@ai-sdk/openai 2.0.41 → 2.0.43

package/dist/internal/index.d.mts

@@ -129,7 +129,7 @@ declare class OpenAIEmbeddingModel implements EmbeddingModelV2<string> {
     doEmbed({ values, headers, abortSignal, providerOptions, }: Parameters<EmbeddingModelV2<string>['doEmbed']>[0]): Promise<Awaited<ReturnType<EmbeddingModelV2<string>['doEmbed']>>>;
 }
 
-type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
+type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | 'gpt-image-1' | 'gpt-image-1-mini' | (string & {});
 declare const modelMaxImagesPerCall: Record<OpenAIImageModelId, number>;
 declare const hasDefaultResponseFormat: Set<string>;
 
@@ -203,7 +203,7 @@ declare class OpenAISpeechModel implements SpeechModelV2 {
     doGenerate(options: Parameters<SpeechModelV2['doGenerate']>[0]): Promise<Awaited<ReturnType<SpeechModelV2['doGenerate']>>>;
 }
 
-type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4' | 'gpt-4-0613' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
+type OpenAIResponsesModelId = 'chatgpt-4o-latest' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4-0613' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1' | 'gpt-4' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini' | 'gpt-4o' | 'gpt-5-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-5-mini-2025-08-07' | 'gpt-5-mini' | 'gpt-5-nano-2025-08-07' | 'gpt-5-nano' | 'gpt-5-pro-2025-10-06' | 'gpt-5-pro' | 'gpt-5' | 'o1-2024-12-17' | 'o1' | 'o3-2025-04-16' | 'o3-mini-2025-01-31' | 'o3-mini' | 'o3' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV2 {
     readonly specificationVersion = "v2";
@@ -458,4 +458,103 @@ declare const fileSearch: _ai_sdk_provider_utils.ProviderDefinedToolFactoryWithO
     filters?: OpenAIResponsesFileSearchToolComparisonFilter | OpenAIResponsesFileSearchToolCompoundFilter;
 }>;
 
-export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };
+declare const imageGenerationArgsSchema: z.ZodObject<{
+    background: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        opaque: "opaque";
+        transparent: "transparent";
+    }>>;
+    inputFidelity: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        high: "high";
+    }>>;
+    inputImageMask: z.ZodOptional<z.ZodObject<{
+        fileId: z.ZodOptional<z.ZodString>;
+        imageUrl: z.ZodOptional<z.ZodString>;
+    }, z.core.$strip>>;
+    model: z.ZodOptional<z.ZodString>;
+    moderation: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+    }>>;
+    outputCompression: z.ZodOptional<z.ZodNumber>;
+    outputFormat: z.ZodOptional<z.ZodEnum<{
+        png: "png";
+        jpeg: "jpeg";
+        webp: "webp";
+    }>>;
+    quality: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        medium: "medium";
+        high: "high";
+        auto: "auto";
+    }>>;
+    size: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        "1024x1024": "1024x1024";
+        "1024x1536": "1024x1536";
+        "1536x1024": "1536x1024";
+    }>>;
+}, z.core.$strict>;
+declare const imageGenerationOutputSchema: z.ZodObject<{
+    result: z.ZodString;
+}, z.core.$strip>;
+type ImageGenerationArgs = {
+    /**
+     * Background type for the generated image. Default is 'auto'.
+     */
+    background?: 'auto' | 'opaque' | 'transparent';
+    /**
+     * Input fidelity for the generated image. Default is 'low'.
+     */
+    inputFidelity?: 'low' | 'high';
+    /**
+     * Optional mask for inpainting.
+     * Contains image_url (string, optional) and file_id (string, optional).
+     */
+    inputImageMask?: {
+        /**
+         * File ID for the mask image.
+         */
+        fileId?: string;
+        /**
+         * Base64-encoded mask image.
+         */
+        imageUrl?: string;
+    };
+    /**
+     * The image generation model to use. Default: gpt-image-1.
+     */
+    model?: string;
+    /**
+     * Moderation level for the generated image. Default: auto.
+     */
+    moderation?: 'auto';
+    /**
+     * Compression level for the output image. Default: 100.
+     */
+    outputCompression?: number;
+    /**
+     * The output format of the generated image. One of png, webp, or jpeg.
+     * Default: png
+     */
+    outputFormat?: 'png' | 'jpeg' | 'webp';
+    /**
+     * The quality of the generated image.
+     * One of low, medium, high, or auto. Default: auto.
+     */
+    quality?: 'auto' | 'low' | 'medium' | 'high';
+    /**
+     * The size of the generated image.
+     * One of 1024x1024, 1024x1536, 1536x1024, or auto.
+     * Default: auto.
+     */
+    size?: 'auto' | '1024x1024' | '1024x1536' | '1536x1024';
+};
+declare const imageGeneration: (args?: ImageGenerationArgs) => _ai_sdk_provider_utils.Tool<{}, {
+    /**
+     * The generated image encoded in base64.
+     */
+    result: string;
+}>;
+
+export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, imageGeneration, imageGenerationArgsSchema, imageGenerationOutputSchema, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };

package/dist/internal/index.d.ts

@@ -129,7 +129,7 @@ declare class OpenAIEmbeddingModel implements EmbeddingModelV2<string> {
     doEmbed({ values, headers, abortSignal, providerOptions, }: Parameters<EmbeddingModelV2<string>['doEmbed']>[0]): Promise<Awaited<ReturnType<EmbeddingModelV2<string>['doEmbed']>>>;
 }
 
-type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
+type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | 'gpt-image-1' | 'gpt-image-1-mini' | (string & {});
 declare const modelMaxImagesPerCall: Record<OpenAIImageModelId, number>;
 declare const hasDefaultResponseFormat: Set<string>;
 
@@ -203,7 +203,7 @@ declare class OpenAISpeechModel implements SpeechModelV2 {
     doGenerate(options: Parameters<SpeechModelV2['doGenerate']>[0]): Promise<Awaited<ReturnType<SpeechModelV2['doGenerate']>>>;
 }
 
-type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4' | 'gpt-4-0613' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
+type OpenAIResponsesModelId = 'chatgpt-4o-latest' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4-0613' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1' | 'gpt-4' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini' | 'gpt-4o' | 'gpt-5-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-5-mini-2025-08-07' | 'gpt-5-mini' | 'gpt-5-nano-2025-08-07' | 'gpt-5-nano' | 'gpt-5-pro-2025-10-06' | 'gpt-5-pro' | 'gpt-5' | 'o1-2024-12-17' | 'o1' | 'o3-2025-04-16' | 'o3-mini-2025-01-31' | 'o3-mini' | 'o3' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV2 {
     readonly specificationVersion = "v2";
@@ -458,4 +458,103 @@ declare const fileSearch: _ai_sdk_provider_utils.ProviderDefinedToolFactoryWithO
     filters?: OpenAIResponsesFileSearchToolComparisonFilter | OpenAIResponsesFileSearchToolCompoundFilter;
 }>;
 
