@ai-sdk/xai 4.0.0-beta.21 → 4.0.0-beta.24

package/docs/01-xai.mdx

@@ -1,6 +1,6 @@
 ---
 title: xAI Grok
-description: Learn how to use xAI Grok.
+description: Learn how to use xAI Grok and Imagine.
 ---
 
 # xAI Grok Provider
@@ -73,10 +73,10 @@ You can use the following optional settings to customize the xAI provider instan
 ## 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-3`.
+first argument is the model id, e.g. `grok-4.20-non-reasoning`.
 
 ```ts
-const model = xai('grok-3');
+const model = xai('grok-4.20-non-reasoning');
 ```
 
 By default, `xai(modelId)` uses the Responses API. To use the [Chat Completions API](https://docs.x.ai/docs/api-reference#chat-completions) (legacy), use `xai.chat(modelId)`.
@@ -90,7 +90,7 @@ import { xai } from '@ai-sdk/xai';
 import { generateText } from 'ai';
 
 const { text } = await generateText({
-  model: xai('grok-3'),
+  model: xai('grok-4.20-non-reasoning'),
   prompt: 'Write a vegetarian lasagna recipe for 4 people.',
 });
 ```
@@ -104,7 +104,7 @@ and support structured data generation with [`Output`](/docs/reference/ai-sdk-co
 The xAI Responses API is the default when using `xai(modelId)`. 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-fast-non-reasoning');
+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:
@@ -148,7 +148,7 @@ import { xai } from '@ai-sdk/xai';
 import { generateText } from 'ai';
 
 const { text, sources } = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  model: xai.responses('grok-4.20-non-reasoning'),
   prompt: 'What are the latest developments in AI?',
   tools: {
     web_search: xai.tools.webSearch({
@@ -182,7 +182,7 @@ The X search tool enables searching X (Twitter) for posts, with filtering by han
 
 ```ts
 const { text, sources } = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  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({
@@ -228,7 +228,7 @@ The code execution tool enables the model to write and execute Python code for c
 
 ```ts
 const { text } = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  model: xai.responses('grok-4.20-non-reasoning'),
   prompt:
     'Calculate the compound interest for $10,000 at 5% annually for 10 years',
   tools: {
@@ -243,7 +243,7 @@ The view image tool enables the model to view and analyze images:
 
 ```ts
 const { text } = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  model: xai.responses('grok-4.20-non-reasoning'),
   prompt: 'Describe what you see in the image',
   tools: {
     view_image: xai.tools.viewImage(),
@@ -257,7 +257,7 @@ The view X video tool enables the model to view and analyze videos from X (Twitt
 
 ```ts
 const { text } = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  model: xai.responses('grok-4.20-non-reasoning'),
   prompt: 'Summarize the content of this X video',
   tools: {
     view_x_video: xai.tools.viewXVideo(),
@@ -271,7 +271,7 @@ The MCP server tool enables the model to connect to remote [Model Context Protoc
 
 ```ts
 const { text } = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  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({
@@ -319,7 +319,7 @@ import { xai, type XaiLanguageModelResponsesOptions } from '@ai-sdk/xai';
 import { streamText } from 'ai';
 
 const result = streamText({
-  model: xai.responses('grok-4-1-fast-reasoning'),
+  model: xai.responses('grok-4.20-reasoning'),
   prompt: 'What documents do you have access to?',
   tools: {
     file_search: xai.tools.fileSearch({
@@ -352,7 +352,7 @@ const result = streamText({
   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 and the Responses API. Vector stores
+  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>
@@ -366,7 +366,7 @@ import { xai } from '@ai-sdk/xai';
 import { streamText } from 'ai';
 
 const { fullStream } = streamText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  model: xai.responses('grok-4.20-non-reasoning'),
   prompt: 'Research AI safety developments and calculate risk metrics',
   tools: {
     web_search: xai.tools.webSearch(),
@@ -400,7 +400,7 @@ import { xai, type XaiLanguageModelResponsesOptions } from '@ai-sdk/xai';
 import { generateText } from 'ai';
 
 const result = await generateText({
-  model: xai.responses('grok-4-fast-non-reasoning'),
+  model: xai.responses('grok-4.20-non-reasoning'),
   providerOptions: {
     xai: {
       reasoningEffort: 'high',
@@ -445,19 +445,16 @@ The following provider options are available:
 
