@ai-sdk/provider 4.0.0-canary.18 → 4.0.1

package/CHANGELOG.md

@@ -1,5 +1,65 @@
 # @ai-sdk/provider
 
+## 4.0.1
+
+### Patch Changes
+
+- 0274f34: feat (video): add first-class `frameImages` and `inputReferences` call options for video generation
+
+## 4.0.0
+
+### Major Changes
+
+- f7d4f01: feat(provider): add support for `reasoning-file` type for files that are part of reasoning
+- 776b617: feat(provider): adding new 'custom' content type
+- 34bd95d: feat(ai): add support for uploading provider skills using the provider references abstraction
+- ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only (`"type": "module"`). Consumers using `require()` must switch to ESM `import` syntax.
+- c29a26f: feat(provider): add support for provider references and uploading files as supported per provider
+- 3887c70: feat(provider): add new top-level reasoning parameter to spec and support it in `generateText` and `streamText`
+- 9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type
+- 8359612: Start v7 pre-release
+- 5463d0d: feat(provider): align tool result output content file part types with top-level message file part types
+
+### Patch Changes
+
+- 1f509d4: fix(ai): force template check on 'kind' param
+- 176466a: chore(provider): align V4 model return types to have their own definitions across all model interfaces
+- 5c2a5a2: fix(provider): fix v4 spec to not use shared v3 types
+- 9f0e36c: trigger release for all packages after provenance setup
+- 008271d: feat(openai-compatible): emit warning when using kebab-case instead of camelCase
+- 7fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.
+- 0c4c275: trigger initial canary release
+- 6fd51c0: fix(provider): preserve error type prefix in getErrorMessage
+- ce769dd: feat(provider): add experimental Realtime API support for voice conversations
+
+  Adds first-class support for realtime (speech-to-speech) APIs:
+
+  - `Experimental_RealtimeModelV4` spec in `@ai-sdk/provider` with normalized event types and factory
+  - OpenAI, Google, and xAI realtime provider implementations
+  - `openai.experimental_realtime()` / `google.experimental_realtime()` / `xai.experimental_realtime()` work in both server and browser
+  - `.getToken()` static method on each provider for server-side ephemeral token creation
+  - `experimental_getRealtimeToolDefinitions` helper for provider session tool definitions
+  - `experimental_useRealtime` hook in `@ai-sdk/react` returning `UIMessage[]` (aligned with `useChat`), with `onToolCall` and `addToolOutput` for client-driven tool execution
+  - `inputAudioTranscription` session config for showing transcribed user audio messages when supported by the provider
+
+- e311194: feat(ai): allow passing provider instance to `uploadFile` and `uploadSkill` as shorthand
+- 258c093: chore: ensure consistent import handling and avoid import duplicates or cycles
+- b8396f0: trigger initial beta release
+- 0416e3e: feat (video): add first-class `generateAudio` call option
+- ff5eba1: feat: roll `image-*` tool output types into their equivalent `file-*` types
+
+## 4.0.0-beta.20
+
+### Patch Changes
+
+- 0416e3e: feat (video): add first-class `generateAudio` call option
+
+## 4.0.0-beta.19
+
+### Patch Changes
+
+- b8396f0: trigger initial beta release
+
 ## 4.0.0-canary.18
 
 ### Patch Changes

package/dist/index.d.ts

@@ -6730,6 +6730,27 @@ type VideoModelV4File = {
     providerOptions?: SharedV4ProviderMetadata;
 };
 
