feat (docs): add note on developer messages (#4173)

content/providers/01-ai-sdk-providers/01-openai.mdx

@@ -390,10 +390,17 @@ console.log('Usage:', {
 ```
 
 <Note type="warning">
-  Reasoning models like `o1`, `o1-preview`, and `o1-mini` require additional
-  runtime inference to complete their reasoning phase before generating a
-  response. You can use the `reasoningEffort` model setting to influence the
-  inference time.
+  Reasoning models like `o1-mini` and `o1-preview` require additional runtime
+  inference to complete their reasoning phase before generating a response. This
+  introduces longer latency compared to other models, with `o1-preview`
+  exhibiting significantly more inference time than `o1-mini`.
+</Note>
+
+<Note>
+  OpenAI has introduced a new `developer` message type for reasoning models.
+  However, `system` messages are automatically converted to `developer` messages
+  by OpenAI. You can pass `system` messages to reasoning models and set the
+  `system` instruction as usual.
 </Note>
 
 #### Prompt Caching
@@ -551,7 +558,7 @@ using the `.embedding()` factory method.
 const model = openai.embedding('text-embedding-3-large');
 ```
 
-OpenAI embedding models support several aditional settings.
+OpenAI embedding models support several additional settings.
 You can pass them as an options argument:
 
 ```ts