 | Model                         | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      | Reasoning           |
 | ----------------------------- | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
-| `grok-4-1`                    | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `grok-4.20-reasoning`         | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `grok-4.20-non-reasoning`     | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
 | `grok-4-1-fast-reasoning`     | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `grok-4-1-fast-non-reasoning` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
-| `grok-4-fast-non-reasoning`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `grok-4-1`                    | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
 | `grok-4-fast-reasoning`       | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `grok-4-fast-non-reasoning`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
 | `grok-code-fast-1`            | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
-| `grok-4`                      | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
-| `grok-4-0709`                 | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
-| `grok-4-latest`               | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
 | `grok-3`                      | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
-| `grok-3-latest`               | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
 | `grok-3-mini`                 | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
-| `grok-3-mini-latest`          | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 
 <Note>
   The table above lists popular models. Please see the [xAI
@@ -516,7 +513,7 @@ const { images } = await generateImage({
 
 #### Multi-Image Editing
 
-Combine or reference multiple input images (up to 3) in the prompt:
+Combine or reference multiple input images in the prompt:
 
 ```ts
 import { xai } from '@ai-sdk/xai';
@@ -554,37 +551,53 @@ const { images } = await generateImage({
 
 <Note>
   Input images can be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`, or
-  base64-encoded strings. Up to 3 input images are supported per request.
+  base64-encoded strings.
 </Note>
 
-### Model-specific options
+### Image Provider Options
 
-You can customize the image generation behavior with model-specific settings:
+You can customize the image generation behavior with provider-specific settings via `providerOptions.xai`:
 
 ```ts
-import { xai } from '@ai-sdk/xai';
+import { xai, type XaiImageModelOptions } from '@ai-sdk/xai';
 import { generateImage } from 'ai';
 
 const { images } = await generateImage({
-  model: xai.image('grok-imagine-image'),
+  model: xai.image('grok-imagine-image-pro'),
   prompt: 'A futuristic cityscape at sunset',
   aspectRatio: '16:9',
-  n: 2,
+  providerOptions: {
+    xai: {
+      resolution: '2k',
+      quality: 'high',
+    } satisfies XaiImageModelOptions,
+  },
 });
 ```
 
-### Model Capabilities
+- **resolution** _'1k' | '2k'_
 
-| Model                | Aspect Ratios                                                                                               | Image Editing       |
-| -------------------- | ----------------------------------------------------------------------------------------------------------- | ------------------- |
-| `grok-imagine-image` | `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 size={18} /> |
+  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 size={18} /> |
+| `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 size={18} /> |
 
 ## 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 three video generation modes: text-to-video, image-to-video, and video editing.
+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
 
@@ -594,7 +607,7 @@ Generate videos from text prompts:
 import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
 import { experimental_generateVideo as generateVideo } from 'ai';
 
-const { videos } = await generateVideo({
+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',
@@ -607,15 +620,15 @@ const { videos } = await generateVideo({
 });
 ```
 
-### Image-to-Video
+### Generation with Image Input
 
-Generate videos using an image as the starting frame with an optional text prompt:
+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 { videos } = await generateVideo({
+const { video } = await generateVideo({
   model: xai.video('grok-imagine-video'),
   prompt: {
     image: 'https://example.com/start-frame.png',
@@ -638,11 +651,12 @@ Edit an existing video using a text prompt by providing a source video URL via p
 import { xai, type XaiVideoModelOptions } from '@ai-sdk/xai';
 import { experimental_generateVideo as generateVideo } from 'ai';
 
-const { videos } = await generateVideo({
+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,
@@ -668,6 +682,7 @@ import { experimental_generateVideo as generateVideo } from 'ai';
 
 const providerOptions = {
   xai: {
+    mode: 'edit-video',
     videoUrl: 'https://example.com/source-video.mp4',
     pollTimeoutMs: 600000,
   } satisfies XaiVideoModelOptions,
@@ -689,19 +704,99 @@ const [withSunglasses, withScarf] = await Promise.all([
     model: xai.video('grok-imagine-video'),
     prompt: 'Add sunglasses',
     providerOptions: {
-      xai: { videoUrl: step1VideoUrl, pollTimeoutMs: 600000 },
+      xai: { mode: 'edit-video', videoUrl: step1VideoUrl, pollTimeoutMs: 600000 },
     },
   }),
   generateVideo({
     model: xai.video('grok-imagine-video'),
     prompt: 'Add a scarf',
     providerOptions: {
-      xai: { videoUrl: step1VideoUrl, pollTimeoutMs: 600000 },
+      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.
+
+<Note>
+  Reference-to-video supports `duration`, `aspectRatio`, and `resolution`. Use
+  `mode` to select the operation — each mode is mutually exclusive.
+</Note>
+
 ### Video Provider Options
 
 The following provider options are available via `providerOptions.xai`.
@@ -721,10 +816,27 @@ You can validate the provider options using the `XaiVideoModelOptions` type.
   `1280x720` maps to `720p` and `854x480` maps to `480p`.
   Use this provider option to pass the native format directly.
 