+/**
+ * The role a frame image plays in video generation.
+ *
+ * - `first_frame`: the starting frame the model animates from
+ * - `last_frame`: the ending frame the model animates towards
+ */
+type VideoModelV4FrameType = 'first_frame' | 'last_frame';
+/**
+ * A role-tagged image input for image-to-video and first-last-frame generation.
+ */
+type VideoModelV4FrameImage = {
+    /**
+     * The image file used for this frame.
+     */
+    image: VideoModelV4File;
+    /**
+     * Which frame this image represents.
+     */
+    frameType: VideoModelV4FrameType;
+};
+
 type VideoModelV4CallOptions = {
     /**
      * Text prompt for the video generation.
@@ -6775,6 +6796,20 @@ type VideoModelV4CallOptions = {
      * The image serves as the starting frame that the model will animate.
      */
     image: VideoModelV4File | undefined;
+    /**
+     * Role-tagged image inputs for first-last-frame generation.
+     * Each entry declares whether it is the `first_frame` or the
+     * `last_frame` of the generated video.
+     */
+    frameImages: Array<VideoModelV4FrameImage> | undefined;
+    /**
+     * Reference image inputs for reference-to-video generation.
+     */
+    inputReferences: Array<VideoModelV4File> | undefined;
+    /**
+     * Whether the model should generate audio alongside the video.
+     */
+    generateAudio: boolean | undefined;
     /**
      * Additional provider-specific options that are passed through to the provider
      * as body parameters.
@@ -6951,6 +6986,27 @@ type VideoModelV3File = {
     providerOptions?: SharedV3ProviderMetadata;
 };
 
+/**
+ * The role a frame image plays in video generation.
+ *
+ * - `first_frame`: the starting frame the model animates from
+ * - `last_frame`: the ending frame the model animates towards
+ */
+type VideoModelV3FrameType = 'first_frame' | 'last_frame';
+/**
+ * A role-tagged image input for image-to-video and first-last-frame generation.
+ */
+type VideoModelV3FrameImage = {
+    /**
+     * The image file used for this frame.
+     */
+    image: VideoModelV3File;
+    /**
+     * Which frame this image represents.
+     */
+    frameType: VideoModelV3FrameType;
+};
+
 type VideoModelV3CallOptions = {
     /**
      * Text prompt for the video generation.
@@ -6996,6 +7052,20 @@ type VideoModelV3CallOptions = {
      * The image serves as the starting frame that the model will animate.
      */
     image: VideoModelV3File | undefined;
+    /**
+     * Role-tagged image inputs for first-last-frame generation.
+     * Each entry declares whether it is the `first_frame` or the
+     * `last_frame` of the generated video.
+     */
+    frameImages: Array<VideoModelV3FrameImage> | undefined;
+    /**
+     * Reference image inputs for reference-to-video generation.
+     */
+    inputReferences: Array<VideoModelV3File> | undefined;
+    /**
+     * Whether the model should generate audio alongside the video.
+     */
+    generateAudio: boolean | undefined;
     /**
      * Additional provider-specific options that are passed through to the provider
      * as body parameters.
@@ -7135,4 +7205,4 @@ type VideoModelV3 = {
     }>;
 };
 
