OpenAI Chat

Spring AI supports ChatGPT, the AI language model by OpenAI. ChatGPT has been instrumental in sparking interest in AI-driven text generation, thanks to its creation of industry-leading text generation models and embeddings.


You will need to create an API with OpenAI to access ChatGPT models. Create an account at OpenAI signup page and generate the token on the API Keys page. The Spring AI project defines a configuration property named that you should set to the value of the API Key obtained from Exporting an environment variable is one way to set that configuration property:


Add Repositories and BOM

Spring AI artifacts are published in Spring Milestone and Snapshot repositories. Refer to the Repositories section to add these repositories to your build system.

To help with dependency management, Spring AI provides a BOM (bill of materials) to ensure that a consistent version of Spring AI is used throughout the entire project. Refer to the Dependency Management section to add the Spring AI BOM to your build system.


Spring AI provides Spring Boot auto-configuration for the OpenAI Chat Client. To enable it add the following dependency to your project’s Maven pom.xml file:


or to your Gradle build.gradle build file.

dependencies {
    implementation ''
Refer to the Dependency Management section to add the Spring AI BOM to your build file.

Chat Properties

Retry Properties

The prefix is used as the property prefix that lets you configure the retry mechanism for the OpenAI chat model.

Property Description Default

Maximum number of retry attempts.


Initial sleep duration for the exponential backoff policy.

2 sec.

Backoff interval multiplier.


Maximum backoff duration.

3 min.

If false, throw a NonTransientAiException, and do not attempt retry for 4xx client error codes


List of HTTP status codes that should not trigger a retry (e.g. to throw NonTransientAiException).


List of HTTP status codes that should trigger a retry (e.g. to throw TransientAiException).


Connection Properties

The prefix is used as the property prefix that lets you connect to OpenAI.

Property Description Default

The URL to connect to

The API Key


Configuration Properties

The prefix is the property prefix that lets you configure the chat model implementation for OpenAI.

Property Description Default

Enable OpenAI chat model.


Optional overrides the to provide chat specific url


Optional overrides the to provide chat specific api-key


This is the OpenAI Chat model to use. gpt-4o, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-0125-preview, gpt-4-turbo-preview, gpt-3.5-turbo, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106. See the models page for more information.


The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict.


Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.


Modify the likelihood of specified tokens appearing in the completion.


The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length.


How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.


Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.


An object specifying the format that the model must output. Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.


This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.


Up to 4 sequences where the API will stop generating further tokens.


An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.


A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.


Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type: "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present.


A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.


List of functions, identified by their names, to enable for function calling in a single prompt requests. Functions with those names must exist in the functionCallbacks registry.


(For streaming only) Set to add an additional chunk with token usage statistics for the entire request. The choices field for this chunk is an empty array and all other chunks will also include a usage field, but with a null value.


You can override the common and for the ChatModel and EmbeddingModel implementations. The and 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.
All properties prefixed with can be overridden at runtime by adding a request specific Runtime Options to the Prompt call.

Runtime Options

The provides model configurations, such as the model to use, the temperature, the frequency penalty, etc.

On start-up, the default options can be configured with the OpenAiChatModel(api, options) constructor or the* properties.

At run-time you can override the default options by adding new, request specific, options to the Prompt call. For example to override the default model and temperature for a specific request:

ChatResponse response =
    new Prompt(
        "Generate the names of 5 famous pirates.",
In addition to the model specific OpenAiChatOptions you can use a portable ChatOptions instance, created with the ChatOptionsBuilder#builder().

Function Calling

You can register custom Java functions with the OpenAiChatModel and have the OpenAI model intelligently choose to output a JSON object containing arguments to call one or many of the registered functions. This is a powerful technique to connect the LLM capabilities with external tools and APIs. Read more about OpenAI Function Calling.


Multimodality refers to a model’s ability to simultaneously understand and process information from various sources, including text, images, audio, and other data formats. Presently, the OpenAI gpt-4-visual-preview and gpt-4o models offers multimodal support. Refer to the Vision guide for more information.

