### .NET SDK Setup

Source: https://docs.apiyi.com/en/api-capabilities/openai/compatible

Install the OpenAI .NET package and configure the client with your API key and the compatible API base URL. This example demonstrates getting a chat client and completing a chat.

```bash
dotnet add package OpenAI
```

```csharp
using OpenAI;
using OpenAI.Chat;

var client = new OpenAIClient(
    new System.ClientModel.ApiKeyCredential("YOUR_API_KEY"),
    new OpenAIClientOptions { Endpoint = new Uri("https://api.apiyi.com/v1") }
);

var chatClient = client.GetChatClient("gpt-5.4");
var response = await chatClient.CompleteChatAsync("Hello!");
Console.WriteLine(response.Value.Content[0].Text);
```

--------------------------------

### Go SDK Setup

Source: https://docs.apiyi.com/en/api-capabilities/openai/compatible

Install the official OpenAI Go SDK and configure the client with your API key and the compatible API base URL. This example shows how to create a new chat completion.

```bash
go get github.com/openai/openai-go
```

```go
package main

import (
    "context"
    "fmt"

    "github.com/openai/openai-go"
    "github.com/openai/openai-go/option"
)

func main() {
    client := openai.NewClient(
        option.WithAPIKey("YOUR_API_KEY"),
        option.WithBaseURL("https://api.apiyi.com/v1"),
    )

    completion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
        Model: "gpt-5.4",
        Messages: []openai.ChatCompletionMessageParamUnion{
            openai.UserMessage("Hello!"),
        },
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(completion.Choices[0].Message.Content)
}
```

--------------------------------

### Python OpenAI SDK Examples for Qwen3.6

Source: https://docs.apiyi.com/en/api-capabilities/qwen-3-6/overview

Use these examples to interact with Qwen3.6 models via the OpenAI SDK. Ensure you have the SDK installed and replace 'sk-your-api-key' with your actual API key. The `base_url` should be set to 'https://api.apiyi.com/v1'.

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.apiyi.com/v1"
)

# Max-Preview: coding Agent driver
resp = client.chat.completions.create(
    model="qwen3.6-max-preview",
    messages=[
        {"role": "system", "content": "You are a senior Python engineer. Return changes as a unified diff."},
        {"role": "user", "content": "Add type hints and fix any latent bugs in this snippet ..."}
    ]
)
print(resp.choices[0].message.content)
```

```python
# Flash: image + text multimodal input
resp = client.chat.completions.create(
    model="qwen3.6-flash",
    messages=[
        {"role": "user", "content": [
            {"type": "text", "text": "Describe the key information in this image."},
            {"type": "image_url", "image_url": {"url": "https://your-image-url.png"}}
        ]}
    ]
)
print(resp.choices[0].message.content)
```

```python
# Plus: daily dialog and mid-complexity reasoning
resp = client.chat.completions.create(
    model="qwen3.6-plus",
    messages=[{"role": "user", "content": "Introduce yourself in one sentence."}]
)
print(resp.choices[0].message.content)
```

--------------------------------

### Quickstart: OpenAI-Compatible API

Source: https://docs.apiyi.com/en/news/kimi-k2-6-launch

Initialize the OpenAI client with your API key and base URL to interact with the Kimi K2.6 model. This example demonstrates a typical use case for agentic coding and tool calls.

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-apiyi-key",
    base_url="https://api.apiyi.com/v1"
)

# Typical use: agentic coding + tool calls
resp = client.chat.completions.create(
    model="kimi-k2.6",
    messages=[
        {"role": "system", "content": "You are a senior full-stack engineer who ships real PR-scale work in production repos."},
        {"role": "user", "content": "Migrate this repo's logging layer to structlog and produce the minimal-diff PR."}
    ],
    temperature=0.3,
)
print(resp.choices[0].message.content)
```

--------------------------------

### Node.js OpenAI SDK Example for Qwen3.6

Source: https://docs.apiyi.com/en/api-capabilities/qwen-3-6/overview

This Node.js example demonstrates how to use the OpenAI SDK to interact with Qwen3.6 models. Ensure you have the SDK installed and replace 'sk-your-api-key' with your actual API key. Set `baseURL` to 'https://api.apiyi.com/v1'.

```javascript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: 'https://api.apiyi.com/v1',
});

const resp = await client.chat.completions.create({
  model: 'qwen3.6-plus',
  messages: [{ role: 'user', content: 'Introduce yourself in one sentence.' }],
});

console.log(resp.choices[0].message.content);
```

--------------------------------

### Python SDK Setup

Source: https://docs.apiyi.com/en/api-capabilities/openai/compatible

Install the OpenAI Python SDK and configure the client with your API key and the compatible API base URL. Alternatively, use environment variables for configuration.

```bash
pip install openai
```

```python
from openai import OpenAI, AsyncOpenAI

# Synchronous client
client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

# Async client
async_client = AsyncOpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)
```

```bash
export OPENAI_API_KEY="YOUR_API_KEY"
export OPENAI_BASE_URL="https://api.apiyi.com/v1"
```

```python
from openai import OpenAI
client = OpenAI()  # reads the environment automatically
```

--------------------------------

### Java SDK Setup

Source: https://docs.apiyi.com/en/api-capabilities/openai/compatible

Add the official OpenAI Java SDK to your project and configure the client with your API key and the compatible API base URL. This example demonstrates creating a chat completion.