-export { AISDKError, APICallError, type EmbeddingModelV2, type EmbeddingModelV2Embedding, type EmbeddingModelV3, type EmbeddingModelV3CallOptions, type EmbeddingModelV3Embedding, type EmbeddingModelV3Middleware, type EmbeddingModelV3Result, type EmbeddingModelV4, type EmbeddingModelV4CallOptions, type EmbeddingModelV4Embedding, type EmbeddingModelV4Middleware, type EmbeddingModelV4Result, EmptyResponseBodyError, type RealtimeFactoryV4 as Experimental_RealtimeFactoryV4, type RealtimeFactoryV4GetTokenOptions as Experimental_RealtimeFactoryV4GetTokenOptions, type RealtimeFactoryV4GetTokenResult as Experimental_RealtimeFactoryV4GetTokenResult, type RealtimeModelV4 as Experimental_RealtimeModelV4, type RealtimeModelV4AudioMessage as Experimental_RealtimeModelV4AudioMessage, type RealtimeModelV4ClientEvent as Experimental_RealtimeModelV4ClientEvent, type RealtimeModelV4ClientSecretOptions as Experimental_RealtimeModelV4ClientSecretOptions, type RealtimeModelV4ClientSecretResult as Experimental_RealtimeModelV4ClientSecretResult, type RealtimeModelV4ConversationItem as Experimental_RealtimeModelV4ConversationItem, type RealtimeModelV4FunctionCallOutput as Experimental_RealtimeModelV4FunctionCallOutput, type RealtimeModelV4ServerEvent as Experimental_RealtimeModelV4ServerEvent, type RealtimeModelV4SessionConfig as Experimental_RealtimeModelV4SessionConfig, type RealtimeModelV4TextMessage as Experimental_RealtimeModelV4TextMessage, type RealtimeModelV4ToolDefinition as Experimental_RealtimeModelV4ToolDefinition, type VideoModelV3 as Experimental_VideoModelV3, type VideoModelV3CallOptions as Experimental_VideoModelV3CallOptions, type VideoModelV3File as Experimental_VideoModelV3File, type VideoModelV3VideoData as Experimental_VideoModelV3VideoData, type VideoModelV4 as Experimental_VideoModelV4, type VideoModelV4CallOptions as Experimental_VideoModelV4CallOptions, type VideoModelV4File as Experimental_VideoModelV4File, type VideoModelV4Result as Experimental_VideoModelV4Result, type VideoModelV4VideoData as Experimental_VideoModelV4VideoData, type FilesV4, type FilesV4UploadFileCallOptions, type FilesV4UploadFileResult, type ImageModelV2, type ImageModelV2CallOptions, type ImageModelV2CallWarning, type ImageModelV2ProviderMetadata, type ImageModelV3, type ImageModelV3CallOptions, type ImageModelV3File, type ImageModelV3Middleware, type ImageModelV3ProviderMetadata, type ImageModelV3Usage, type ImageModelV4, type ImageModelV4CallOptions, type ImageModelV4File, type ImageModelV4Middleware, type ImageModelV4ProviderMetadata, type ImageModelV4Result, type ImageModelV4Usage, InvalidArgumentError, InvalidPromptError, InvalidResponseDataError, type JSONArray, type JSONObject, JSONParseError, type JSONValue, type LanguageModelV2, type LanguageModelV2CallOptions, type LanguageModelV2CallWarning, type LanguageModelV2Content, type LanguageModelV2DataContent, type LanguageModelV2File, type LanguageModelV2FilePart, type LanguageModelV2FinishReason, type LanguageModelV2FunctionTool, type LanguageModelV2Message, type LanguageModelV2Middleware, type LanguageModelV2Prompt, type LanguageModelV2ProviderDefinedTool, type LanguageModelV2Reasoning, type LanguageModelV2ReasoningPart, type LanguageModelV2ResponseMetadata, type LanguageModelV2Source, type LanguageModelV2StreamPart, type LanguageModelV2Text, type LanguageModelV2TextPart, type LanguageModelV2ToolCall, type LanguageModelV2ToolCallPart, type LanguageModelV2ToolChoice, type LanguageModelV2ToolResultOutput, type LanguageModelV2ToolResultPart, type LanguageModelV2Usage, type LanguageModelV3, type LanguageModelV3CallOptions, type LanguageModelV3Content, type LanguageModelV3DataContent, type