uncloseai.

Swift Examples

This page demonstrates how to use the uncloseai. API endpoints with Swift using the SwiftOpenAI community library. All examples use the same OpenAI-compatible API interface, making it easy to switch between different models and endpoints.

Available Endpoints:

• hermes.ai.unturf.com: https://hermes.ai.unturf.com/v1 - chat completions on an RTX 4090
• qwen.ai.unturf.com: https://qwen.ai.unturf.com/v1 - chat completions on an RTX 3090
• TTS: https://speech.ai.unturf.com/v1 - Text-to-speech generation

Both chat hostnames currently serve the same model, turboderp/Qwen3.8-27B-exl3 (read live from /v1/models). Hostnames are routing labels, not model names: every example below asks the endpoint which model it serves instead of hard-coding an id, so a model swap on the cards never breaks your code. The served model reasons before it answers (the reasoning arrives in a separate reasoning field), so give it room: the samples ask for 600 tokens because at 150 the budget ran out before the answer began.

Many endpoints from environment variables

Our clients (uncloseai-cli, uncloseai.js, opencompletion and the downloadable implementation for every language on this site) share one convention, so an endpoint is configuration, never code:

export MODEL_ENDPOINT_0="https://hermes.ai.unturf.com/v1"
export MODEL_ENDPOINT_1="https://qwen.ai.unturf.com/v1"
# export MODEL_API_KEY_1="sk-..."      # only for an endpoint that needs one
export TTS_ENDPOINT_0="https://speech.ai.unturf.com/v1"

The first endpoint is the default; the rest fail over, in order. The downloadable implementations under /languages/ read these variables and discover each endpoint's models at startup.

Swift Client Installation

Add SwiftOpenAI to your Package.swift dependencies:

dependencies: [
    .package(url: "https://github.com/jamesrochabrun/SwiftOpenAI", from: "3.8.5")
]

Non-Streaming Examples

Non-streaming mode waits for the complete response before returning. This is simpler to use but provides no intermediate feedback during generation.

Using hermes.ai.unturf.com (RTX 4090)

import SwiftOpenAI

let service = OpenAIServiceFactory.service(
    apiKey: "choose-any-value",
    baseURL: "https://hermes.ai.unturf.com/v1"
)

// Ask the endpoint which model it serves; never hard-code an id.
let model = try await service.listModels().data[0].id

let parameters = ChatCompletionParameters(
    messages: [.init(role: .user, content: .text("Give a Python Fizzbuzz solution in one line of code?"))],
    model: .custom(model),
    temperature: 0.5,
    maxTokens: 600
)

do {
    let completion = try await service.startChat(parameters: parameters)
    if let content = completion.choices.first?.message.content {
        print(content)
    }
} catch {
    print("Error: \(error)")
}

Using qwen.ai.unturf.com (RTX 3090)

import SwiftOpenAI

let service = OpenAIServiceFactory.service(
    apiKey: "choose-any-value",
    baseURL: "https://qwen.ai.unturf.com/v1"
)

// Ask the endpoint which model it serves; never hard-code an id.
let model = try await service.listModels().data[0].id

let parameters = ChatCompletionParameters(
    messages: [.init(role: .user, content: .text("Give a Python Fizzbuzz solution in one line of code?"))],
    model: .custom(model),
    temperature: 0.5,
    maxTokens: 600
)

do {
    let completion = try await service.startChat(parameters: parameters)
    if let content = completion.choices.first?.message.content {
        print(content)
    }
} catch {
    print("Error: \(error)")
}

Streaming Examples

Streaming mode returns chunks of the response as they are generated, providing real-time feedback. This is ideal for interactive applications and long responses.

Using hermes.ai.unturf.com (RTX 4090)

import SwiftOpenAI

let service = OpenAIServiceFactory.service(
    apiKey: "choose-any-value",
    baseURL: "https://hermes.ai.unturf.com/v1"
)

// Ask the endpoint which model it serves; never hard-code an id.
let model = try await service.listModels().data[0].id

let parameters = ChatCompletionParameters(
    messages: [.init(role: .user, content: .text("Give a Python Fizzbuzz solution in one line of code?"))],
    model: .custom(model),
    temperature: 0.5,
    maxTokens: 600
)

do {
    let stream = try await service.startStreamedChat(parameters: parameters)
    for try await chunk in stream {
        if let content = chunk.choices.first?.delta.content {
            print(content, terminator: "")
        }
    }
} catch {
    print("Error: \(error)")
}

Using qwen.ai.unturf.com (RTX 3090)

import SwiftOpenAI

let service = OpenAIServiceFactory.service(
    apiKey: "choose-any-value",
    baseURL: "https://qwen.ai.unturf.com/v1"
)

// Ask the endpoint which model it serves; never hard-code an id.
let model = try await service.listModels().data[0].id

let parameters = ChatCompletionParameters(
    messages: [.init(role: .user, content: .text("Give a Python Fizzbuzz solution in one line of code?"))],
    model: .custom(model),
    temperature: 0.5,
    maxTokens: 600
)

do {
    let stream = try await service.startStreamedChat(parameters: parameters)
    for try await chunk in stream {
        if let content = chunk.choices.first?.delta.content {
            print(content, terminator: "")
        }
    }
} catch {
    print("Error: \(error)")
}

Text-to-Speech Example

Generate audio speech from text using the TTS endpoint. The audio is saved as an MP3 file.

import Foundation

// SwiftOpenAI's voice enum is closed to OpenAI's voice names, so call the
// speech endpoint directly: it is one JSON POST.
var request = URLRequest(url: URL(string: "https://speech.ai.unturf.com/v1/audio/speech")!)
request.httpMethod = "POST"
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.setValue("Bearer YOLO", forHTTPHeaderField: "Authorization")
request.httpBody = try JSONSerialization.data(withJSONObject: [
    "model": "tts-1-f5",
    "voice": "foxhop",
    "speed": 0.9,
    "input": "I think so therefore, Today is a wonderful day to grow something people love!",
])

do {
    let (audioData, _) = try await URLSession.shared.data(for: request)
    let fileURL = FileManager.default.temporaryDirectory.appendingPathComponent("speech.mp3")
    try audioData.write(to: fileURL)
    print("Audio saved to: \(fileURL)")
} catch {
    print("Error: \(error)")
}