@@ -14342,6 +14342,27 @@ paths:
                         description: Number of tokens in the input
                         example: 8
                         type: integer
+                      prompt_tokens_details:
+                        description: >-
+                          Per-modality token breakdown. Only present when the input contains 2+ modalities (e.g. text +
+                          image) and the upstream provider returns modality-level usage data. Only non-zero modality
+                          counts are included.
+                        properties:
+                          audio_tokens:
+                            description: Number of audio tokens in the input
+                            type: integer
+                          image_tokens:
+                            description: Number of image tokens in the input
+                            example: 258
+                            type: integer
+                          text_tokens:
+                            description: Number of text tokens in the input
+                            example: 8
+                            type: integer
+                          video_tokens:
+                            description: Number of video tokens in the input
+                            type: integer
+                        type: object
                       total_tokens:
                         description: Total number of tokens used
                         example: 8