# xAI Grok Provider

The [xAI Grok](https://x.ai) provider contains language model support for the [xAI API](https://x.ai/api).

## Setup

The xAI Grok provider is available via the `@ai-sdk/xai` module. You can
install it with

<InstallPackages packages="@ai-sdk/xai" />

## Provider Instance

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

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

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

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

const xai = createXai({
  apiKey: 'your-api-key',
});
```

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

- **baseURL** _string_

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

- **apiKey** _string_

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

- **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.

## Language Models

You can create [xAI models](https://console.x.ai) using a provider instance. The
first argument is the model id, e.g. `grok-4.20-non-reasoning`.

```ts
const model = xai('grok-4.20-non-reasoning');
```

<Note>
  Since AI SDK 7, `xai(modelId)` uses the xAI Responses API by default. To use
  the [Chat Completions
  API](https://docs.x.ai/docs/api-reference#chat-completions) (legacy), use
  `xai.chat(modelId)`.
</Note>

### Example

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

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

const { text } = await generateText({
  model: xai('grok-4.20-non-reasoning'),
  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
});
```

xAI language models can also be used in the `streamText` function
and support structured data generation with [`Output`](/docs/reference/ai-sdk-core/output)
(see [AI SDK Core](/docs/ai-sdk-core)).

### Reasoning Effort

For models with configurable reasoning, you can control how much effort the
model spends thinking before responding via
`providerOptions.xai.reasoningEffort`. This works for both the Responses API
(default) and the Chat Completions API (`xai.chat()`).

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

const { text } = await generateText({
  model: xai('grok-4.3'),
  prompt: 'Explain quantum entanglement.',
  providerOptions: {
    xai: { reasoningEffort: 'medium' },
  },
});
```

The AI SDK option accepts these values, but each xAI model supports a subset:

- `'none'` — Disables reasoning entirely; no thinking tokens are used. Best
  for simple use cases that need a near-instant response.
- `'low'` — Uses some reasoning tokens, but still fast. Good for general
  agentic use and tool calling.
- `'medium'` — More thinking for less-latency-sensitive applications such as
  complex data analysis and long-context reasoning.
- `'high'` — More reasoning tokens for deeper thinking. Suited for very
  challenging problems, complex math, multi-step logic, and competition-level
  tasks.

<Note>
  Support and defaults are model-specific. `grok-4.3` supports `'none'`,
  `'low'`, `'medium'`, and `'high'`. `grok-4.5` supports `'low'`, `'medium'`,
  and `'high'`, defaults to `'high'`, and cannot disable reasoning. The
  `grok-4.20-reasoning` and `grok-4.20-non-reasoning` variants do not accept
  this option. For `grok-4.20-multi-agent`, `'low'`, `'medium'`, and `'high'`
  control the number of agents instead of reasoning depth. See xAI's [reasoning
  docs](https://docs.x.ai/developers/model-capabilities/text/reasoning) and
  [Grok 4.3 model page](https://docs.x.ai/developers/models/grok-4.3) for
  current details.
</Note>

## Realtime Models

<Note type="warning">Realtime is an experimental feature.</Note>

You can create models that call the [xAI Realtime API](https://docs.x.ai/docs/guides/realtime)
using the `.experimental_realtime()` factory method.

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

const model = xai.experimental_realtime('grok-voice-latest');
```

Realtime sessions run in the browser and require a short-lived token created on
your server with `xai.experimental_realtime.getToken()`:

```ts
const token = await xai.experimental_realtime.getToken({
  model: 'grok-voice-latest',
});
```

See [Realtime](/docs/ai-sdk-core/realtime) for the complete setup and tool
calling pattern.

## Responses API (Agentic Tools)

The xAI Responses API is the default when using `xai(modelId)` (since AI SDK 7). You can also use `xai.responses(modelId)` explicitly. This enables the model to autonomously orchestrate tool calls and research on xAI's servers.

```ts
const model = xai.responses('grok-4.20-non-reasoning');
```

The Responses API provides server-side tools that the model can autonomously execute during its reasoning process:

- **web_search**: Real-time web search and page browsing
- **x_search**: Search X (Twitter) posts, users, and threads
- **code_execution**: Execute Python code for calculations and data analysis
- **view_image**: View and analyze images
- **view_x_video**: View and analyze videos from X posts
- **mcp_server**: Connect to remote MCP servers and use their tools
- **file_search**: Search through documents in vector stores (collections)

### Vision

The Responses API supports image input with vision models:

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

const { text } = await generateText({
  model: xai.responses('grok-3'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What do you see in this image?' },
        {
          type: 'file',
          mediaType: 'image',
          data: fs.readFileSync('./image.png'),
        },
      ],
    },
  ],
});
```

You can control the resolution at which the model processes an image with
the `imageDetail` provider option on the image part:

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

const { text } = await generateText({
  model: xai('grok-4.3'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What do you see in this image?' },
        {
          type: 'file',
          mediaType: 'image/png',
          data: fs.readFileSync('./image.png'),
          providerOptions: {
            xai: { imageDetail: 'low' },
          },
        },
      ],
    },
  ],
});
```

The following image detail values are supported:

- **low**: processes the image at reduced resolution and consumes fewer input tokens.
- **high**: processes the image at full resolution.
- **auto**: lets the xAI API decide.

