Merge pull request #380 from openai/dev/jzhou/usage-audio-token

Add audio tokens to Usage API

Author: jzhou-openai

openapi.yaml

@@ -6003,6 +6003,8 @@ paths:
                                 "input_tokens": 1000,
                                 "output_tokens": 500,
                                 "input_cached_tokens": 800,
+                                "input_audio_tokens": 0,
+                                "output_audio_tokens": 0,
                                 "num_model_requests": 5,
                                 "project_id": null,
                                 "user_id": null,
@@ -6014,7 +6016,7 @@ paths:
                     }
                 ],
                 "has_more": true,
-                "next_page": "AAAAAGdGxdEiJdKOAAAAAGcqsYA="
+                "next_page": "page_AAAAAGdGxdEiJdKOAAAAAGcqsYA="
             }
   /organization/usage/embeddings:
     get:
@@ -23331,17 +23333,25 @@ components:
             - organization.usage.completions.result
         input_tokens:
           type: integer
-          description: The aggregated number of input tokens used. For customers subscribe
-            to scale tier, this includes scale tier tokens.
+          description: The aggregated number of text input tokens used, including cached
+            tokens. For customers subscribe to scale tier, this includes scale
+            tier tokens.
         input_cached_tokens:
           type: integer
-          description: The aggregated number of input tokens that has been cached from
-            previous requests. For customers subscribe to scale tier, this
+          description: The aggregated number of text input tokens that has been cached
+            from previous requests. For customers subscribe to scale tier, this
             includes scale tier tokens.
         output_tokens:
           type: integer
-          description: The aggregated number of output tokens used. For customers
+          description: The aggregated number of text output tokens used. For customers
             subscribe to scale tier, this includes scale tier tokens.
+        input_audio_tokens:
+          type: integer
+          description: The aggregated number of audio input tokens used, including cached
+            tokens.
+        output_audio_tokens:
+          type: integer
+          description: The aggregated number of audio output tokens used.
         num_model_requests:
           type: integer
           description: The count of requests made to the model.
@@ -23383,6 +23393,8 @@ components:
               "input_tokens": 5000,
               "output_tokens": 1000,
               "input_cached_tokens": 4000,
+              "input_audio_tokens": 300,
+              "output_audio_tokens": 200,
               "num_model_requests": 5,
               "project_id": "proj_abc",
               "user_id": "user-abc",