Java

Gunakan library resmi openai-java dengan api14. Atur baseUrl pada client builder dan kirim ID model (misalnya openai/gpt-5-mini) sebagai string biasa.

Instalasi

Gradle:

implementation("com.openai:openai-java:4.+")

Maven:

<dependency>
  <groupId>com.openai</groupId>
  <artifactId>openai-java</artifactId>
  <version>LATEST</version>
</dependency>

Lalu atur API14_API_KEY=sk-api14-... di environment Anda.

Konfigurasi

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://api14.com/api/v1")
    .apiKey(System.getenv("API14_API_KEY"))
    .build();

OpenAIOkHttpClient.fromEnv() membaca OPENAI_BASE_URL dan OPENAI_API_KEY, sehingga Anda dapat berpindah environment tanpa mengubah kode:

export OPENAI_BASE_URL="https://api14.com/api/v1"
export OPENAI_API_KEY="sk-api14-..."

Chat

import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("openai/gpt-5-mini")
    .addUserMessage("Explain vector databases in two sentences.")
    .build();

ChatCompletion completion = client.chat().completions().create(params);
completion.choices().get(0).message().content().ifPresent(System.out::println);

Streaming

import com.openai.core.http.StreamResponse;
import com.openai.models.chat.completions.ChatCompletionChunk;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("anthropic/claude-sonnet-4.5")
    .addUserMessage("Write a haiku about APIs.")
    .build();

try (StreamResponse<ChatCompletionChunk> stream = client.chat().completions().createStreaming(params)) {
    stream.stream()
        .flatMap(chunk -> chunk.choices().stream())
        .flatMap(choice -> choice.delta().content().stream())
        .forEach(System.out::print);
}

Lihat Streaming.

Tool calling

Deskripsikan tool sebagai class; SDK menurunkan JSON Schema-nya dan mem-parse argumen kembali ke class tersebut:

import com.fasterxml.jackson.annotation.JsonClassDescription;
import com.openai.models.chat.completions.*;
import java.util.Collection;

@JsonClassDescription("Current weather for a city")
static class GetWeather {
    public String city;
}

ChatCompletionCreateParams.Builder builder = ChatCompletionCreateParams.builder()
    .model("openai/gpt-5-mini")
    .addTool(GetWeather.class)
    .addUserMessage("What's the weather in Istanbul?");

while (true) {
    ChatCompletionMessage message = client.chat().completions().create(builder.build())
        .choices().get(0).message();
    builder.addMessage(message);
    if (message.toolCalls().map(Collection::isEmpty).orElse(true)) {
        message.content().ifPresent(System.out::println);
        break;
    }
    for (ChatCompletionMessageToolCall call : message.toolCalls().get()) {
        GetWeather args = call.asFunction().function().arguments(GetWeather.class);
        builder.addMessage(ChatCompletionToolMessageParam.builder()
            .toolCallId(call.asFunction().id())
            .contentAsJson(getWeather(args.city)) // your function
            .build());
    }
}

Builder menyimpan seluruh percakapan: setiap putaran loop menambahkan pesan assistant beserta panggilan tool-nya, lalu satu pesan tool per panggilan, dan mengirim semuanya lagi. Field pada class tool menjadi properti skema; tambahkan @JsonPropertyDescription pada field untuk memberi tahu model artinya. Batasi jumlah iterasi di kode production agar model yang terus memanggil tool tidak berputar selamanya. Lihat Tool calling.

Structured output

Kirim class ke responseFormat; SDK menghasilkan JSON Schema yang ketat darinya dan mem-parse konten setiap choice menjadi sebuah instance. Gunakan model yang mencantumkan structured_outputs atau response_format di supported_parameters-nya:

static class Person {
    public String name;
    public int born;
    public String city;
}

StructuredChatCompletionCreateParams<Person> params = ChatCompletionCreateParams.builder()
    .model("openai/gpt-5-mini")
    .responseFormat(Person.class)
    .addUserMessage("Extract: Ada Lovelace, born 1815 in London.")
    .build();

client.chat().completions().create(params).choices().stream()
    .flatMap(choice -> choice.message().content().stream())
    .forEach(person -> System.out.println(person.name + " " + person.born));

Lihat Structured outputs.

Input gambar

import java.util.List;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("google/gemini-2.5-flash")
    .addUserMessageOfArrayOfContentParts(List.of(
        ChatCompletionContentPart.ofText(ChatCompletionContentPartText.builder()
            .text("What is in this picture?").build()),
        ChatCompletionContentPart.ofImageUrl(ChatCompletionContentPartImage.builder()
            .imageUrl(ChatCompletionContentPartImage.ImageUrl.builder()
                .url("https://example.com/photo.jpg") // or a data:image/png;base64,... URL
                .build())
            .build())))
    .build();

Lihat Vision dan file.

Parameter tambahan

Field gateway tanpa setter bertipe (reasoning, provider, models) dikirim lewat putAdditionalBodyProperty:

import com.openai.core.JsonValue;
import java.util.Map;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("anthropic/claude-sonnet-4.5")
    .addUserMessage("Prove there are infinitely many primes.")
    .putAdditionalBodyProperty("reasoning", JsonValue.from(Map.of("effort", "high")))
    .build();

Error

Respons non-2xx melempar subclass dari OpenAIServiceException, yang menyediakan status dan header:

import com.openai.errors.OpenAIServiceException;

try {
    client.chat().completions().create(params);
} catch (OpenAIServiceException e) {
    if (e.statusCode() == 402) {
        System.err.println("Balance too low, add funds (insufficient_balance)");
    } else if (e.statusCode() == 429) {
        System.err.println("Rate limited, retry after " + e.headers().values("Retry-After") + "s");
    } else {
        throw e;
    }
}

Lihat Error.

Timeout dan retry

Klien mengulang error koneksi, 408, 409, 429, dan 5xx sebanyak dua kali secara default dengan exponential backoff. Atur jumlah dan timeout pada builder, atau per request:

import com.openai.core.RequestOptions;
import java.time.Duration;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://api14.com/api/v1")
    .apiKey(System.getenv("API14_API_KEY"))
    .maxRetries(4)
    .timeout(Duration.ofSeconds(60))
    .build();

client.chat().completions().create(params,
    RequestOptions.builder().timeout(Duration.ofMinutes(5)).build());

Timeout pada builder berlaku untuk setiap percobaan. Request reasoning yang panjang bisa memakan waktu beberapa menit, jadi beri timeout per request yang lebih panjang atau gunakan streaming. Mengulang tidak membantu untuk daily_limit_reached atau insufficient_balance; tangkap RateLimitException dan periksa kode error sebelum menjadwalkan percobaan lain. Lihat Batas laju.

Semua kemampuan

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.chat.completions.create({
  "model": "openai/gpt-5-mini",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);