LanguageModelV3File, type LanguageModelV3FilePart, type LanguageModelV3FinishReason, type LanguageModelV3FunctionTool, type LanguageModelV3GenerateResult, type LanguageModelV3Message, type LanguageModelV3Middleware, type LanguageModelV3Prompt, type LanguageModelV3ProviderTool, type LanguageModelV3Reasoning, type LanguageModelV3ReasoningPart, type LanguageModelV3ResponseMetadata, type LanguageModelV3Source, type LanguageModelV3StreamPart, type LanguageModelV3StreamResult, type LanguageModelV3Text, type LanguageModelV3TextPart, type LanguageModelV3ToolApprovalRequest, type LanguageModelV3ToolApprovalResponsePart, type LanguageModelV3ToolCall, type LanguageModelV3ToolCallPart, type LanguageModelV3ToolChoice, type LanguageModelV3ToolResult, type LanguageModelV3ToolResultOutput, type LanguageModelV3ToolResultPart, type LanguageModelV3Usage, type LanguageModelV4, type LanguageModelV4CallOptions, type LanguageModelV4Content, type LanguageModelV4CustomContent, type LanguageModelV4CustomPart, type LanguageModelV4File, type LanguageModelV4FilePart, type LanguageModelV4FinishReason, type LanguageModelV4FunctionTool, type LanguageModelV4GenerateResult, type LanguageModelV4Message, type LanguageModelV4Middleware, type LanguageModelV4Prompt, type LanguageModelV4ProviderTool, type LanguageModelV4Reasoning, type LanguageModelV4ReasoningFile, type LanguageModelV4ReasoningFilePart, type LanguageModelV4ReasoningPart, type LanguageModelV4ResponseMetadata, type LanguageModelV4Source, type LanguageModelV4StreamPart, type LanguageModelV4StreamResult, type LanguageModelV4Text, type LanguageModelV4TextPart, type LanguageModelV4ToolApprovalRequest, type LanguageModelV4ToolApprovalResponsePart, type LanguageModelV4ToolCall, type LanguageModelV4ToolCallPart, type LanguageModelV4ToolChoice, type LanguageModelV4ToolResult, type LanguageModelV4ToolResultOutput, type LanguageModelV4ToolResultPart, type LanguageModelV4Usage, LoadAPIKeyError, LoadSettingError, NoContentGeneratedError, NoSuchModelError, NoSuchProviderReferenceError, type ProviderV2, type ProviderV3, type ProviderV4, type RerankingModelV3, type RerankingModelV3CallOptions, type RerankingModelV4, type RerankingModelV4CallOptions, type RerankingModelV4Result, type SharedV2Headers, type SharedV2ProviderMetadata, type SharedV2ProviderOptions, type SharedV3Headers, type SharedV3ProviderMetadata, type SharedV3ProviderOptions, type SharedV3Warning, type SharedV4FileData, type SharedV4FileDataData, type SharedV4FileDataReference, type SharedV4FileDataText, type SharedV4FileDataUrl, type SharedV4Headers, type SharedV4ProviderMetadata, type SharedV4ProviderOptions, type SharedV4ProviderReference, type SharedV4Warning, type SkillsV4, type SkillsV4File, type SkillsV4UploadSkillCallOptions, type SkillsV4UploadSkillResult, type SpeechModelV2, type SpeechModelV2CallOptions, type SpeechModelV2CallWarning, type SpeechModelV3, type SpeechModelV3CallOptions, type SpeechModelV4, type SpeechModelV4CallOptions, type SpeechModelV4Result, TooManyEmbeddingValuesForCallError, type TranscriptionModelV2, type TranscriptionModelV2CallOptions, type TranscriptionModelV2CallWarning, type TranscriptionModelV3, type TranscriptionModelV3CallOptions, type TranscriptionModelV4, type TranscriptionModelV4CallOptions, type TranscriptionModelV4Result, type TypeValidationContext, TypeValidationError, UnsupportedFunctionalityError, getErrorMessage, isJSONArray, isJSONObject, isJSONValue };