The OpenAI User Message API can incorporate a list of base64-encoded images or image urls with the message. Spring AI’s Message interface facilitates multimodal AI models by introducing the Media type. This type encompasses data and details regarding media attachments in messages, utilizing Spring’s org.springframework.util.MimeType and a java.lang.Object for the raw media data.

Below is a code example excerpted from, illustrating the fusion of user text with an image using the the GPT_4_VISION_PREVIEW model.

byte[] imageData = new ClassPathResource("/multimodal.test.png").getContentAsByteArray();

var userMessage = new UserMessage("Explain what do you see on this picture?",
        List.of(new Media(MimeTypeUtils.IMAGE_PNG, imageData)));

ChatResponse response = Prompt(List.of(userMessage),

or the image URL equivalent using the GPT_4_O model :

var userMessage = new UserMessage("Explain what do you see on this picture?",
        List.of(new Media(MimeTypeUtils.IMAGE_PNG,

ChatResponse response = Prompt(List.of(userMessage),
you can pass multiple images as well.

It takes as an input the multimodal.test.png image:

Multimodal Test Image

along with the text message "Explain what do you see on this picture?", and generates a response like this:

This is an image of a fruit bowl with a simple design. The bowl is made of metal with curved wire edges that
create an open structure, allowing the fruit to be visible from all angles. Inside the bowl, there are two
yellow bananas resting on top of what appears to be a red apple. The bananas are slightly overripe, as
indicated by the brown spots on their peels. The bowl has a metal ring at the top, likely to serve as a handle
for carrying. The bowl is placed on a flat surface with a neutral-colored background that provides a clear
view of the fruit inside.

Sample Controller

Create a new Spring Boot project and add the spring-ai-openai-spring-boot-starter to your pom (or gradle) dependencies.

Add a file, under the src/main/resources directory, to enable and configure the OpenAi chat model:
replace the api-key with your OpenAI credentials.

This will create a OpenAiChatModel implementation that you can inject into your class. Here is an example of a simple @Controller class that uses the chat model for text generations.

public class ChatController {

    private final OpenAiChatModel chatModel;

    public ChatController(OpenAiChatModel chatModel) {
        this.chatModel = chatModel;

    public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        return Map.of("generation",;

	public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));

Manual Configuration

The OpenAiChatModel implements the ChatModel and StreamingChatModel and uses the Low-level OpenAiApi Client to connect to the OpenAI service.

Add the spring-ai-openai dependency to your project’s Maven pom.xml file:


or to your Gradle build.gradle build file.

dependencies {
    implementation ''
Refer to the Dependency Management section to add the Spring AI BOM to your build file.

Next, create a OpenAiChatModel and use it for text generations:

var openAiApi = new OpenAiApi(System.getenv("OPENAI_API_KEY"));
var openAiChatOptions = OpenAiChatOptions.builder()
var chatModel = new OpenAiChatModel(openAiApi, openAiChatOptions);

ChatResponse response =
    new Prompt("Generate the names of 5 famous pirates."));

// Or with streaming responses
Flux<ChatResponse> response =
    new Prompt("Generate the names of 5 famous pirates."));

The OpenAiChatOptions provides the configuration information for the chat requests. The OpenAiChatOptions.Builder is fluent options builder.

Low-level OpenAiApi Client

The OpenAiApi provides is lightweight Java client for OpenAI Chat API OpenAI Chat API.

Following class diagram illustrates the OpenAiApi chat interfaces and building blocks:

OpenAiApi Chat API Diagram

Here is a simple snippet how to use the api programmatically:

OpenAiApi openAiApi =
    new OpenAiApi(System.getenv("OPENAI_API_KEY"));

ChatCompletionMessage chatCompletionMessage =
    new ChatCompletionMessage("Hello world", Role.USER);

// Sync request
ResponseEntity<ChatCompletion> response = openAiApi.chatCompletionEntity(
    new ChatCompletionRequest(List.of(chatCompletionMessage), "gpt-3.5-turbo", 0.8f, false));

// Streaming request
Flux<ChatCompletionChunk> streamResponse = openAiApi.chatCompletionStream(
        new ChatCompletionRequest(List.of(chatCompletionMessage), "gpt-3.5-turbo", 0.8f, true));

Follow the's JavaDoc for further information.

Low-level API Examples