When not set, the image is processed at full resolution.

### Web Search Tool

The web search tool enables autonomous web research with optional domain filtering and image understanding:

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

const { text, sources } = await generateText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt: 'What are the latest developments in AI?',
  tools: {
    web_search: xai.tools.webSearch({
      allowedDomains: ['arxiv.org', 'openai.com'],
      enableImageUnderstanding: true,
    }),
  },
});

console.log(text);
console.log('Citations:', sources);
```

#### Web Search Parameters

- **allowedDomains** _string[]_

  Only search within specified domains (max 5). Cannot be used with `excludedDomains`.

- **excludedDomains** _string[]_

  Exclude specified domains from search (max 5). Cannot be used with `allowedDomains`.

- **enableImageSearch** _boolean_

  Allow the model to perform image search as a separate Web Search mode when images are useful for the answer. The model can choose between regular web search and image search; responses can include Markdown image embeds when relevant.

- **enableImageUnderstanding** _boolean_

  Enable the model to view and analyze images found during search. Increases token usage. To allow explicitly searching for images, use `enableImageSearch`.

### X Search Tool

The X search tool enables searching X (Twitter) for posts, with filtering by handles and date ranges:

```ts
const { text, sources } = await generateText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt: 'What are people saying about AI on X this week?',
  tools: {
    x_search: xai.tools.xSearch({
      allowedXHandles: ['elonmusk', 'xai'],
      fromDate: '2025-10-23',
      toDate: '2025-10-30',
      enableImageUnderstanding: true,
      enableVideoUnderstanding: true,
    }),
  },
});
```

#### X Search Parameters

- **allowedXHandles** _string[]_

  Only search posts from specified X handles (max 10). Cannot be used with `excludedXHandles`.

- **excludedXHandles** _string[]_

  Exclude posts from specified X handles (max 10). Cannot be used with `allowedXHandles`.

- **fromDate** _string_

  Start date for posts in ISO8601 format (`YYYY-MM-DD`).

- **toDate** _string_

  End date for posts in ISO8601 format (`YYYY-MM-DD`).

- **enableImageUnderstanding** _boolean_

  Enable the model to view and analyze images in X posts.

- **enableVideoUnderstanding** _boolean_

  Enable the model to view and analyze videos in X posts.

### Code Execution Tool

The code execution tool enables the model to write and execute Python code for calculations and data analysis:

```ts
const { text } = await generateText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt:
    'Calculate the compound interest for $10,000 at 5% annually for 10 years',
  tools: {
    code_execution: xai.tools.codeExecution(),
  },
});
```

### View Image Tool

The view image tool enables the model to view and analyze images:

```ts
const { text } = await generateText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt: 'Describe what you see in the image',
  tools: {
    view_image: xai.tools.viewImage(),
  },
});
```

### View X Video Tool

The view X video tool enables the model to view and analyze videos from X (Twitter) posts:

```ts
const { text } = await generateText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt: 'Summarize the content of this X video',
  tools: {
    view_x_video: xai.tools.viewXVideo(),
  },
});
```

### MCP Server Tool

The MCP server tool enables the model to connect to remote [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) servers and use their tools:

```ts
const { text } = await generateText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt: 'Use the weather tool to check conditions in San Francisco',
  tools: {
    weather_server: xai.tools.mcpServer({
      serverUrl: 'https://example.com/mcp',
      serverLabel: 'weather-service',
      serverDescription: 'Weather data provider',
      allowedTools: ['get_weather', 'get_forecast'],
    }),
  },
});
```

#### MCP Server Parameters

- **serverUrl** _string_ (required)

  The URL of the remote MCP server.

- **serverLabel** _string_

  A label to identify the MCP server.

- **serverDescription** _string_

  A description of what the MCP server provides.

- **allowedTools** _string[]_

  List of tool names that the model is allowed to use from the MCP server. If not specified, all tools are allowed.

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

  Custom headers to include when connecting to the MCP server.

- **authorization** _string_

  Authorization header value for authenticating with the MCP server (e.g., `'Bearer token123'`).

### File Search Tool

The file search tool enables searching through documents stored in xAI vector stores (collections):

