openai 7.1.0 → 7.3.0

package/resources/beta/responses/responses.d.ts

@@ -1025,9 +1025,13 @@ export interface BetaResponse {
      *   will use 'default'.
      * - If set to 'default', then the request will be processed with the standard
      *   pricing and performance for the selected model.
-     * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-     *   '[priority](https://openai.com/api-priority-processing/)', then the request
-     *   will be processed with the corresponding service tier.
+     * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+     *   then the request will be processed with the Flex Processing service tier.
+     * - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+     *   include the `service_tier=fast` or `service_tier=priority` parameter for
+     *   Responses or Chat Completions. The response will show `service_tier=priority`
+     *   regardless of if you specify `service_tier=fast` or `priority` in your
+     *   request.
      * - When not set, the default behavior is 'auto'.
      *
      * When the `service_tier` parameter is set, the response body will include the
@@ -1035,7 +1039,7 @@ export interface BetaResponse {
      * request. This response value may be different from the value set in the
      * parameter.
      */
-    service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | null;
+    service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | null;
     /**
      * The status of the response generation. One of `completed`, `failed`,
      * `in_progress`, `cancelled`, `queued`, or `incomplete`.
@@ -8478,9 +8482,13 @@ export declare namespace BetaResponsesClientEvent {
          *   will use 'default'.
          * - If set to 'default', then the request will be processed with the standard
          *   pricing and performance for the selected model.
-         * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-         *   '[priority](https://openai.com/api-priority-processing/)', then the request
-         *   will be processed with the corresponding service tier.
+         * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+         *   then the request will be processed with the Flex Processing service tier.
+         * - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+         *   include the `service_tier=fast` or `service_tier=priority` parameter for
+         *   Responses or Chat Completions. The response will show `service_tier=priority`
+         *   regardless of if you specify `service_tier=fast` or `priority` in your
+         *   request.
          * - When not set, the default behavior is 'auto'.
          *
          * When the `service_tier` parameter is set, the response body will include the
@@ -8488,7 +8496,7 @@ export declare namespace BetaResponsesClientEvent {
          * request. This response value may be different from the value set in the
          * parameter.
          */
-        service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | null;
+        service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | null;
         /**
          * Whether to store the generated model response for later retrieval via API.
          */
@@ -9519,9 +9527,13 @@ export interface ResponseCreateParamsBase {
      *   will use 'default'.
      * - If set to 'default', then the request will be processed with the standard
      *   pricing and performance for the selected model.
-     * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-     *   '[priority](https://openai.com/api-priority-processing/)', then the request
-     *   will be processed with the corresponding service tier.
+     * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+     *   then the request will be processed with the Flex Processing service tier.
+     * - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+     *   include the `service_tier=fast` or `service_tier=priority` parameter for
+     *   Responses or Chat Completions. The response will show `service_tier=priority`
+     *   regardless of if you specify `service_tier=fast` or `priority` in your
+     *   request.
      * - When not set, the default behavior is 'auto'.
      *
      * When the `service_tier` parameter is set, the response body will include the
@@ -9529,7 +9541,7 @@ export interface ResponseCreateParamsBase {
      * request. This response value may be different from the value set in the
      * parameter.
      */
-    service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | null;
+    service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | null;
     /**
      * Body param: Whether to store the generated model response for later retrieval
      * via API.
@@ -9950,9 +9962,23 @@ export interface ResponseCompactParams {
      */
     prompt_cache_retention?: 'in_memory' | '24h' | null;
     /**
-     * Body param: The service tier to use for this request.
-     */
-    service_tier?: 'auto' | 'default' | 'flex' | 'priority' | null;
+     * Body param: Specifies the processing type used for serving the request. - If set
+     * to 'auto', then the request will be processed with the service tier configured
+     * in the Project settings. Unless otherwise configured, the Project will use
+     * 'default'. - If set to 'default', then the request will be processed with the
+     * standard pricing and performance for the selected model. - If set to
+     * '[flex](https://platform.openai.com/docs/guides/flex-processing)', then the
+     * request will be processed with the Flex Processing service tier. - To opt-in to
+     * [Fast mode](/api/docs/guides/fast-mode) at the request level, include the
+     * `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat
+     * Completions. The response will show `service_tier=priority` regardless of if you
+     * specify `service_tier=fast` or `priority` in your request. - When not set, the
+     * default behavior is 'auto'. When the `service_tier` parameter is set, the
+     * response body will include the `service_tier` value based on the processing mode
+     * actually used to serve the request. This response value may be different from
+     * the value set in the parameter.
+     */
+    service_tier?: 'auto' | 'default' | 'fast' | 'flex' | 'priority' | null;
     /**
      * Header param: Optional beta features to enable for this request.
      */