+- **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 for video editing. When provided, the prompt is used
-  to describe the desired edits to the video.
+  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.
@@ -744,14 +856,21 @@ 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
+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      | Video Editing       |
-| -------------------- | -------- | ------------------------------------------------- | -------------- | ------------------- | ------------------- |
-| `grok-imagine-video` | 1–15s    | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3` | `480p`, `720p` | <Check size={18} /> | <Check size={18} /> |
+| 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 size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 
 <Note>
   You can also pass any available provider model ID as a string if needed.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/xai",
-  "version": "4.0.0-beta.21",
+  "version": "4.0.0-beta.24",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -29,9 +29,9 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/openai-compatible": "3.0.0-beta.13",
-    "@ai-sdk/provider": "4.0.0-beta.5",
-    "@ai-sdk/provider-utils": "5.0.0-beta.9"
+    "@ai-sdk/openai-compatible": "3.0.0-beta.15",
+    "@ai-sdk/provider": "4.0.0-beta.7",
+    "@ai-sdk/provider-utils": "5.0.0-beta.11"
   },
   "devDependencies": {
     "@types/node": "20.17.24",

package/src/convert-to-xai-chat-messages.ts

@@ -3,7 +3,11 @@ import {
   LanguageModelV4Prompt,
   UnsupportedFunctionalityError,
 } from '@ai-sdk/provider';
-import { convertToBase64 } from '@ai-sdk/provider-utils';
+import {
+  convertToBase64,
+  isProviderReference,
+  resolveProviderReference,
+} from '@ai-sdk/provider-utils';
 import { XaiChatPrompt } from './xai-chat-prompt';
 
 export function convertToXaiChatMessages(prompt: LanguageModelV4Prompt): {
@@ -34,6 +38,18 @@ export function convertToXaiChatMessages(prompt: LanguageModelV4Prompt): {
                 return { type: 'text', text: part.text };
               }
               case 'file': {
+                if (isProviderReference(part.data)) {
+                  return {
+                    type: 'file',
+                    file: {
+                      file_id: resolveProviderReference({
+                        reference: part.data,
+                        provider: 'xai',
+                      }),
+                    },
+                  };
+                }
+
                 if (part.mediaType.startsWith('image/')) {
                   const mediaType =
                     part.mediaType === 'image/*'

package/src/files/xai-files-api.ts

@@ -0,0 +1,16 @@
+import { lazySchema, zodSchema } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
+
+export const xaiFilesResponseSchema = lazySchema(() =>
+  zodSchema(
+    z.object({
+      id: z.string(),
+      object: z.string().nullish(),
+      bytes: z.number().nullish(),
+      created_at: z.number().nullish(),
+      filename: z.string().nullish(),
+      purpose: z.string().nullish(),
+      status: z.string().nullish(),
+    }),
+  ),
+);

package/src/files/xai-files-options.ts

@@ -0,0 +1,15 @@
+import { InferSchema, lazySchema, zodSchema } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
+
+export const xaiFilesOptionsSchema = lazySchema(() =>
+  zodSchema(
+    z
+      .object({
+        teamId: z.string().optional(),
+        filePath: z.string().optional(),
+      })
+      .passthrough(),
+  ),
+);
+
+export type XaiFilesOptions = InferSchema<typeof xaiFilesOptionsSchema>;