```ts
import { xai, type XaiLanguageModelResponsesOptions } from '@ai-sdk/xai';
import { streamText } from 'ai';

const result = streamText({
  model: xai.responses('grok-4.20-reasoning'),
  prompt: 'What documents do you have access to?',
  tools: {
    file_search: xai.tools.fileSearch({
      vectorStoreIds: ['collection_your-collection-id'],
      maxNumResults: 10,
    }),
  },
  providerOptions: {
    xai: {
      include: ['file_search_call.results'],
    } satisfies XaiLanguageModelResponsesOptions,
  },
});
```

#### File Search Parameters

- **vectorStoreIds** _string[]_ (required)

  The IDs of the vector stores (collections) to search.

- **maxNumResults** _number_

  The maximum number of results to return from the search.

#### Provider Options for File Search

- **include** _Array&lt;'file_search_call.results'&gt;_

  Include file search results in the response. When set to `['file_search_call.results']`, the response will contain the actual search results with file content and scores.

<Note>
  File search requires grok-4 family models (including grok-4.20) and the
  Responses API. Vector stores can be created using the [xAI
  API](https://docs.x.ai/docs/guides/using-collections/api).
</Note>

### Multiple Tools

You can combine multiple server-side tools for comprehensive research:

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

const { stream } = streamText({
  model: xai.responses('grok-4.20-non-reasoning'),
  prompt: 'Research AI safety developments and calculate risk metrics',
  tools: {
    web_search: xai.tools.webSearch(),
    x_search: xai.tools.xSearch(),
    code_execution: xai.tools.codeExecution(),
    file_search: xai.tools.fileSearch({
      vectorStoreIds: ['collection_your-documents'],
    }),
    data_service: xai.tools.mcpServer({
      serverUrl: 'https://data.example.com/mcp',
      serverLabel: 'data-service',
    }),
  },
});

for await (const part of stream) {
  if (part.type === 'text-delta') {
    process.stdout.write(part.text);
  } else if (part.type === 'source' && part.sourceType === 'url') {
    console.log('\nSource:', part.url);
  }
}
```

### Provider Options

The Responses API supports the following provider options:

```ts
import { xai, type XaiLanguageModelResponsesOptions } from '@ai-sdk/xai';
import { generateText } from 'ai';

const result = await generateText({
  model: xai.responses('grok-4.5'),
  providerOptions: {
    xai: {
      reasoningEffort: 'high',
    } satisfies XaiLanguageModelResponsesOptions,
  },
  // ...
});
```

The following provider options are available:

- **reasoningEffort** _'none' | 'low' | 'medium' | 'high'_

  Control the reasoning effort for supported models. See [Reasoning Effort](#reasoning-effort) for model-specific values and defaults.

- **logprobs** _boolean_

  Return log probabilities for output tokens.

- **topLogprobs** _number_

  Number of most likely tokens to return per token position (0-8). When set, `logprobs` is automatically enabled.

- **include** _Array&lt;'file_search_call.results'&gt;_

  Specify additional output data to include in the model response. Use `['file_search_call.results']` to include file search results with scores and content.

- **store** _boolean_

  Whether to store the input message(s) and model response for later retrieval. Defaults to `true`.

- **previousResponseId** _string_

  The ID of the previous response from the model. You can use it to continue a conversation.

<Note>
  The Responses API only supports server-side tools. You cannot mix server-side
  tools with client-side function tools in the same request.
</Note>

## Model Capabilities

| Model                         | Image Input | Object Generation | Tool Usage | Tool Streaming | Reasoning |
| ----------------------------- | ----------- | ----------------- | ---------- | -------------- | --------- |
| `grok-4.5`                    | <Check />   | <Check />         | <Check />  | <Check />      | <Check /> |
| `grok-4.20-reasoning`         | <Check />   | <Check />         | <Check />  | <Check />      | <Check /> |
| `grok-4.20-non-reasoning`     | <Check />   | <Check />         | <Check />  | <Check />      | <Cross /> |
| `grok-4-1-fast-reasoning`     | <Check />   | <Check />         | <Check />  | <Check />      | <Check /> |
| `grok-4-1-fast-non-reasoning` | <Check />   | <Check />         | <Check />  | <Check />      | <Cross /> |
| `grok-4-1`                    | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
| `grok-4-fast-reasoning`       | <Check />   | <Check />         | <Check />  | <Check />      | <Check /> |
| `grok-4-fast-non-reasoning`   | <Check />   | <Check />         | <Check />  | <Check />      | <Cross /> |
| `grok-code-fast-1`            | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |
| `grok-3`                      | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
| `grok-3-mini`                 | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |

