feat: add GPT-5 model enum support and update documentation

- Add GPT_5 and GPT_5_2025_08_07 enum constants to ChatModel in OpenAiApi.java
- Update OpenAiApiIT test to use enum constants instead of hardcoded strings
- Enhance README.md to highlight support for latest models including GPT-5
- Include JavaDoc documentation with temperature requirement notes (1.0)

Fixes GPT-5 model integration with proper type-safe enum constants

Author: markpollack

README.md

@@ -23,6 +23,7 @@ You can find more details in the [Reference Documentation](https://docs.spring.i
   - [Audio Transcription](https://docs.spring.io/spring-ai/reference/api/audio/transcriptions.html)
   - [Text to Speech](https://docs.spring.io/spring-ai/reference/api/audio/speech.html)
   - [Moderation](https://docs.spring.io/spring-ai/reference/api/index.html#api/moderation)
+  - **Latest Models**: GPT-5, and other cutting-edge models for advanced AI applications.
 * Portable API support across AI providers for both synchronous and streaming options. Access to [model-specific features](https://docs.spring.io/spring-ai/reference/api/chatmodel.html#_chat_options) is also available.
 * [Structured Outputs](https://docs.spring.io/spring-ai/reference/api/structured-output-converter.html) - Mapping of AI Model output to POJOs.
 * Support for all major [Vector Database providers](https://docs.spring.io/spring-ai/reference/api/vectordbs.html) such as *Apache Cassandra, Azure Vector Search, Chroma, Elasticsearch, Milvus, MongoDB Atlas, MariaDB, Neo4j, Oracle, PostgreSQL/PGVector, PineCone, Qdrant, Redis, and Weaviate*.

models/spring-ai-openai/src/main/java/org/springframework/ai/openai/api/OpenAiApi.java

@@ -468,6 +468,33 @@ public enum ChatModel implements ChatModelDescription {
 		 */
 		GPT_4_1("gpt-4.1"),
 
+		/**
+		 * <b>GPT-5</b> is the next-generation flagship model with enhanced capabilities
+		 * for complex reasoning and problem-solving tasks.
+		 * <p>
+		 * Note: GPT-5 models require temperature=1.0 (default value). Custom temperature
+		 * values are not supported and will cause errors.
+		 * <p>
+		 * Model ID: gpt-5
+		 * <p>
+		 * See: <a href="https://platform.openai.com/docs/models/gpt-5">gpt-5</a>
+		 */
+		GPT_5("gpt-5"),
+
+		/**
+		 * <b>GPT-5 (2025-08-07)</b> is a specific snapshot of the GPT-5 model from
+		 * August 7, 2025, providing enhanced capabilities for complex reasoning and
+		 * problem-solving tasks.
+		 * <p>
+		 * Note: GPT-5 models require temperature=1.0 (default value). Custom temperature
+		 * values are not supported and will cause errors.
+		 * <p>
+		 * Model ID: gpt-5-2025-08-07
+		 * <p>
+		 * See: <a href="https://platform.openai.com/docs/models/gpt-5">gpt-5</a>
+		 */
+		GPT_5_2025_08_07("gpt-5-2025-08-07"),
+
 		/**
 		 * <b>GPT-4o</b> (“o” for “omni”) is the versatile, high-intelligence flagship
 		 * model. It accepts both text and image inputs, and produces text outputs

models/spring-ai-openai/src/test/java/org/springframework/ai/openai/api/OpenAiApiIT.java

@@ -24,7 +24,7 @@
 import org.junit.jupiter.api.Test;
 import org.junit.jupiter.api.condition.EnabledIfEnvironmentVariable;
 import org.junit.jupiter.params.ParameterizedTest;
-import org.junit.jupiter.params.provider.ValueSource;
+import org.junit.jupiter.params.provider.EnumSource;
 import reactor.core.publisher.Flux;
 
 import org.springframework.ai.openai.api.OpenAiApi.ChatCompletion;
@@ -159,17 +159,17 @@ void streamOutputAudio() {
 	}
 
 	@ParameterizedTest(name = "{0} : {displayName}")
-	@ValueSource(strings = { "gpt-5", "gpt-5-2025-08-07" })
-	void chatCompletionEntityWithNewModels(String modelName) {
+	@EnumSource(names = {"GPT_5", "GPT_5_2025_08_07"})
+	void chatCompletionEntityWithNewModels(OpenAiApi.ChatModel modelName) {
 		ChatCompletionMessage chatCompletionMessage = new ChatCompletionMessage("Hello world", Role.USER);
 		ResponseEntity<ChatCompletion> response = this.openAiApi
-			.chatCompletionEntity(new ChatCompletionRequest(List.of(chatCompletionMessage), modelName, 1.0, false));
+			.chatCompletionEntity(new ChatCompletionRequest(List.of(chatCompletionMessage), modelName.getValue(), 1.0, false));
 
 		assertThat(response).isNotNull();
 		assertThat(response.getBody()).isNotNull();
 		assertThat(response.getBody().choices()).isNotEmpty();
 		assertThat(response.getBody().choices().get(0).message().content()).isNotEmpty();
-		assertThat(response.getBody().model()).containsIgnoringCase(modelName);
+		assertThat(response.getBody().model()).containsIgnoringCase(modelName.getValue());
 	}
 
 }