@ai-sdk/openai 3.0.91 → 3.0.93

package/docs/03-openai.mdx

@@ -231,10 +231,12 @@ The following provider options are available:
   `.nullable()`.
 </Note>
 
-- **serviceTier** _'auto' | 'flex' | 'priority' | 'default'_
+- **serviceTier** _'auto' | 'flex' | 'priority' | 'fast' | 'default'_
   Service tier for the request. Set to 'flex' for 50% cheaper processing
   at the cost of increased latency (available for o3, o4-mini, and gpt-5 models).
   Set to 'priority' for faster processing with Enterprise access (available for gpt-4, gpt-5, gpt-5-mini, o3, o4-mini; gpt-5-nano is not supported).
+  'fast' is OpenAI's newer name for the 'priority' tier; the two are interchangeable, and responses from
+  gpt-5.6 and earlier report `serviceTier: 'priority'` for either.
 
   Defaults to 'auto'.
 
@@ -1709,11 +1711,13 @@ The following optional provider options are available for OpenAI chat models:
 
   Parameters for prediction mode.
 
-- **serviceTier** _'auto' | 'flex' | 'priority' | 'default'_
+- **serviceTier** _'auto' | 'flex' | 'priority' | 'fast' | 'default'_
 
   Service tier for the request. Set to 'flex' for 50% cheaper processing
   at the cost of increased latency (available for o3, o4-mini, and gpt-5 models).
   Set to 'priority' for faster processing with Enterprise access (available for gpt-4, gpt-5, gpt-5-mini, o3, o4-mini; gpt-5-nano is not supported).
+  'fast' is OpenAI's newer name for the 'priority' tier; the two are interchangeable, and responses from
+  gpt-5.6 and earlier report `serviceTier: 'priority'` for either.
 
   Defaults to 'auto'.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/openai",
-  "version": "3.0.91",
+  "version": "3.0.93",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -36,8 +36,8 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/provider": "3.0.14",
-    "@ai-sdk/provider-utils": "4.0.42"
+    "@ai-sdk/provider": "3.0.15",
+    "@ai-sdk/provider-utils": "4.0.44"
   },
   "devDependencies": {
     "@types/node": "20.17.24",

package/src/chat/openai-chat-language-model.ts

@@ -283,7 +283,8 @@ export class OpenAIChatLanguageModel implements LanguageModelV3 {
 
     // Validate priority processing support
     if (
-      openaiOptions.serviceTier === 'priority' &&
+      (openaiOptions.serviceTier === 'priority' ||
+        openaiOptions.serviceTier === 'fast') &&
       !modelCapabilities.supportsPriorityProcessing
     ) {
       warnings.push({

package/src/chat/openai-chat-options.ts

@@ -138,11 +138,14 @@ export const openaiLanguageModelChatOptions = lazySchema(() =>
        *           Project settings. Unless otherwise configured, the Project will use 'default'.
        * - 'flex': 50% cheaper processing at the cost of increased latency. Only available for o3 and o4-mini models.
        * - 'priority': Higher-speed processing with predictably low latency at premium cost. Available for Enterprise customers.
+       * - 'fast': OpenAI's newer name for the 'priority' tier. Interchangeable with it.
        * - 'default': The request will be processed with the standard pricing and performance for the selected model.
        *
        * @default 'auto'
        */
-      serviceTier: z.enum(['auto', 'flex', 'priority', 'default']).optional(),
+      serviceTier: z
+        .enum(['auto', 'flex', 'priority', 'fast', 'default'])
+        .optional(),
 
       /**
        * Whether to use strict JSON schema validation.

package/src/responses/openai-responses-language-model.ts

@@ -450,7 +450,8 @@ export class OpenAIResponsesLanguageModel implements LanguageModelV3 {
 
     // Validate priority processing support
     if (
-      openaiOptions?.serviceTier === 'priority' &&
+      (openaiOptions?.serviceTier === 'priority' ||
+        openaiOptions?.serviceTier === 'fast') &&
       !modelCapabilities.supportsPriorityProcessing
     ) {
       warnings.push({

package/src/responses/openai-responses-options.ts

@@ -293,10 +293,13 @@ export const openaiLanguageModelResponsesOptionsSchema = lazySchema(() =>
        * Service tier for the request.
        * Set to 'flex' for 50% cheaper processing at the cost of increased latency (available for o3, o4-mini, and gpt-5 models).
        * Set to 'priority' for faster processing with Enterprise access (available for gpt-4, gpt-5, gpt-5-mini, o3, o4-mini; gpt-5-nano is not supported).
+       * Set to 'fast' for the same tier as 'priority' (OpenAI's newer name for it).
        *
        * Defaults to 'auto'.
        */
-      serviceTier: z.enum(['auto', 'flex', 'priority', 'default']).nullish(),
+      serviceTier: z
+        .enum(['auto', 'flex', 'priority', 'fast', 'default'])
+        .nullish(),
 
       /**
        * Whether to store the generation. Defaults to `true`.