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

## Speech Models

You can create models that call the [xAI Text to Speech API](https://docs.x.ai/developers/model-capabilities/audio/text-to-speech)
using the `.speech()` factory method. xAI's text-to-speech endpoint does not
require a model identifier.

```ts
const model = xai.speech();
```

Use xAI speech models with the `generateSpeech` function:

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

const result = await generateSpeech({
  model: xai.speech(),
  text: 'Hello from the AI SDK!',
  voice: 'ara',
  language: 'en',
  outputFormat: 'mp3',
  speed: 1.1,
});
```

### Supported Parameters

- **text** _string_ (required)

  Text to synthesize. You can include xAI speech tags such as `[pause]`,
  `[laugh]`, or `<whisper>...</whisper>` directly in the text.

- **voice** _string_

  The xAI voice ID. Defaults to `'eve'`. Built-in voice IDs are `'eve'`,
  `'ara'`, `'rex'`, `'sal'`, and `'leo'`; custom voice IDs are also accepted.

- **language** _string_

  A BCP-47 language code or `'auto'` for automatic detection. Defaults to
  `'auto'` when omitted.

- **speed** _number_

  Speech rate multiplier from `0.7` to `1.5`.

- **outputFormat** _string_

  The audio codec to generate. Supported values are `'mp3'`, `'wav'`, `'pcm'`,
  `'mulaw'`, and `'alaw'`. Defaults to `'mp3'`.

<Note>
  xAI does not expose a separate `instructions` field for text-to-speech. Use
  speech tags in `text` to control expressive delivery.
</Note>

### Provider Options

You can pass xAI-specific controls using `providerOptions.xai`:

```ts
import { xai, type XaiSpeechModelOptions } from '@ai-sdk/xai';
import { generateSpeech } from 'ai';

const result = await generateSpeech({
  model: xai.speech(),
  text: 'A high fidelity narration sample.',
  outputFormat: 'mp3',
  providerOptions: {
    xai: {
      sampleRate: 44100,
      bitRate: 192000,
      optimizeStreamingLatency: 1,
      textNormalization: true,
    } satisfies XaiSpeechModelOptions,
  },
});
```

- **sampleRate** _8000 | 16000 | 22050 | 24000 | 44100 | 48000_

  Sample rate of the output audio in Hz.

- **bitRate** _32000 | 64000 | 96000 | 128000 | 192000_

  MP3 bit rate in bits per second. Only applies when `outputFormat` is
  `'mp3'`.

- **optimizeStreamingLatency** _0 | 1 | 2_

  Latency optimization level. Higher values reduce time to first audio with a
  quality tradeoff at chunk boundaries.

- **textNormalization** _boolean_

  Whether to normalize written-form input text before synthesizing speech.

### Model Capabilities

| Model     | Language  | Speed     | Output Formats             |
| --------- | --------- | --------- | -------------------------- |
| `default` | <Check /> | <Check /> | mp3, wav, pcm, mulaw, alaw |

## Transcription Models

You can create models that call the [xAI Speech to Text API](https://docs.x.ai/developers/model-capabilities/audio/speech-to-text)
using the `.transcription()` factory method. xAI's batch transcription endpoint
does not require a model identifier.

```ts
const model = xai.transcription();
```

Use xAI transcription models with the `transcribe` function:

```ts
import { xai } from '@ai-sdk/xai';
import { transcribe } from 'ai';
import { readFile } from 'fs/promises';

const result = await transcribe({
  model: xai.transcription(),
  audio: await readFile('meeting.mp3'),
});
```

### Provider Options

You can pass xAI-specific controls using `providerOptions.xai`:

```ts
import { xai, type XaiTranscriptionModelOptions } from '@ai-sdk/xai';
import { transcribe } from 'ai';
import { readFile } from 'fs/promises';

