openai-kotlin

What it is

OpenAI API client for Kotlin. It provides a multiplatform Kotlin client for OpenAI APIs with coroutine support and various features (Chat, Images, Embeddings, Files, fine-tuning, Moderations, Audio, Batch, etc.).

How it works

The library exposes an OpenAI client that you instantiate with a token and optional configuration, then use the client to perform API requests. It supports multiple targets and engines based on Ktor HTTP client configurations. The README references a pre-configured OpenAIConfig for building the client and describes using different engines per target.

Getting started

Install via Gradle by adding the dependency:

repositories {
    mavenCentral()
}

dependencies {
    implementation "com.aallam.openai:openai-client:4.1.0"
}

Or use the BOM approach:

dependencies {
    // import Kotlin API client BOM
    implementation platform('com.aallam.openai:openai-client-bom:4.1.0')

    // define dependencies without versions
    implementation 'com.aallam.openai:openai-client'
    runtimeOnly 'io.ktor:ktor-client-okhttp'
}

Create an OpenAI instance:

val openai = OpenAI(
    token = "your-api-key",
    timeout = Timeout(socket = 60.seconds),
    // additional configurations...
)

Or with OpenAIConfig:

val config = OpenAIConfig(
    token = apiKey,
    timeout = Timeout(socket = 60.seconds),
    // additional configurations...
)

val openAI = OpenAI(config)

Supported features include: Responses, Models, Chat, Images, Embeddings, Files, Fine-tuning, Moderations, Audio, Batch, and beta features like Assistants, Threads, Messages, Runs, Vector Stores.

Quick usage notes

• Documentation and guides are linked in the repository.
• Environment variables are recommended for API key handling.

Recent releases

• 4.1.0 (2026-02-07): Added batch support by making OpenAI interface extend Batch; added Responses API support (create, retrieve, cancel, delete, input_items listing); various internal changes.
• 4.0.1 (2025-02-02): Added chat features like reasoning effort, max completion tokens, store options for reasoning model support.
• 4.0.0 (2025-02-02): WasmJs target; added structured response for assistants; chat structured outputs; updated ChatCompletionRequest (and related features).
• 4.0.0-beta01 (2024-10-28): WasmJs target; structured response for assistants.

Traction

• Stars: 1842
• Forks: 237
• Open issues: 81

License

MIT

Behind the repo

Not provided in the facts block beyond the repository metadata.

Caveats

License: MIT; age since creation: 2021-03-06; last push: 2026-02-07. No further caveats specified in the provided content.