+export { AISDKError, APICallError, type EmbeddingModelV2, type EmbeddingModelV2Embedding, type EmbeddingModelV3, type EmbeddingModelV3CallOptions, type EmbeddingModelV3Embedding, type EmbeddingModelV3Middleware, type EmbeddingModelV3Result, type EmbeddingModelV4, type EmbeddingModelV4CallOptions, type EmbeddingModelV4Embedding, type EmbeddingModelV4Middleware, type EmbeddingModelV4Result, EmptyResponseBodyError, type RealtimeFactoryV4 as Experimental_RealtimeFactoryV4, type RealtimeFactoryV4GetTokenOptions as Experimental_RealtimeFactoryV4GetTokenOptions, type RealtimeFactoryV4GetTokenResult as Experimental_RealtimeFactoryV4GetTokenResult, type RealtimeModelV4 as Experimental_RealtimeModelV4, type RealtimeModelV4AudioMessage as Experimental_RealtimeModelV4AudioMessage, type RealtimeModelV4ClientEvent as Experimental_RealtimeModelV4ClientEvent, type RealtimeModelV4ClientSecretOptions as Experimental_RealtimeModelV4ClientSecretOptions, type RealtimeModelV4ClientSecretResult as Experimental_RealtimeModelV4ClientSecretResult, type RealtimeModelV4ConversationItem as Experimental_RealtimeModelV4ConversationItem, type RealtimeModelV4FunctionCallOutput as Experimental_RealtimeModelV4FunctionCallOutput, type RealtimeModelV4ServerEvent as Experimental_RealtimeModelV4ServerEvent, type RealtimeModelV4SessionConfig as Experimental_RealtimeModelV4SessionConfig, type RealtimeModelV4TextMessage as Experimental_RealtimeModelV4TextMessage, type RealtimeModelV4ToolDefinition as Experimental_RealtimeModelV4ToolDefinition, type VideoModelV3 as Experimental_VideoModelV3, type VideoModelV3CallOptions as Experimental_VideoModelV3CallOptions, type VideoModelV3File as Experimental_VideoModelV3File, type VideoModelV3FrameImage as Experimental_VideoModelV3FrameImage, type VideoModelV3FrameType as Experimental_VideoModelV3FrameType, type VideoModelV3VideoData as Experimental_VideoModelV3VideoData, type VideoModelV4 as Experimental_VideoModelV4, type VideoModelV4CallOptions as Experimental_VideoModelV4CallOptions, type VideoModelV4File as Experimental_VideoModelV4File, type VideoModelV4FrameImage as Experimental_VideoModelV4FrameImage, type VideoModelV4FrameType as Experimental_VideoModelV4FrameType, type VideoModelV4Result as Experimental_VideoModelV4Result, type VideoModelV4VideoData as Experimental_VideoModelV4VideoData, type FilesV4, type FilesV4UploadFileCallOptions, type FilesV4UploadFileResult, type ImageModelV2, type ImageModelV2CallOptions, type ImageModelV2CallWarning, type ImageModelV2ProviderMetadata, type ImageModelV3, type ImageModelV3CallOptions, type ImageModelV3File, type ImageModelV3Middleware, type ImageModelV3ProviderMetadata, type ImageModelV3Usage, type ImageModelV4, type ImageModelV4CallOptions, type ImageModelV4File, type ImageModelV4Middleware, type ImageModelV4ProviderMetadata, type ImageModelV4Result, type ImageModelV4Usage, InvalidArgumentError, InvalidPromptError, InvalidResponseDataError, type JSONArray, type JSONObject, JSONParseError, type JSONValue, type LanguageModelV2, type LanguageModelV2CallOptions, type LanguageModelV2CallWarning, type LanguageModelV2Content, type LanguageModelV2DataContent, type LanguageModelV2File, type LanguageModelV2FilePart, type LanguageModelV2FinishReason, type LanguageModelV2FunctionTool, type LanguageModelV2Message, type LanguageModelV2Middleware, type LanguageModelV2Prompt, type LanguageModelV2ProviderDefinedTool, type LanguageModelV2Reasoning, type LanguageModelV2ReasoningPart, type LanguageModelV2ResponseMetadata, type LanguageModelV2Source, type LanguageModelV2StreamPart, type LanguageModelV2Text, type LanguageModelV2TextPart, type LanguageModelV2ToolCall, type LanguageModelV2ToolCallPart, type LanguageModelV2ToolChoice, type LanguageModelV2ToolResultOutput, type LanguageModelV2ToolResultPart, type LanguageModelV2Usage, type LanguageModelV3, type LanguageModelV3CallOptions, type