const result = await transcribe({
  model: xai.transcription(),
  audio: await readFile('meeting.mp3'),
  providerOptions: {
    xai: {
      language: 'en',
      format: true,
      keyterm: ['AI SDK', 'Grok'],
      diarize: true,
    } satisfies XaiTranscriptionModelOptions,
  },
});
```

- **audioFormat** _`pcm` | `mulaw` | `alaw`_

  Audio encoding for raw, headerless input audio.

- **sampleRate** _8000 | 16000 | 22050 | 24000 | 44100 | 48000_

  Sample rate of the input audio in Hz.

- **language** _string_

  Language code used for inverse text normalization.

- **format** _boolean_

  Enables inverse text normalization. Requires `language`.

- **multichannel** _boolean_

  Enables per-channel transcription for interleaved multichannel audio.

- **channels** _2 | 3 | 4 | 5 | 6 | 7 | 8_

  Number of interleaved audio channels.

- **diarize** _boolean_

  Enables speaker diarization.

- **keyterm** _string | string[]_

  One or more terms to bias transcription toward.

- **fillerWords** _boolean_

  Includes filler words such as `uh` and `um` in the transcript.

- **streaming** _object_

  Options for streaming speech-to-text over WebSocket. Use with `experimental_streamTranscribe`.
  - **interimResults** _boolean_

    Emits partial transcripts while speech is being processed.

  - **endpointing** _number_

    Silence duration in milliseconds before an utterance-final event. Range: 0-5000.

  - **smartTurn** _number_

    End-of-turn detection threshold. When set, enables Smart Turn. Range: 0.0-1.0.

  - **smartTurnTimeout** _number_

    Maximum silence duration in milliseconds before forcing `speech_final`. Range: 1-5000.

### Model Capabilities

| Model     | Request/Response | Streaming | Word Timestamps | Diarization | Multichannel |
| --------- | ---------------- | --------- | --------------- | ----------- | ------------ |
| `default` | <Check />        | <Check /> | <Check />       | <Check />   | <Check />    |

<Note>
  Word timestamps, diarization results, and segments are only returned on the
  request/response path (`transcribe`). Streaming transcription
  (`experimental_streamTranscribe`) emits partial and final transcript text with
  utterance-level timing, but does not surface per-word timestamps, speaker
  labels, or segments.
</Note>

## Image Models

You can create xAI image models using the `.image()` factory method. For more on image generation with the AI SDK see [generateImage()](/docs/reference/ai-sdk-core/generate-image).

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

const { image } = await generateImage({
  model: xai.image('grok-imagine-image'),
  prompt: 'A futuristic cityscape at sunset',
});
```

<Note>
  The xAI image model does not support the `size` parameter. Use `aspectRatio`
  instead. Supported aspect ratios: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`,
  `2:3`, `2:1`, `1:2`, `19.5:9`, `9:19.5`, `20:9`, `9:20`, and `auto`.
</Note>

### Image Editing

xAI supports image editing through the `grok-imagine-image` model. Pass input images via `prompt.images` to transform or edit existing images.

<Note>
  xAI image editing does not support masks. Editing is prompt-driven - describe
  what you want to change in the text prompt.
</Note>

#### Basic Image Editing

Transform an existing image using text prompts:

```ts
import { xai } from '@ai-sdk/xai';
import { generateImage } from 'ai';
import { readFileSync } from 'fs';

const imageBuffer = readFileSync('./input-image.png');

const { images } = await generateImage({
  model: xai.image('grok-imagine-image'),
  prompt: {
    text: 'Turn the cat into a golden retriever dog',
    images: [imageBuffer],
  },
});
```

#### Multi-Image Editing

Combine or reference multiple input images in the prompt:

```ts
import { xai } from '@ai-sdk/xai';
import { generateImage } from 'ai';
import { readFileSync } from 'fs';

const cat = readFileSync('./cat.png');
const dog = readFileSync('./dog.png');

const { images } = await generateImage({
  model: xai.image('grok-imagine-image'),
  prompt: {
    text: 'Combine these two animals into a group photo',
    images: [cat, dog],
  },
});
```

#### Style Transfer

Apply artistic styles to an image:

```ts
const imageBuffer = readFileSync('./input-image.png');

const { images } = await generateImage({
  model: xai.image('grok-imagine-image'),
  prompt: {
    text: 'Transform this into a watercolor painting style',
    images: [imageBuffer],
  },
  aspectRatio: '1:1',
});
```

<Note>
  Input images can be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`, or
  base64-encoded strings.
</Note>

### Image Provider Options

You can customize the image generation behavior with provider-specific settings via `providerOptions.xai`:

```ts
import { xai, type XaiImageModelOptions } from '@ai-sdk/xai';
import { generateImage } from 'ai';

const { images } = await generateImage({
  model: xai.image('grok-imagine-image-pro'),
  prompt: 'A futuristic cityscape at sunset',
  aspectRatio: '16:9',
  providerOptions: {
    xai: {
      resolution: '2k',
      quality: 'high',
    } satisfies XaiImageModelOptions,
  },
});
```

- **resolution** _'1k' | '2k'_

  Output resolution. `1k` produces ~1024×1024 images, `2k` produces ~2048×2048
  images (actual dimensions vary based on aspect ratio). Available for
  `grok-imagine-image-pro`.

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

  Image quality level. Higher quality may increase generation time.

