Add GPT-5 model support and temperature documentation

GPT-5 models (gpt-5, gpt-5-2025-08-07) only support temperature=1.0
and will error with other values. This change adds a parameterized test
to validate both models work correctly and updates documentation to
warn users about this temperature requirement.

- Add chatCompletionEntityWithNewModels test in OpenAiApiIT
- Set temperature to 1.0 for GPT-5 compatibility
- Add NOTE section in openai-chat.adoc about temperature restriction

Author: markpollack

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

@@ -23,6 +23,8 @@
 import org.junit.jupiter.api.Disabled;
 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 reactor.core.publisher.Flux;
 
 import org.springframework.ai.openai.api.OpenAiApi.ChatCompletion;
@@ -156,4 +158,18 @@ void streamOutputAudio() {
 			.hasMessageContaining("400 Bad Request from POST https://api.openai.com/v1/chat/completions");
 	}
 
+	@ParameterizedTest(name = "{0} : {displayName}")
+	@ValueSource(strings = { "gpt-5", "gpt-5-2025-08-07" })
+	void chatCompletionEntityWithNewModels(String modelName) {
+		ChatCompletionMessage chatCompletionMessage = new ChatCompletionMessage("Hello world", Role.USER);
+		ResponseEntity<ChatCompletion> response = this.openAiApi
+			.chatCompletionEntity(new ChatCompletionRequest(List.of(chatCompletionMessage), modelName, 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);
+	}
+
 }

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/openai-chat.adoc

@@ -179,6 +179,11 @@ The `JSON_SCHEMA` type enables link:https://platform.openai.com/docs/guides/stru
 | spring.ai.openai.chat.options.proxy-tool-calls | If true, the Spring AI will not handle the function calls internally, but will proxy them to the client. Then is the client's responsibility to handle the function calls, dispatch them to the appropriate function, and return the results. If false (the default), the Spring AI will handle the function calls internally. Applicable only for chat models with function calling support | false
 |====
 
+[NOTE]
+====
+When using GPT-5 models (`gpt-5`, `gpt-5-2025-08-07`), the temperature parameter must be set to `1.0` (the default value). These models do not support custom temperature values and will return an error if any other temperature value is specified.
+====
+
 NOTE: You can override the common `spring.ai.openai.base-url` and `spring.ai.openai.api-key` for the `ChatModel` and `EmbeddingModel` implementations.
 The `spring.ai.openai.chat.base-url` and `spring.ai.openai.chat.api-key` properties, if set, take precedence over the common properties.
 This is useful if you want to use different OpenAI accounts for different models and different model endpoints.
@@ -644,4 +649,3 @@ This is useful when you need to:
 * Retrieve the API key from a secure key store
 * Rotate API keys dynamically
 * Implement custom API key selection logic
-