LanguageModelV3Content, type LanguageModelV3DataContent, type LanguageModelV3File, type LanguageModelV3FilePart, type LanguageModelV3FinishReason, type LanguageModelV3FunctionTool, type LanguageModelV3GenerateResult, type LanguageModelV3Message, type LanguageModelV3Middleware, type LanguageModelV3Prompt, type LanguageModelV3ProviderTool, type LanguageModelV3Reasoning, type LanguageModelV3ReasoningPart, type LanguageModelV3ResponseMetadata, type LanguageModelV3Source, type LanguageModelV3StreamPart, type LanguageModelV3StreamResult, type LanguageModelV3Text, type LanguageModelV3TextPart, type LanguageModelV3ToolApprovalRequest, type LanguageModelV3ToolApprovalResponsePart, type LanguageModelV3ToolCall, type LanguageModelV3ToolCallPart, type LanguageModelV3ToolChoice, type LanguageModelV3ToolResult, type LanguageModelV3ToolResultOutput, type LanguageModelV3ToolResultPart, type LanguageModelV3Usage, type LanguageModelV4, type LanguageModelV4CallOptions, type LanguageModelV4Content, type LanguageModelV4CustomContent, type LanguageModelV4CustomPart, type LanguageModelV4File, type LanguageModelV4FilePart, type LanguageModelV4FinishReason, type LanguageModelV4FunctionTool, type LanguageModelV4GenerateResult, type LanguageModelV4Message, type LanguageModelV4Middleware, type LanguageModelV4Prompt, type LanguageModelV4ProviderTool, type LanguageModelV4Reasoning, type LanguageModelV4ReasoningFile, type LanguageModelV4ReasoningFilePart, type LanguageModelV4ReasoningPart, type LanguageModelV4ResponseMetadata, type LanguageModelV4Source, type LanguageModelV4StreamPart, type LanguageModelV4StreamResult, type LanguageModelV4Text, type LanguageModelV4TextPart, type LanguageModelV4ToolApprovalRequest, type LanguageModelV4ToolApprovalResponsePart, type LanguageModelV4ToolCall, type LanguageModelV4ToolCallPart, type LanguageModelV4ToolChoice, type LanguageModelV4ToolResult, type LanguageModelV4ToolResultOutput, type LanguageModelV4ToolResultPart, type LanguageModelV4Usage, LoadAPIKeyError, LoadSettingError, NoContentGeneratedError, NoSuchModelError, NoSuchProviderReferenceError, type ProviderV2, type ProviderV3, type ProviderV4, type RerankingModelV3, type RerankingModelV3CallOptions, type RerankingModelV4, type RerankingModelV4CallOptions, type RerankingModelV4Result, type SharedV2Headers, type SharedV2ProviderMetadata, type SharedV2ProviderOptions, type SharedV3Headers, type SharedV3ProviderMetadata, type SharedV3ProviderOptions, type SharedV3Warning, type SharedV4FileData, type SharedV4FileDataData, type SharedV4FileDataReference, type SharedV4FileDataText, type SharedV4FileDataUrl, type SharedV4Headers, type SharedV4ProviderMetadata, type SharedV4ProviderOptions, type SharedV4ProviderReference, type SharedV4Warning, type SkillsV4, type SkillsV4File, type SkillsV4UploadSkillCallOptions, type SkillsV4UploadSkillResult, type SpeechModelV2, type SpeechModelV2CallOptions, type SpeechModelV2CallWarning, type SpeechModelV3, type SpeechModelV3CallOptions, type SpeechModelV4, type SpeechModelV4CallOptions, type SpeechModelV4Result, TooManyEmbeddingValuesForCallError, type TranscriptionModelV2, type TranscriptionModelV2CallOptions, type TranscriptionModelV2CallWarning, type TranscriptionModelV3, type TranscriptionModelV3CallOptions, type TranscriptionModelV4, type TranscriptionModelV4CallOptions, type TranscriptionModelV4Result, type TypeValidationContext, TypeValidationError, UnsupportedFunctionalityError, getErrorMessage, isJSONArray, isJSONObject, isJSONValue };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/provider",
-  "version": "4.0.0-canary.18",
+  "version": "4.0.1",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,

