@ai-sdk/openai 2.0.0-canary.2 → 2.0.0-canary.20

package/dist/index.d.ts

@@ -1,133 +1,13 @@
-import { LanguageModelV2, ProviderV2, EmbeddingModelV1, ImageModelV1 } from '@ai-sdk/provider';
+import { LanguageModelV2, ProviderV2, EmbeddingModelV2, ImageModelV2, TranscriptionModelV1, SpeechModelV1 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod';
 
-type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024-09-12' | 'o1-preview' | 'o1-preview-2024-09-12' | 'o3-mini' | 'o3-mini-2025-01-31' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-audio-preview' | 'gpt-4o-audio-preview-2024-10-01' | 'gpt-4o-audio-preview-2024-12-17' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo-preview' | 'gpt-4-0125-preview' | 'gpt-4-1106-preview' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
-interface OpenAIChatSettings {
-    /**
-  Modify the likelihood of specified tokens appearing in the completion.
-  
-  Accepts a JSON object that maps tokens (specified by their token ID in
-  the GPT tokenizer) to an associated bias value from -100 to 100. You
-  can use this tokenizer tool to convert text to token IDs. Mathematically,
-  the bias is added to the logits generated by the model prior to sampling.
-  The exact effect will vary per model, but values between -1 and 1 should
-  decrease or increase likelihood of selection; values like -100 or 100
-  should result in a ban or exclusive selection of the relevant token.
-  
-  As an example, you can pass {"50256": -100} to prevent the <|endoftext|>
-  token from being generated.
-  */
-    logitBias?: Record<number, number>;
-    /**
-  Return the log probabilities of the tokens. Including logprobs will increase
-  the response size and can slow down response times. However, it can
-  be useful to better understand how the model is behaving.
-  
-  Setting to true will return the log probabilities of the tokens that
-  were generated.
-  
-  Setting to a number will return the log probabilities of the top n
-  tokens that were generated.
-  */
-    logprobs?: boolean | number;
-    /**
-  Whether to enable parallel function calling during tool use. Default to true.
-     */
-    parallelToolCalls?: boolean;
-    /**
-  Whether to use structured outputs. Defaults to false.
-  
-  When enabled, tool calls and object generation will be strict and follow the provided schema.
-   */
-    structuredOutputs?: boolean;
-    /**
-  Whether to use legacy function calling. Defaults to false.
-  
-  Required by some open source inference engines which do not support the `tools` API. May also
-  provide a workaround for `parallelToolCalls` resulting in the provider buffering tool calls,
-  which causes `streamObject` to be non-streaming.
-  
-  Prefer setting `parallelToolCalls: false` over this option.
-  
-  @deprecated this API is supported but deprecated by OpenAI.
-     */
-    useLegacyFunctionCalling?: boolean;
-    /**
-  A unique identifier representing your end-user, which can help OpenAI to
-  monitor and detect abuse. Learn more.
-  */
-    user?: string;
-    /**
-  Automatically download images and pass the image as data to the model.
-  OpenAI supports image URLs for public models, so this is only needed for
-  private models or when the images are not publicly accessible.
-  
-  Defaults to `false`.
-     */
-    downloadImages?: boolean;
-    /**
-  Simulates streaming by using a normal generate call and returning it as a stream.
-  Enable this if the model that you are using does not support streaming.
-  
-  Defaults to `false`.
-  
-  @deprecated Use `simulateStreamingMiddleware` instead.
-     */
-    simulateStreaming?: boolean;
-    /**
-  Reasoning effort for reasoning models. Defaults to `medium`.
-     */
-    reasoningEffort?: 'low' | 'medium' | 'high';
-}
+type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024-09-12' | 'o1-preview' | 'o1-preview-2024-09-12' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'o4-mini' | 'o4-mini-2025-04-16' | '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-audio-preview' | 'gpt-4o-audio-preview-2024-10-01' | 'gpt-4o-audio-preview-2024-12-17' | 'gpt-4o-search-preview' | 'gpt-4o-search-preview-2025-03-11' | 'gpt-4o-mini-search-preview' | 'gpt-4o-mini-search-preview-2025-03-11' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo-preview' | 'gpt-4-0125-preview' | 'gpt-4-1106-preview' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
 