-export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };
+declare const imageGenerationArgsSchema: z.ZodObject<{
+    background: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        opaque: "opaque";
+        transparent: "transparent";
+    }>>;
+    inputFidelity: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        high: "high";
+    }>>;
+    inputImageMask: z.ZodOptional<z.ZodObject<{
+        fileId: z.ZodOptional<z.ZodString>;
+        imageUrl: z.ZodOptional<z.ZodString>;
+    }, z.core.$strip>>;
+    model: z.ZodOptional<z.ZodString>;
+    moderation: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+    }>>;
+    outputCompression: z.ZodOptional<z.ZodNumber>;
+    outputFormat: z.ZodOptional<z.ZodEnum<{
+        png: "png";
+        jpeg: "jpeg";
+        webp: "webp";
+    }>>;
+    quality: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        medium: "medium";
+        high: "high";
+        auto: "auto";
+    }>>;
+    size: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        "1024x1024": "1024x1024";
+        "1024x1536": "1024x1536";
+        "1536x1024": "1536x1024";
+    }>>;
+}, z.core.$strict>;
+declare const imageGenerationOutputSchema: z.ZodObject<{
+    result: z.ZodString;
+}, z.core.$strip>;
+type ImageGenerationArgs = {
+    /**
+     * Background type for the generated image. Default is 'auto'.
+     */
+    background?: 'auto' | 'opaque' | 'transparent';
+    /**
+     * Input fidelity for the generated image. Default is 'low'.
+     */
+    inputFidelity?: 'low' | 'high';
+    /**
+     * Optional mask for inpainting.
+     * Contains image_url (string, optional) and file_id (string, optional).
+     */
+    inputImageMask?: {
+        /**
+         * File ID for the mask image.
+         */
+        fileId?: string;
+        /**
+         * Base64-encoded mask image.
+         */
+        imageUrl?: string;
+    };
+    /**
+     * The image generation model to use. Default: gpt-image-1.
+     */
+    model?: string;
+    /**
+     * Moderation level for the generated image. Default: auto.
+     */
+    moderation?: 'auto';
+    /**
+     * Compression level for the output image. Default: 100.
+     */
+    outputCompression?: number;
+    /**
+     * The output format of the generated image. One of png, webp, or jpeg.
+     * Default: png
+     */
+    outputFormat?: 'png' | 'jpeg' | 'webp';
+    /**
+     * The quality of the generated image.
+     * One of low, medium, high, or auto. Default: auto.
+     */
+    quality?: 'auto' | 'low' | 'medium' | 'high';
+    /**
+     * The size of the generated image.
+     * One of 1024x1024, 1024x1536, 1536x1024, or auto.
+     * Default: auto.
+     */
+    size?: 'auto' | '1024x1024' | '1024x1536' | '1536x1024';
+};
+declare const imageGeneration: (args?: ImageGenerationArgs) => _ai_sdk_provider_utils.Tool<{}, {
+    /**
+     * The generated image encoded in base64.
+     */
+    result: string;
+}>;
+
+export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, imageGeneration, imageGenerationArgsSchema, imageGenerationOutputSchema, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };

package/dist/internal/index.js

@@ -36,6 +36,9 @@ __export(internal_exports, {
   fileSearchArgsSchema: () => fileSearchArgsSchema,
   fileSearchOutputSchema: () => fileSearchOutputSchema,
   hasDefaultResponseFormat: () => hasDefaultResponseFormat,
+  imageGeneration: () => imageGeneration,
+  imageGenerationArgsSchema: () => imageGenerationArgsSchema,
+  imageGenerationOutputSchema: () => imageGenerationOutputSchema,
   modelMaxImagesPerCall: () => modelMaxImagesPerCall,
   openAITranscriptionProviderOptions: () => openAITranscriptionProviderOptions,
   openaiChatLanguageModelOptions: () => openaiChatLanguageModelOptions,
@@ -1605,9 +1608,13 @@ var import_v48 = require("zod/v4");
 var modelMaxImagesPerCall = {
   "dall-e-3": 1,
   "dall-e-2": 10,
-  "gpt-image-1": 10
+  "gpt-image-1": 10,
+  "gpt-image-1-mini": 10
 };
-var hasDefaultResponseFormat = /* @__PURE__ */ new Set(["gpt-image-1"]);
+var hasDefaultResponseFormat = /* @__PURE__ */ new Set([
+  "gpt-image-1",
+  "gpt-image-1-mini"
+]);
 
 // src/image/openai-image-model.ts
 var OpenAIImageModel = class {
@@ -2518,6 +2525,9 @@ var imageGenerationToolFactory = (0, import_provider_utils15.createProviderDefin
   inputSchema: import_v418.z.object({}),
   outputSchema: imageGenerationOutputSchema
 });
+var imageGeneration = (args = {}) => {
+  return imageGenerationToolFactory(args);
+};
 
 // src/responses/openai-responses-prepare-tools.ts
 function prepareResponsesTools({
@@ -4030,6 +4040,9 @@ var openaiResponsesProviderOptionsSchema = import_v419.z.object({
   fileSearchArgsSchema,
   fileSearchOutputSchema,
   hasDefaultResponseFormat,
+  imageGeneration,
+  imageGenerationArgsSchema,
+  imageGenerationOutputSchema,
   modelMaxImagesPerCall,
   openAITranscriptionProviderOptions,
   openaiChatLanguageModelOptions,