------------------------- |
| `gpt-image-1` | 1024x1024, 1536x1024, 1024x1536 |
| `dall-e-3`    | 1024x1024, 1792x1024, 1024x1792 |
| `dall-e-2`    | 256x256, 512x512, 1024x1024     |

You can pass optional `providerOptions` to the image model. These are prone to change by OpenAI and are model dependent. For example, the `gpt-image-1` model supports the `quality` option:

```ts
const { image } = await generateImage({
  model: openai.image('gpt-image-1'),
  prompt: 'A salamander at sunrise in a forest pond in the Seychelles.',
  providerOptions: {
    openai: { quality: 'high' },
  },
});
```

For more on `generateImage()` see [Image Generation](/docs/ai-sdk-core/image-generation).

For more information on the available OpenAI image model options, see the [OpenAI API reference](https://platform.openai.com/docs/api-reference/images/create).

## Transcription Models

You can create models that call the [OpenAI transcription API](https://platform.openai.com/docs/api-reference/audio/transcribe)
using the `.transcription()` factory method.

The first argument is the model id e.g. `whisper-1`.

```ts
const model = openai.transcription('whisper-1');
```

You can also pass additional provider-specific options using the `providerOptions` argument. For example, supplying the input language in ISO-639-1 (e.g. `en`) format will improve accuracy and latency.

```ts highlight="6"
import { experimental_transcribe as transcribe } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await transcribe({
  model: openai.transcription('whisper-1'),
  audio: new Uint8Array([1, 2, 3, 4]),
  providerOptions: { openai: { language: 'en' } },
});
```

The following provider options are available:

- **timestampGranularities** _string[]_
  The granularity of the timestamps in the transcription.
  Defaults to `['segment']`.
  Possible values are `['word']`, `['segment']`, and `['word', 'segment']`.
  Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

- **language** _string_
  The language of the input audio. Supplying the input language in ISO-639-1 format (e.g. 'en') will improve accuracy and latency.
  Optional.

- **prompt** _string_
  An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
  Optional.

- **temperature** _number_
  The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
  Defaults to 0.
  Optional.

- **include** _string[]_
  Additional information to include in the transcription response.

### Model Capabilities

| Model                    | Transcription       | Duration            | Segments            | Language            |
| ------------------------ | ------------------- | ------------------- | ------------------- | ------------------- |
| `whisper-1`              | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `gpt-4o-mini-transcribe` | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
| `gpt-4o-transcribe`      | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |

## Speech Models

You can create models that call the [OpenAI speech API](https://platform.openai.com/docs/api-reference/audio/speech)
using the `.speech()` factory method.

The first argument is the model id e.g. `tts-1`.

```ts
const model = openai.speech('tts-1');
```

You can also pass additional provider-specific options using the `providerOptions` argument. For example, supplying a voice to use for the generated audio.

```ts highlight="6"
import { experimental_generateSpeech as generateSpeech } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateSpeech({
  model: openai.speech('tts-1'),
  text: 'Hello, world!',
  providerOptions: { openai: {} },
});
```

- **instructions** _string_
  Control the voice of your generated audio with additional instructions e.g. "Speak in a slow and steady tone".
  Does not work with `tts-1` or `tts-1-hd`.
  Optional.

- **response_format** _string_
  The format to audio in.
  Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`.
  Defaults to `mp3`.
  Optional.

- **speed** _number_
  The speed of the generated audio.
  Select a value from 0.25 to 4.0.
  Defaults to 1.0.
  Optional.

### Model Capabilities

| Model             | Instructions        |
| ----------------- | ------------------- |
| `tts-1`           | <Check size={18} /> |
| `tts-1-hd`        | <Check size={18} /> |
| `gpt-4o-mini-tts` | <Check size={18} /> |


## Navigation

- [xAI Grok](/v4/providers/ai-sdk-providers/xai)
- [Vercel](/v4/providers/ai-sdk-providers/vercel)
- [OpenAI](/v4/providers/ai-sdk-providers/openai)
- [Azure OpenAI](/v4/providers/ai-sdk-providers/azure)
- [Anthropic](/v4/providers/ai-sdk-providers/anthropic)
- [Amazon Bedrock](/v4/providers/ai-sdk-providers/amazon-bedrock)
- [Groq](/v4/providers/ai-sdk-providers/groq)
- [Fal](/v4/providers/ai-sdk-providers/fal)
- [AssemblyAI](/v4/providers/ai-sdk-providers/assemblyai)
- [DeepInfra](/v4/providers/ai-sdk-providers/deepinfra)
- [Deepgram](/v4/providers/ai-sdk-providers/deepgram)
- [Gladia](/v4/providers/ai-sdk-providers/gladia)
- [LMNT](/v4/providers/ai-sdk-providers/lmnt)
- [Google Generative AI](/v4/providers/ai-sdk-providers/google-generative-ai)
- [Hume](/v4/providers/ai-sdk-providers/hume)
- [Google Vertex AI](/v4/providers/ai-sdk-providers/google-vertex)
- [Rev.ai](/v4/providers/ai-sdk-providers/revai)
- [Mistral AI](/v4/providers/ai-sdk-providers/mistral)
- [Together.ai](/v4/providers/ai-sdk-providers/togetherai)
- [Cohere](/v4/providers/ai-sdk-providers/cohere)
- [Fireworks](/v4/providers/ai-sdk-providers/fireworks)
- [DeepSeek](/v4/providers/ai-sdk-providers/deepseek)
- [Cerebras](/v4/providers/ai-sdk-providers/cerebras)
- [Replicate](/v4/providers/ai-sdk-providers/replicate)
- [Perplexity](/v4/providers/ai-sdk-providers/perplexity)
- [Luma](/v4/providers/ai-sdk-providers/luma)
- [ElevenLabs](/v4/providers/ai-sdk-providers/elevenlabs)


[Full Sitemap](/sitemap.md)