package/src/files/xai-files.ts

@@ -0,0 +1,93 @@
+import {
+  FilesV4,
+  FilesV4UploadFileCallOptions,
+  FilesV4UploadFileResult,
+} from '@ai-sdk/provider';
+import {
+  combineHeaders,
+  convertBase64ToUint8Array,
+  createJsonResponseHandler,
+  FetchFunction,
+  parseProviderOptions,
+  postFormDataToApi,
+} from '@ai-sdk/provider-utils';
+import { xaiFailedResponseHandler } from '../xai-error';
+import { xaiFilesResponseSchema } from './xai-files-api';
+import { xaiFilesOptionsSchema, XaiFilesOptions } from './xai-files-options';
+
+interface XaiFilesConfig {
+  provider: string;
+  baseURL: string | undefined;
+  headers: () => Record<string, string | undefined>;
+  fetch?: FetchFunction;
+}
+
+export class XaiFiles implements FilesV4 {
+  readonly specificationVersion = 'v4';
+
+  get provider(): string {
+    return this.config.provider;
+  }
+
+  constructor(private readonly config: XaiFilesConfig) {}
+
+  async uploadFile({
+    data,
+    mediaType,
+    filename,
+    providerOptions,
+  }: FilesV4UploadFileCallOptions): Promise<FilesV4UploadFileResult> {
+    const xaiOptions = (await parseProviderOptions({
+      provider: 'xai',
+      providerOptions,
+      schema: xaiFilesOptionsSchema,
+    })) as XaiFilesOptions | undefined;
+
+    const fileBytes =
+      data instanceof Uint8Array ? data : convertBase64ToUint8Array(data);
+
+    const blob = new Blob([fileBytes], {
+      type: mediaType,
+    });
+
+    const formData = new FormData();
+    if (filename != null) {
+      formData.append('file', blob, filename);
+    } else {
+      formData.append('file', blob);
+    }
+
+    if (xaiOptions?.teamId != null) {
+      formData.append('team_id', xaiOptions.teamId);
+    }
+
+    const { value: response } = await postFormDataToApi({
+      url: `${this.config.baseURL}/files`,
+      headers: combineHeaders(this.config.headers()),
+      formData,
+      failedResponseHandler: xaiFailedResponseHandler,
+      successfulResponseHandler: createJsonResponseHandler(
+        xaiFilesResponseSchema,
+      ),
+      fetch: this.config.fetch,
+    });
+
+    return {
+      warnings: [],
+      providerReference: { xai: response.id },
+      ...((response.filename ?? filename)
+        ? { filename: response.filename ?? filename }
+        : {}),
+      ...(mediaType != null ? { mediaType } : {}),
+      providerMetadata: {
+        xai: {
+          ...(response.filename != null ? { filename: response.filename } : {}),
+          ...(response.bytes != null ? { bytes: response.bytes } : {}),
+          ...(response.created_at != null
+            ? { createdAt: response.created_at }
+            : {}),
+        },
+      },
+    };
+  }
+}

package/src/index.ts

@@ -20,6 +20,7 @@ export type {
   /** @deprecated Use `XaiVideoModelOptions` instead. */
   XaiVideoModelOptions as XaiVideoProviderOptions,
 } from './xai-video-options';
+export type { XaiFilesOptions } from './files/xai-files-options';
 export { createXai, xai } from './xai-provider';
 export type { XaiProvider, XaiProviderSettings } from './xai-provider';
 export {

package/src/responses/convert-to-xai-responses-input.ts

@@ -3,7 +3,11 @@ import {
   LanguageModelV4Message,
   UnsupportedFunctionalityError,
 } from '@ai-sdk/provider';
-import { convertToBase64 } from '@ai-sdk/provider-utils';
+import {
+  convertToBase64,
+  isProviderReference,
+  resolveProviderReference,
+} from '@ai-sdk/provider-utils';
 import {
   XaiResponsesInput,
   XaiResponsesUserMessageContentPart,
@@ -42,7 +46,15 @@ export async function convertToXaiResponsesInput({
             }
 
             case 'file': {
-              if (block.mediaType.startsWith('image/')) {
+              if (isProviderReference(block.data)) {
+                contentParts.push({
+                  type: 'input_file',
+                  file_id: resolveProviderReference({
+                    reference: block.data,
+                    provider: 'xai',
+                  }),
+                });
+              } else if (block.mediaType.startsWith('image/')) {
                 const mediaType =
                   block.mediaType === 'image/*'
                     ? 'image/jpeg'

package/src/responses/xai-responses-api.ts

@@ -26,7 +26,8 @@ export type XaiResponsesSystemMessage = {
 
 export type XaiResponsesUserMessageContentPart =
   | { type: 'input_text'; text: string }
-  | { type: 'input_image'; image_url: string };
+  | { type: 'input_image'; image_url: string }
+  | { type: 'input_file'; file_id: string };
 
 export type XaiResponsesUserMessage = {
   role: 'user';

package/src/xai-chat-prompt.ts

@@ -18,7 +18,8 @@ export interface XaiUserMessage {
 
 export type XaiUserMessageContent =
   | { type: 'text'; text: string }
-  | { type: 'image_url'; image_url: { url: string } };
+  | { type: 'image_url'; image_url: { url: string } }
+  | { type: 'file'; file: { file_id: string } };
 
 export interface XaiAssistantMessage {
   role: 'assistant';