### Image Model Capabilities

| Model                    | Resolution | Aspect Ratios                                                                                               | Image Editing |
| ------------------------ | ---------- | ----------------------------------------------------------------------------------------------------------- | ------------- |
| `grok-imagine-image-pro` | `1k`, `2k` | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `2:1`, `1:2`, `19.5:9`, `9:19.5`, `20:9`, `9:20`, `auto` | <Check />     |
| `grok-imagine-image`     | `1k`       | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `2:1`, `1:2`, `19.5:9`, `9:19.5`, `20:9`, `9:20`, `auto` | <Check />     |

## Video Models

You can create xAI video models using the `.video()` factory method.
For more on video generation with the AI SDK see [generateVideo()](/docs/reference/ai-sdk-core/generate-video).

This provider supports standard video generation from text prompts or image input, plus explicit video editing, video extension, and reference-to-video (R2V) operations.

### Text-to-Video

Generate videos from text prompts:

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';

const { video } = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: 'A chicken flying into the sunset in the style of 90s anime.',
  aspectRatio: '16:9',
  duration: 5,
  providerOptions: {
    xai: {
      user: 'user-123',
      pollTimeoutMs: 600000, // 10 minutes
    } satisfies XaiVideoModelOptions,
  },
});
```

### Generation with Image Input

Generate videos using an image as the starting frame with an optional text prompt. This uses the standard generation path rather than a separate provider mode:

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';

const { video } = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: {
    image: 'https://example.com/start-frame.png',
    text: 'The cat slowly turns its head and blinks',
  },
  duration: 5,
  providerOptions: {
    xai: {
      pollTimeoutMs: 600000, // 10 minutes
    } satisfies XaiVideoModelOptions,
  },
});
```

You can also pass the starting frame via the top-level `frameImages` option using the `first_frame` role. This is provider-agnostic and accepts file data (e.g. a `Buffer`) or a `{ type: 'url', url }` object:

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';

const { video } = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: 'The cat slowly turns its head and blinks',
  frameImages: [
    {
      image: fs.readFileSync('./start-frame.png'),
      frameType: 'first_frame',
    },
  ],
  duration: 5,
  providerOptions: {
    xai: {
      pollTimeoutMs: 600000, // 10 minutes
    } satisfies XaiVideoModelOptions,
  },
});
```

<Note>
  xAI does not support first-last-frame interpolation. A `last_frame` entry in
  `frameImages` is ignored with a warning — use the `extend-video` mode to
  continue from a video's last frame instead.
</Note>

### Video Editing

Edit an existing video using a text prompt by providing a source video URL via provider options:

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';

const { video } = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: 'Give the person sunglasses and a hat',
  providerOptions: {
    xai: {
      mode: 'edit-video',
      videoUrl: 'https://example.com/source-video.mp4',
      pollTimeoutMs: 600000, // 10 minutes
    } satisfies XaiVideoModelOptions,
  },
});
```

<Note>
  Video editing accepts input videos up to 8.7 seconds long. The `duration`,
  `aspectRatio`, and `resolution` parameters are not supported for editing - the
  output matches the input video's properties (capped at 720p).
</Note>

### Chaining and Concurrent Edits

The xAI-hosted video URL is available in `providerMetadata.xai.videoUrl`.
You can use it to chain sequential edits or branch into concurrent edits
using `Promise.all`:

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';

const providerOptions = {
  xai: {
    mode: 'edit-video',
    videoUrl: 'https://example.com/source-video.mp4',
    pollTimeoutMs: 600000,
  } satisfies XaiVideoModelOptions,
};

// Step 1: Apply an initial edit
const step1 = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: 'Add a party hat to the person',
  providerOptions,
});

// Get the xAI-hosted URL from provider metadata
const step1VideoUrl = step1.providerMetadata?.xai?.videoUrl as string;

// Step 2: Apply two more edits concurrently, building on step 1
const [withSunglasses, withScarf] = await Promise.all([
  generateVideo({
    model: xai.video('grok-imagine-video'),
    prompt: 'Add sunglasses',
    providerOptions: {
      xai: {
        mode: 'edit-video',
        videoUrl: step1VideoUrl,
        pollTimeoutMs: 600000,
      },
    },
  }),
  generateVideo({
    model: xai.video('grok-imagine-video'),
    prompt: 'Add a scarf',
    providerOptions: {
      xai: {
        mode: 'edit-video',
        videoUrl: step1VideoUrl,
        pollTimeoutMs: 600000,
      },
    },
  }),
]);
```

### Video Extension

Extend an existing video from its last frame. The `duration` controls the length of the extension only, not the total output. The output inherits `aspectRatio` and `resolution` from the source video.

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';

// Step 1: Generate a source video
const source = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: 'A cat sitting on a sunlit windowsill, tail gently swishing.',
  duration: 5,
  aspectRatio: '16:9',
  providerOptions: {
    xai: {
      pollTimeoutMs: 600000,
    } satisfies XaiVideoModelOptions,
  },
});

const sourceUrl = source.providerMetadata?.xai?.videoUrl as string;

// Step 2: Extend the video with a new scene
const extended = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt: 'The cat turns its head, notices a butterfly, and leaps off.',
  duration: 6,
  providerOptions: {
    xai: {
      mode: 'extend-video',
      videoUrl: sourceUrl,
      pollTimeoutMs: 600000,
    } satisfies XaiVideoModelOptions,
  },
});
```

