diff --git a/src/docs/sdk/performance/span-data-conventions.mdx b/src/docs/sdk/performance/span-data-conventions.mdx
index 4f2df7fdf8..2e56814908 100644
--- a/src/docs/sdk/performance/span-data-conventions.mdx
+++ b/src/docs/sdk/performance/span-data-conventions.mdx
@@ -71,6 +71,19 @@ Below describes the conventions for the Span interface for the `data` field on t
 | `cache.hit`       | boolean | If the cache was hit during this span.                 | `true`   |
 | `cache.item_size` | int     | The size of the requested item in the cache. In bytes. | 58       |
 
+## AI
+
+| Attribute                   | Type    | Description                                           | Examples                                 |
+|-----------------------------|---------|-------------------------------------------------------|------------------------------------------|
+| `ai.input_messages`         | string  | The input messages sent to the model                  | `[{"role": "user", "message": "hello"}]` |
+| `ai.completion_tоkens.used` | int     | The number of tokens used to respond to the message   | `10`                                     |
+| `ai.prompt_tоkens.used`     | int     | The number of tokens used to process just the prompt  | `20`                                     |
+| `ai.total_tоkens.used`      | int     | The total number of tokens used to process the prompt | `30`                                     |
+| `ai.model_id`               | list    | The vendor-specific ID of the model used              | `"gpt-4"`                                |
+| `ai.streaming`              | boolean | Whether the request was streamed back                 | `true`                                   |
+| `ai.responses`              | list    | The response messages sent back by the AI model       | `["hello", "world"]`                     |
+
+
 ## Thread
 
 | Attribute         | Type    | Description                                                        | Examples |