 type OpenAICompletionModelId = 'gpt-3.5-turbo-instruct' | (string & {});
-interface OpenAICompletionSettings {
-    /**
-  Echo back the prompt in addition to the completion.
-     */
-    echo?: boolean;
-    /**
-  Modify the likelihood of specified tokens appearing in the completion.
-  
-  Accepts a JSON object that maps tokens (specified by their token ID in
-  the GPT tokenizer) to an associated bias value from -100 to 100. You
-  can use this tokenizer tool to convert text to token IDs. Mathematically,
-  the bias is added to the logits generated by the model prior to sampling.
-  The exact effect will vary per model, but values between -1 and 1 should
-  decrease or increase likelihood of selection; values like -100 or 100
-  should result in a ban or exclusive selection of the relevant token.
-  
-  As an example, you can pass {"50256": -100} to prevent the <|endoftext|>
-  token from being generated.
-     */
-    logitBias?: Record<number, number>;
-    /**
-  Return the log probabilities of the tokens. Including logprobs will increase
-  the response size and can slow down response times. However, it can
-  be useful to better understand how the model is behaving.
-  
-  Setting to true will return the log probabilities of the tokens that
-  were generated.
-  
-  Setting to a number will return the log probabilities of the top n
-  tokens that were generated.
-     */
-    logprobs?: boolean | number;
-    /**
-  The suffix that comes after a completion of inserted text.
-     */
-    suffix?: string;
-    /**
-  A unique identifier representing your end-user, which can help OpenAI to
-  monitor and detect abuse. Learn more.
-     */
-    user?: string;
-}
 
 type OpenAICompletionConfig = {
     provider: string;
-    compatibility: 'strict' | 'compatible';
     headers: () => Record<string, string | undefined>;
     url: (options: {
         modelId: string;
@@ -137,47 +17,20 @@ type OpenAICompletionConfig = {
 };
 declare class OpenAICompletionLanguageModel implements LanguageModelV2 {
     readonly specificationVersion = "v2";
-    readonly defaultObjectGenerationMode: undefined;
     readonly modelId: OpenAICompletionModelId;
-    readonly settings: OpenAICompletionSettings;
     private readonly config;
-    constructor(modelId: OpenAICompletionModelId, settings: OpenAICompletionSettings, config: OpenAICompletionConfig);
+    private get providerOptionsName();
+    constructor(modelId: OpenAICompletionModelId, config: OpenAICompletionConfig);
     get provider(): string;
+    readonly supportedUrls: Record<string, RegExp[]>;
     private getArgs;
     doGenerate(options: Parameters<LanguageModelV2['doGenerate']>[0]): Promise<Awaited<ReturnType<LanguageModelV2['doGenerate']>>>;
     doStream(options: Parameters<LanguageModelV2['doStream']>[0]): Promise<Awaited<ReturnType<LanguageModelV2['doStream']>>>;
 }
 
 type OpenAIEmbeddingModelId = 'text-embedding-3-small' | 'text-embedding-3-large' | 'text-embedding-ada-002' | (string & {});
-interface OpenAIEmbeddingSettings {
-    /**
-  Override the maximum number of embeddings per call.
-     */
-    maxEmbeddingsPerCall?: number;
-    /**
-  Override the parallelism of embedding calls.
-      */
-    supportsParallelCalls?: boolean;
-    /**
-  The number of dimensions the resulting output embeddings should have.
-  Only supported in text-embedding-3 and later models.
-     */
-    dimensions?: number;
-    /**
-  A unique identifier representing your end-user, which can help OpenAI to
-  monitor and detect abuse. Learn more.
-  */
-    user?: string;
-}
 
-type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | (string & {});
-interface OpenAIImageSettings {
-    /**
-  Override the maximum number of images per call (default is dependent on the
-  model, or 1 for an unknown model).
-     */
-    maxImagesPerCall?: number;
-}
+type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
 
 declare const WebSearchPreviewParameters: z.ZodObject<{}, "strip", z.ZodTypeAny, {}, {}>;
 declare function webSearchPreviewTool({ searchContextSize, userLocation, }?: {
@@ -199,20 +52,24 @@ declare const openaiTools: {
     webSearchPreview: typeof webSearchPreviewTool;
 };
 
-type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024-09-12' | 'o1-preview' | 'o1-preview-2024-09-12' | 'o3-mini' | 'o3-mini-2025-01-31' | '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-turbo-preview' | 'gpt-4-0125-preview' | 'gpt-4-1106-preview' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
+type OpenAITranscriptionModelId = 'whisper-1' | 'gpt-4o-mini-transcribe' | 'gpt-4o-transcribe' | (string & {});
+
+type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024-09-12' | 'o1-preview' | 'o1-preview-2024-09-12' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'o4-mini' | 'o4-mini-2025-04-16' | '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-audio-preview' | 'gpt-4o-audio-preview-2024-10-01' | 'gpt-4o-audio-preview-2024-12-17' | 'gpt-4o-search-preview' | 'gpt-4o-search-preview-2025-03-11' | 'gpt-4o-mini-search-preview' | 'gpt-4o-mini-search-preview-2025-03-11' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo-preview' | 'gpt-4-0125-preview' | 'gpt-4-1106-preview' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
+
+type OpenAISpeechModelId = 'tts-1' | 'tts-1-hd' | 'gpt-4o-mini-tts' | (string & {});
 
