@ai-sdk/openai 2.0.0-canary.11 → 2.0.0-canary.13

package/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @ai-sdk/openai
 
+## 2.0.0-canary.13
+
+### Patch Changes
+
+- 177526b: chore(providers/openai-transcription): switch to providerOptions
+- c15dfbf: feat (providers/openai): add gpt-image-1 model id to image settings
+- 9bf7291: chore(providers/openai): enable structuredOutputs by default & switch to provider option
+- 4617fab: chore(embedding-models): remove remaining settings
+- Updated dependencies [9bf7291]
+- Updated dependencies [4617fab]
+- Updated dependencies [e030615]
+  - @ai-sdk/provider@2.0.0-canary.11
+  - @ai-sdk/provider-utils@3.0.0-canary.12
+
+## 2.0.0-canary.12
+
+### Patch Changes
+
+- db72adc: chore(providers/openai): update completion model to use providerOptions
+- 66962ed: fix(packages): export node10 compatible types
+- 9301f86: refactor (image-model): rename `ImageModelV1` to `ImageModelV2`
+- 7df7a25: feat (providers/openai): support gpt-image-1 image generation
+- Updated dependencies [66962ed]
+- Updated dependencies [9301f86]
+- Updated dependencies [a3f768e]
+  - @ai-sdk/provider-utils@3.0.0-canary.11
+  - @ai-sdk/provider@2.0.0-canary.10
+
 ## 2.0.0-canary.11
 
 ### Patch Changes

package/dist/index.d.mts

@@ -1,48 +1,10 @@
-import { LanguageModelV2, ProviderV2, EmbeddingModelV2, ImageModelV1, TranscriptionModelV1, SpeechModelV1 } 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' | '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 & {});
-interface OpenAIChatSettings {
-    /**
-  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;
-}
 
 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>;
-    /**
-  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;
@@ -57,9 +19,9 @@ type OpenAICompletionConfig = {
 declare class OpenAICompletionLanguageModel implements LanguageModelV2 {
     readonly specificationVersion = "v2";
     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;
     getSupportedUrls(): Promise<Record<string, RegExp[]>>;
     private getArgs;
@@ -68,18 +30,8 @@ declare class OpenAICompletionLanguageModel implements LanguageModelV2 {
 }
 
 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;
-}
 
-type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | (string & {});
+type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
 interface OpenAIImageSettings {
     /**
   Override the maximum number of images per call (default is dependent on the
@@ -115,17 +67,17 @@ type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024
 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.
      */
@@ -133,29 +85,29 @@ 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): EmbeddingModelV2<string>;
+    embedding(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for text embeddings.
   
   @deprecated Use `textEmbeddingModel` instead.
      */
-    textEmbedding(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbedding(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for text embeddings.
      */
-    textEmbeddingModel(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbeddingModel(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for image generation.
      */
-    image(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV1;
+    image(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV2;
     /**
   Creates a model for image generation.
      */
-    imageModel(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV1;
+    imageModel(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV2;
     /**
   Creates a model for transcription.
      */

package/dist/index.d.ts

@@ -1,48 +1,10 @@
-import { LanguageModelV2, ProviderV2, EmbeddingModelV2, ImageModelV1, TranscriptionModelV1, SpeechModelV1 } 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' | '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 & {});
-interface OpenAIChatSettings {
-    /**
-  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;
-}
 
 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>;
-    /**
-  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;
@@ -57,9 +19,9 @@ type OpenAICompletionConfig = {
 declare class OpenAICompletionLanguageModel implements LanguageModelV2 {
     readonly specificationVersion = "v2";
     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;
     getSupportedUrls(): Promise<Record<string, RegExp[]>>;
     private getArgs;
@@ -68,18 +30,8 @@ declare class OpenAICompletionLanguageModel implements LanguageModelV2 {
 }
 
 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;
-}
 
-type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | (string & {});
+type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
 interface OpenAIImageSettings {
     /**
   Override the maximum number of images per call (default is dependent on the
@@ -115,17 +67,17 @@ type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024
 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.
      */
@@ -133,29 +85,29 @@ 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): EmbeddingModelV2<string>;
+    embedding(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for text embeddings.
   
   @deprecated Use `textEmbeddingModel` instead.
      */
-    textEmbedding(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbedding(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for text embeddings.
      */
-    textEmbeddingModel(modelId: OpenAIEmbeddingModelId, settings?: OpenAIEmbeddingSettings): EmbeddingModelV2<string>;
+    textEmbeddingModel(modelId: OpenAIEmbeddingModelId): EmbeddingModelV2<string>;
     /**
   Creates a model for image generation.
      */
-    image(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV1;
+    image(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV2;
     /**
   Creates a model for image generation.
      */
-    imageModel(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV1;
+    imageModel(modelId: OpenAIImageModelId, settings?: OpenAIImageSettings): ImageModelV2;
     /**
   Creates a model for transcription.
      */