diff --git a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/openai-chat.adoc b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/openai-chat.adoc
index a1d7a359adc..e62c809f77e 100644
--- a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/openai-chat.adoc
+++ b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/openai-chat.adoc
@@ -514,7 +514,9 @@ Next, create an `OpenAiChatModel` and use it for text generations:
 
 [source,java]
 ----
-var openAiApi = new OpenAiApi(System.getenv("OPENAI_API_KEY"));
+var openAiApi = OpenAiApi.builder()
+            .apiKey(System.getenv("OPENAI_API_KEY"))
+            .build();
 var openAiChatOptions = OpenAiChatOptions.builder()
             .model("gpt-3.5-turbo")
             .temperature(0.4)
@@ -531,7 +533,7 @@ Flux<ChatResponse> response = this.chatModel.stream(
 ----
 
 The `OpenAiChatOptions` provides the configuration information for the chat requests.
-The `OpenAiChatOptions.Builder` is a fluent options-builder.
+The `OpenAiApi.Builder` and `OpenAiChatOptions.Builder` are fluent options-builders for API client and chat config respectively.
 
 == Low-level OpenAiApi Client [[low-level-api]]
 
@@ -545,8 +547,9 @@ Here is a simple snippet showing how to use the API programmatically:
 
 [source,java]
 ----
-OpenAiApi openAiApi =
-    new OpenAiApi(System.getenv("OPENAI_API_KEY"));
+OpenAiApi openAiApi = OpenAiApi.builder()
+            .apiKey(System.getenv("OPENAI_API_KEY"))
+            .build();
 
 ChatCompletionMessage chatCompletionMessage =
     new ChatCompletionMessage("Hello world", Role.USER);
diff --git a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/embeddings/openai-embeddings.adoc b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/embeddings/openai-embeddings.adoc
index bcb174cab94..23c9626fc1f 100644
--- a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/embeddings/openai-embeddings.adoc
+++ b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/embeddings/openai-embeddings.adoc
@@ -212,7 +212,9 @@ Next, create an `OpenAiEmbeddingModel` instance and use it to compute the simila
 
 [source,java]
 ----
-var openAiApi = new OpenAiApi(System.getenv("OPENAI_API_KEY"));
+var openAiApi = OpenAiApi.builder()
+                .apiKey(System.getenv("OPENAI_API_KEY"))
+                .build();
 
 var embeddingModel = new OpenAiEmbeddingModel(
 		this.openAiApi,
@@ -228,6 +230,6 @@ EmbeddingResponse embeddingResponse = this.embeddingModel
 ----
 
 The `OpenAiEmbeddingOptions` provides the configuration information for the embedding requests.
-The options class offers a `builder()` for easy options creation.
+The api and options class offers a `builder()` for easy options creation.
 
 
diff --git a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/usage-handling.adoc b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/usage-handling.adoc
index 3ec4c35a0b9..3a9daf396d6 100644
--- a/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/usage-handling.adoc
+++ b/spring-ai-docs/src/main/antora/modules/ROOT/pages/api/usage-handling.adoc
@@ -13,9 +13,9 @@ Object getNativeUsage();
 ```
 This method allows access to the model-specific native usage data, enabling more detailed usage tracking when needed.
 
-=== Using with ChatClient
+=== Using with ChatModel
 
-Here's a complete example showing how to track usage with OpenAI's ChatClient:
+Here's a complete example showing how to track usage with OpenAI's ChatModel:
 
 ```java
 @SpringBootConfiguration
@@ -23,12 +23,16 @@ public class Configuration {
 
         @Bean
         public OpenAiApi chatCompletionApi() {
-            return new OpenAiApi(System.getenv("OPENAI_API_KEY"));
+            return OpenAiApi.builder()
+                .apiKey(System.getenv("OPENAI_API_KEY"))
+                .build();
         }
 
         @Bean
         public OpenAiChatModel openAiClient(OpenAiApi openAiApi) {
-            return new OpenAiChatModel(openAiApi);
+            return OpenAiChatModel.builder()
+                .openAiApi(openAiApi)
+                .build();
         }
 
     }
@@ -46,10 +50,8 @@ public class ChatService {
         // Create a chat prompt
         Prompt prompt = new Prompt("What is the weather like today?");
 
-        ChatClient chatClient = ChatClient.builder(this.chatModel).build();
-
         // Get the chat response
-        ChatResponse response = chatClient.call(prompt);
+        ChatResponse response = this.chatModel.call(prompt);
 
         // Access the usage information
         Usage usage = response.getMetadata().getUsage();
@@ -80,6 +82,26 @@ public class ChatService {
 }
 ```
 
+=== Using with ChatClient
+
+If you are using the `ChatClient`, you can access the usage information using the `ChatResponse` object:
+
+```java
+// Create a chat prompt
+Prompt prompt = new Prompt("What is the weather like today?");
+
+// Create a chat client
+ChatClient chatClient = ChatClient.create(chatModel);
+
+// Get the chat response
+ChatResponse response = chatClient.prompt(prompt)
+        .call()
+        .chatResponse();
+
+// Access the usage information
+Usage usage = response.getMetadata().getUsage();
+```
+
 == Benefits
 
 **Standardization**: Provides a consistent way to handle usage across different AI models