<Note>
  Video extension does not support custom `aspectRatio` or `resolution` — the
  output inherits those from the source video. `duration` is supported and
  controls how long the extension is (not the total video length).
</Note>

### Reference-to-Video (R2V)

Provide reference images to guide the video's style and content. Unlike image-to-video, reference images are not used as the first frame — the model incorporates their visual elements into the generated video. Each reference image can be a public HTTPS URL or a base64 data URI.

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';

const { video } = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt:
    'The comic cat from <IMAGE_1> and the comic dog from <IMAGE_2> ' +
    'are having a playful chase through a sunlit park. ' +
    'Cinematic slow-motion, warm afternoon light.',
  duration: 8,
  aspectRatio: '16:9',
  providerOptions: {
    xai: {
      mode: 'reference-to-video',
      referenceImageUrls: [
        'https://example.com/comic-cat.png',
        'https://example.com/comic-dog.png',
      ],
      pollTimeoutMs: 600000,
    } satisfies XaiVideoModelOptions,
  },
});
```

Use `<IMAGE_1>`, `<IMAGE_2>`, etc. in your prompt to reference specific images. Up to 7 reference images are supported per request.

Alternatively, use the provider-agnostic top-level `inputReferences` option. Providing it automatically selects reference-to-video mode, and it accepts file data (e.g. a `Buffer`) or `{ type: 'url', url }` objects:

```ts
import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';