package/src/video-model/v3/index.ts

@@ -4,3 +4,7 @@ export type {
 } from './video-model-v3';
 export type { VideoModelV3CallOptions as Experimental_VideoModelV3CallOptions } from './video-model-v3-call-options';
 export type { VideoModelV3File as Experimental_VideoModelV3File } from './video-model-v3-file';
+export type {
+  VideoModelV3FrameImage as Experimental_VideoModelV3FrameImage,
+  VideoModelV3FrameType as Experimental_VideoModelV3FrameType,
+} from './video-model-v3-frame-image';

package/src/video-model/v3/video-model-v3-call-options.ts

@@ -1,5 +1,6 @@
 import type { SharedV3ProviderOptions } from '../../shared';
 import type { VideoModelV3File } from './video-model-v3-file';
+import type { VideoModelV3FrameImage } from './video-model-v3-frame-image';
 
 export type VideoModelV3CallOptions = {
   /**
@@ -54,6 +55,23 @@ export type VideoModelV3CallOptions = {
    */
   image: VideoModelV3File | undefined;
 
+  /**
+   * Role-tagged image inputs for first-last-frame generation.
+   * Each entry declares whether it is the `first_frame` or the
+   * `last_frame` of the generated video.
+   */
+  frameImages: Array<VideoModelV3FrameImage> | undefined;
+
+  /**
+   * Reference image inputs for reference-to-video generation.
+   */
+  inputReferences: Array<VideoModelV3File> | undefined;
+
+  /**
+   * Whether the model should generate audio alongside the video.
+   */
+  generateAudio: boolean | undefined;
+
   /**
    * Additional provider-specific options that are passed through to the provider
    * as body parameters.

package/src/video-model/v3/video-model-v3-frame-image.ts

@@ -0,0 +1,24 @@
+import type { VideoModelV3File } from './video-model-v3-file';
+
+/**
+ * The role a frame image plays in video generation.
+ *
+ * - `first_frame`: the starting frame the model animates from
+ * - `last_frame`: the ending frame the model animates towards
+ */
+export type VideoModelV3FrameType = 'first_frame' | 'last_frame';
+
+/**
+ * A role-tagged image input for image-to-video and first-last-frame generation.
+ */
+export type VideoModelV3FrameImage = {
+  /**
+   * The image file used for this frame.
+   */
+  image: VideoModelV3File;
+
+  /**
+   * Which frame this image represents.
+   */
+  frameType: VideoModelV3FrameType;
+};

package/src/video-model/v4/index.ts

@@ -5,3 +5,7 @@ export type {
   VideoModelV4VideoData as Experimental_VideoModelV4VideoData,
 } from './video-model-v4-result';
 export type { VideoModelV4File as Experimental_VideoModelV4File } from './video-model-v4-file';
+export type {
+  VideoModelV4FrameImage as Experimental_VideoModelV4FrameImage,
+  VideoModelV4FrameType as Experimental_VideoModelV4FrameType,
+} from './video-model-v4-frame-image';

package/src/video-model/v4/video-model-v4-call-options.ts

@@ -1,5 +1,6 @@
 import type { SharedV4ProviderOptions } from '../../shared';
 import type { VideoModelV4File } from './video-model-v4-file';
+import type { VideoModelV4FrameImage } from './video-model-v4-frame-image';
 
 export type VideoModelV4CallOptions = {
   /**
@@ -54,6 +55,23 @@ export type VideoModelV4CallOptions = {
    */
   image: VideoModelV4File | undefined;
 
+  /**
+   * Role-tagged image inputs for first-last-frame generation.
+   * Each entry declares whether it is the `first_frame` or the
+   * `last_frame` of the generated video.
+   */
+  frameImages: Array<VideoModelV4FrameImage> | undefined;
+
+  /**
+   * Reference image inputs for reference-to-video generation.
+   */
+  inputReferences: Array<VideoModelV4File> | undefined;
+
+  /**
+   * Whether the model should generate audio alongside the video.
+   */
+  generateAudio: boolean | undefined;
+
   /**
    * Additional provider-specific options that are passed through to the provider
    * as body parameters.

package/src/video-model/v4/video-model-v4-frame-image.ts

@@ -0,0 +1,24 @@
+import type { VideoModelV4File } from './video-model-v4-file';
+
+/**
+ * The role a frame image plays in video generation.
+ *
+ * - `first_frame`: the starting frame the model animates from
+ * - `last_frame`: the ending frame the model animates towards
+ */
+export type VideoModelV4FrameType = 'first_frame' | 'last_frame';
+
+/**
+ * A role-tagged image input for image-to-video and first-last-frame generation.
+ */
+export type VideoModelV4FrameImage = {
+  /**
+   * The image file used for this frame.
+   */
+  image: VideoModelV4File;
+
+  /**
+   * Which frame this image represents.
+   */
+  frameType: VideoModelV4FrameType;
+};