 interface OpenAIProvider extends ProviderV2 {
-    (modelId: 'gpt-3.5-turbo-instruct', settings?: OpenAICompletionSettings): OpenAICompletionLanguageModel;
-    (modelId: OpenAIChatModelId, settings?: OpenAIChatSettings): LanguageModelV2;
+    (modelId: 'gpt-3.5-turbo-instruct'): OpenAICompletionLanguageModel;
+    (modelId: OpenAIChatModelId): LanguageModelV2;
     /**
   Creates an OpenAI model for text generation.
      */
-    languageModel(modelId: 'gpt-3.5-turbo-instruct', settings?: OpenAICompletionSettings): OpenAICompletionLanguageModel;
-    languageModel(modelId: OpenAIChatModelId, settings?: OpenAIChatSettings): LanguageModelV2;
+    languageModel(modelId: 'gpt-3.5-turbo-instruct'): OpenAICompletionLanguageModel;
+    languageModel(modelId: OpenAIChatModelId): LanguageModelV2;
     /**
   Creates an OpenAI chat model for text generation.
      */
-    chat(modelId: OpenAIChatModelId, settings?: OpenAIChatSettings): LanguageModelV2;
+    chat(modelId: OpenAIChatModelId): LanguageModelV2;
     /**
   Creates an OpenAI responses API model for text generation.
      */
@@ -220,29 +77,38 @@ interface OpenAIProvider extends ProviderV2 {
     /**
   Creates an OpenAI completion model for text generation.
      */
-    completion(modelId: OpenAICompletionModelId, settings?: OpenAICompletionSettings): LanguageModelV2;
+    completion(modelId: OpenAICompletionModelId): LanguageModelV2;
     /**
   Creates a model for text embeddings.
      */
-    embedding(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV1<string>;
+    embedding(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for text embeddings.
   
   @deprecated Use `textEmbeddingModel` instead.
      */
-    textEmbedding(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV1<string>;
+    textEmbedding(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for text embeddings.
      */
-    textEmbeddingModel(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV1<string>;
+    textEmbeddingModel(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for image generation.
+  @deprecated Use `imageModel` instead.
      */
-    image(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV1;
+    image(modelId: OpenAIImageModelId): ImageModelV2;
     /**
   Creates a model for image generation.
      */
-    imageModel(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV1;
+    imageModel(modelId: OpenAIImageModelId): ImageModelV2;
+    /**
+  Creates a model for transcription.
+     */
+    transcription(modelId: OpenAITranscriptionModelId): TranscriptionModelV1;
+    /**
+  Creates a model for speech generation.
+     */
+    speech(modelId: OpenAISpeechModelId): SpeechModelV1;
     /**
   OpenAI-specific tools.
      */
@@ -270,12 +136,6 @@ interface OpenAIProviderSettings {
        */
     headers?: Record<string, string>;
     /**
-  OpenAI compatibility mode. Should be set to `strict` when using the OpenAI API,
-  and `compatible` when using 3rd party providers. In `compatible` mode, newer
-  information such as streamOptions are not being sent. Defaults to 'compatible'.
-     */
-    compatibility?: 'strict' | 'compatible';
-    /**
   Provider name. Overrides the `openai` default name for 3rd party providers.
      */
     name?: string;
@@ -290,7 +150,7 @@ Create an OpenAI provider instance.
  */
 declare function createOpenAI(options?: OpenAIProviderSettings): OpenAIProvider;
 /**
-Default OpenAI provider instance. It uses 'strict' compatibility mode.
+Default OpenAI provider instance.
  */
 declare const openai: OpenAIProvider;
 
@@ -303,24 +163,27 @@ declare const openaiResponsesProviderOptionsSchema: z.ZodObject<{
     reasoningEffort: z.ZodOptional<z.ZodNullable<z.ZodString>>;
     strictSchemas: z.ZodOptional<z.ZodNullable<z.ZodBoolean>>;
     instructions: z.ZodOptional<z.ZodNullable<z.ZodString>>;
+    reasoningSummary: z.ZodOptional<z.ZodNullable<z.ZodString>>;
 }, "strip", z.ZodTypeAny, {
     user?: string | null | undefined;
+    parallelToolCalls?: boolean | null | undefined;
+    reasoningEffort?: string | null | undefined;
     store?: boolean | null | undefined;
     metadata?: any;
-    reasoningEffort?: string | null | undefined;
-    parallelToolCalls?: boolean | null | undefined;
     previousResponseId?: string | null | undefined;
     strictSchemas?: boolean | null | undefined;
     instructions?: string | null | undefined;
+    reasoningSummary?: string | null | undefined;
 }, {
     user?: string | null | undefined;
+    parallelToolCalls?: boolean | null | undefined;
+    reasoningEffort?: string | null | undefined;
     store?: boolean | null | undefined;
     metadata?: any;
-    reasoningEffort?: string | null | undefined;
-    parallelToolCalls?: boolean | null | undefined;
     previousResponseId?: string | null | undefined;
     strictSchemas?: boolean | null | undefined;
     instructions?: string | null | undefined;
+    reasoningSummary?: string | null | undefined;
 }>;
 type OpenAIResponsesProviderOptions = z.infer<typeof openaiResponsesProviderOptionsSchema>;