const { video } = await generateVideo({
  model: xai.video('grok-imagine-video'),
  prompt:
    'The comic cat and the comic dog are having a playful chase ' +
    'through a sunlit park. Cinematic slow-motion, warm afternoon light.',
  inputReferences: [
    fs.readFileSync('./comic-cat.png'),
    fs.readFileSync('./comic-dog.png'),
  ],
  duration: 8,
  aspectRatio: '16:9',
  providerOptions: {
    xai: {
      pollTimeoutMs: 600000,
    } satisfies XaiVideoModelOptions,
  },
});
```

<Note>
  Reference-to-video supports `duration`, `aspectRatio`, and `resolution`. Use
  `mode` to select the operation — each mode is mutually exclusive. When both
  are provided, `frameImages` takes precedence over `inputReferences`, and
  `inputReferences` takes precedence over the legacy `referenceImageUrls`
  provider option. Reference-to-video requires the `grok-imagine-video` model.
</Note>

### Video Provider Options

The following provider options are available via `providerOptions.xai`.
You can validate the provider options using the `XaiVideoModelOptions` type.

- **pollIntervalMs** _number_

  Polling interval in milliseconds for checking task status. Defaults to 5000.

- **pollTimeoutMs** _number_

  Maximum wait time in milliseconds for video generation. Defaults to 600000 (10 minutes).

- **resolution** _'480p' | '720p'_

  Video resolution. When using the SDK's standard `resolution` parameter,
  `1280x720` maps to `720p` and `854x480` maps to `480p`.
  Use this provider option to pass the native format directly.

- **user** _string_

  Optional identifier for the end user responsible for the request. xAI uses
  this value for abuse monitoring. It is sent unchanged for video generation
  (including reference-to-video) and video editing requests, and is omitted
  when not configured. It is not sent for video extension requests. Use an
  opaque stable identifier and avoid sending unnecessary personal information.

- **mode** _'edit-video' | 'extend-video' | 'reference-to-video'_

  Selects the explicit video operation. Each mode is mutually exclusive:
  - `'edit-video'` — edit an existing video (requires `videoUrl`)
  - `'extend-video'` — extend a video from its last frame (requires `videoUrl`)
  - `'reference-to-video'` — generate from reference images (requires `referenceImageUrls`)

  When omitted, standard generation is used. Legacy inputs are still auto-detected from fields for backward compatibility.

- **videoUrl** _string_

  URL of a source video. Used with `mode: 'edit-video'` for video editing
  and `mode: 'extend-video'` for video extension.

- **referenceImageUrls** _string[]_

  Array of reference image URLs (1–7 images) or base64 data URIs for
  reference-to-video (R2V) generation. The model incorporates visual
  elements from these images without using them as the first frame. Use
  `<IMAGE_1>`, `<IMAGE_2>`, etc. in the prompt to reference specific
  images. Used with `mode: 'reference-to-video'`.

<Note>
  Video generation is an asynchronous process that can take several minutes.
  Consider setting `pollTimeoutMs` to at least 10 minutes (600000ms) for
  reliable operation. Generated video URLs are ephemeral and should be
  downloaded promptly.
</Note>

### Aspect Ratio and Resolution

For **text-to-video**, you can specify both `aspectRatio` and `resolution`.
The default aspect ratio is `16:9` and the default resolution is `480p`.

For **image-to-video**, the output defaults to the input image's aspect ratio.
If you specify `aspectRatio`, it will override this and stretch the image to the
desired ratio.

For **video editing**, the output matches the input video's aspect ratio and
resolution. Custom `duration`, `aspectRatio`, and `resolution` are not
supported — the output resolution is capped at 720p (e.g., a 1080p input
will be downsized to 720p).

For **video extension**, the output inherits `aspectRatio` and `resolution`
from the source video. `duration` is supported and controls only the
extension length.

For **reference-to-video (R2V)**, you can specify `duration`, `aspectRatio`,
and `resolution` just like text-to-video.

### Video Model Capabilities

| Model                | Duration | Aspect Ratios                                     | Resolution     | Image-to-Video | Editing   | Extension | R2V       |
| -------------------- | -------- | ------------------------------------------------- | -------------- | -------------- | --------- | --------- | --------- |
| `grok-imagine-video` | 1–15s    | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3` | `480p`, `720p` | <Check />      | <Check /> | <Check /> | <Check /> |

<Note>
  You can also pass any available provider model ID as a string if needed.
</Note>


## Navigation

- [AI Gateway](/providers/ai-sdk-providers/ai-gateway)
- [xAI Grok](/providers/ai-sdk-providers/xai)
- [Vercel](/providers/ai-sdk-providers/vercel)
- [OpenAI](/providers/ai-sdk-providers/openai)
- [Azure OpenAI](/providers/ai-sdk-providers/azure)
- [Anthropic](/providers/ai-sdk-providers/anthropic)
- [Open Responses](/providers/ai-sdk-providers/open-responses)
- [Claude Platform on AWS](/providers/ai-sdk-providers/anthropic-aws)
- [Amazon Bedrock](/providers/ai-sdk-providers/amazon-bedrock)
- [Groq](/providers/ai-sdk-providers/groq)
- [Fal](/providers/ai-sdk-providers/fal)
- [AssemblyAI](/providers/ai-sdk-providers/assemblyai)
- [DeepInfra](/providers/ai-sdk-providers/deepinfra)
- [Deepgram](/providers/ai-sdk-providers/deepgram)
- [Black Forest Labs](/providers/ai-sdk-providers/black-forest-labs)
- [Gladia](/providers/ai-sdk-providers/gladia)
- [LMNT](/providers/ai-sdk-providers/lmnt)
- [Google](/providers/ai-sdk-providers/google)
- [Hume](/providers/ai-sdk-providers/hume)
- [Google Vertex AI](/providers/ai-sdk-providers/google-vertex)
- [Rev.ai](/providers/ai-sdk-providers/revai)
- [Baseten](/providers/ai-sdk-providers/baseten)
- [Hugging Face](/providers/ai-sdk-providers/huggingface)
- [QuiverAI](/providers/ai-sdk-providers/quiverai)
- [Mistral AI](/providers/ai-sdk-providers/mistral)
- [Together.ai](/providers/ai-sdk-providers/togetherai)
- [Cohere](/providers/ai-sdk-providers/cohere)
- [Fireworks](/providers/ai-sdk-providers/fireworks)
- [Voyage AI](/providers/ai-sdk-providers/voyage)
- [DeepSeek](/providers/ai-sdk-providers/deepseek)
- [Moonshot AI](/providers/ai-sdk-providers/moonshotai)
- [Alibaba](/providers/ai-sdk-providers/alibaba)
- [MiniMax](/providers/ai-sdk-providers/minimax)
- [Cerebras](/providers/ai-sdk-providers/cerebras)
- [Replicate](/providers/ai-sdk-providers/replicate)
- [Prodia](/providers/ai-sdk-providers/prodia)
- [Perplexity](/providers/ai-sdk-providers/perplexity)
- [Luma](/providers/ai-sdk-providers/luma)
- [ByteDance](/providers/ai-sdk-providers/bytedance)
- [Kling AI](/providers/ai-sdk-providers/klingai)
- [ElevenLabs](/providers/ai-sdk-providers/elevenlabs)
- [Cartesia](/providers/ai-sdk-providers/cartesia)


[Full Sitemap](/sitemap.md)