@wix/auto_sdk_ai-gateway_generators 1.0.126 → 1.0.127

package/build/cjs/index.d.ts

@@ -298,6 +298,14 @@ interface OpenaiproxyV1CreateChatCompletionRequest extends OpenaiproxyV1CreateCh
      * @maxLength 100
      */
     verbosity?: string | null;
+    /**
+     * Specifies the processing tier used for serving the request. Passed through to OpenAI as "service_tier".
+     * "auto" lets the project default decide, "default" uses standard processing, "flex" uses cheaper/slower
+     * flex processing, and "priority" uses low-latency priority processing.
+     * See https://developers.openai.com/api/docs/guides/priority-processing
+     * @maxLength 100
+     */
+    serviceTier?: string | null;
 }
 /** @oneof */
 interface OpenaiproxyV1CreateChatCompletionRequestFunctionCallOneOf {
@@ -6080,6 +6088,14 @@ interface V1OpenAiResponsesRequest {
     truncation?: string | null;
     /** Whether to store the generated model response for later retrieval via API. */
     store?: boolean | null;
+    /**
+     * Specifies the processing tier used for serving the request. Passed through to OpenAI as "service_tier".
+     * "auto" lets the project default decide, "default" uses standard processing, "flex" uses cheaper/slower
+     * flex processing, and "priority" uses low-latency priority processing.
+     * See https://developers.openai.com/api/docs/guides/priority-processing
+     * @maxLength 100
+     */
+    serviceTier?: string | null;
 }
 declare enum V1ResponsesModel {
     MODEL_UNSPECIFIED = "MODEL_UNSPECIFIED",
@@ -8738,6 +8754,13 @@ interface OpenaiproxyV1CreateChatCompletionResponse {
      * @maxLength 10000
      */
     systemFingerprint?: string | null;
+    /**
+     * The processing tier that OpenAI actually used to serve the request (echoed from OpenAI's "service_tier").
+     * May differ from the requested tier, e.g. "default" when a requested "priority" was downgraded. This is the
+     * tier the cost (microcents_spent) is calculated from.
+     * @maxLength 100
+     */
+    serviceTier?: string | null;
 }
 interface CreateChatCompletionResponsePromptTokenDetails {
     /** Audio input tokens present in the prompt. */
@@ -10188,6 +10211,12 @@ interface V1OpenAiResponsesResponse {
     usage?: V1ResponsesTokenUsage;
     /** Cost of the request in microcents. */
     microcentsSpent?: string | null;
+    /**
+     * The processing tier that OpenAI actually used to serve the request (echoed from OpenAI's "service_tier").
+     * May differ from the requested tier when OpenAI downgrades. This is the tier microcents_spent is based on.
+     * @maxLength 100
+     */
+    serviceTier?: string | null;
 }
 interface OpenAiResponsesResponseIncompleteDetails {
     /**
@@ -11059,6 +11088,11 @@ interface OpenaiproxyV1ChatCompletionChunk {
     usage?: OpenaiproxyV1CreateChatCompletionResponseTokenUsage;
     /** Cost of the entire request in micro cents. Calculated manually and is present only in the last chunk. */
     microcentsSpent?: string | null;
+    /**
+     * The processing tier that OpenAI actually used to serve the request (echoed from OpenAI's "service_tier").
+     * @maxLength 100
+     */
+    serviceTier?: string | null;
 }
 interface ChatCompletionChunkChunkChoiceChunkDelta {
     /**
@@ -14394,6 +14428,11 @@ interface PollImageGenerationResultResponse extends PollImageGenerationResultRes
     bytedanceGetContentTaskResponse?: GetContentTaskResponse;
     /** Fal schemaless proxy GetQueueResult response */
     falGetQueueResultResponse?: FalGetQueueResultResponse;
+    /**
+     * Extracted cost of the polled request in microcents. Absent until the vendor has finished
+     * processing and priced the result.
+     */
+    cost?: string | null;
 }
 /** @oneof */
 interface PollImageGenerationResultResponseResponseOneOf {