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

```java
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .apiKey("YOUR_API_KEY")
    .baseUrl("https://api.apiyi.com/v1")
    .build();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("gpt-5.4")
    .addUserMessage("Hello!")
    .build();

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

--------------------------------

### Quick Start Image Generation (Google Native Format)

Source: https://docs.apiyi.com/en/news/nano-banana-2-launch

This example demonstrates how to generate an image using the recommended Google Native Format. It requires the 'requests' and 'base64' libraries. The generated image is saved as 'output.png'.

```python
import requests
import base64

API_KEY = "sk-your-api-key"

response = requests.post(
    "https://api.apiyi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={
        "contents": [{"parts": [{"text": "A cute Shiba Inu sitting under cherry blossom trees, watercolor style"}]}],
        "generationConfig": {
            "responseModalities": ["IMAGE"],
            "imageConfig": {"aspectRatio": "16:9", "imageSize": "2K"}
        }
    },
    timeout=300
).json()

img_data = response["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
with open("output.png", 'wb') as f:
    f.write(base64.b64decode(img_data))
print("Image saved")
```

--------------------------------

### Gemini Native Format Quick Start

Source: https://docs.apiyi.com/en/api-capabilities/gemini/native

Examples demonstrating how to call the Gemini native format using the google-genai SDK in Python, Node.js, and cURL.

```APIDOC
## Gemini Native Format Quick Start

Use Google's official unified SDK `google-genai`:

```bash
pip install google-genai
```

### Python Example

```python
from google import genai

client = genai.Client(
    api_key="YOUR_API_KEY",  # your APIYI key
    http_options={"base_url": "https://api.apiyi.com"}
)

response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Introduce yourself in one sentence"
)
print(response.text)
```

### Node.js Example

```javascript
import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({
    apiKey: 'YOUR_API_KEY',
    httpOptions: { baseUrl: 'https://api.apiyi.com' }
});

const response = await ai.models.generateContent({
    model: 'gemini-3.5-flash',
    contents: 'Introduce yourself in one sentence'
});
console.log(response.text);
```

### cURL Example

```bash
curl "https://api.apiyi.com/v1beta/models/gemini-3.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Introduce yourself in one sentence"}]}]
  }'
```

**Note**: The `base_url` is `https://api.apiyi.com` (without `/v1`). Use your APIYI key, not a Google AI Studio key.
```

--------------------------------

### Get Text Embedding with OpenAI SDK

Source: https://docs.apiyi.com/en/api-capabilities/text-embedding

This Python example demonstrates how to get a vector representation of a single text using the OpenAI SDK. Ensure you have the SDK installed and replace YOUR_API_KEY with your actual API key.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

def get_embedding(text, model="text-embedding-3-small"):
    """Get vector representation of text"""
    response = client.embeddings.create(
        input=text,
        model=model
    )
    return response.data[0].embedding

# Usage example
text = "Artificial intelligence is changing the world"
embedding = get_embedding(text)

print(f"Vector dimensions: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")
```

--------------------------------

### Python Integration Example

Source: https://docs.apiyi.com/en/scenarios/chat/open-webui

Basic Python script setup for integrating with an API. This snippet requires the `requests` library and serves as a starting point for API interactions.

```python
import requests

```

--------------------------------

### Document Q&A System Setup

Source: https://docs.apiyi.com/en/scenarios/engineering/langchain

Set up a Document Q&A system by loading, splitting, and embedding documents, then creating a RetrievalQA chain.

```python
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA

embeddings = OpenAIEmbeddings(
    api_key="Your APIYI key",
    base_url="https://api.apiyi.com/v1"
)

loader = TextLoader("document.txt")
documents = loader.load()

text_splitter = CharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=0
)
texts = text_splitter.split_documents(documents)

vectorstore = FAISS.from_documents(texts, embeddings)

qa = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever()
)

result = qa.run("What are the key concepts in the document?")
```

--------------------------------

### Node.js / TypeScript SDK Setup

Source: https://docs.apiyi.com/en/api-capabilities/openai/compatible

Install the OpenAI Node.js SDK and configure the client with your API key and the compatible API base URL. This example shows how to make a chat completion request.

```bash
npm install openai
```

```typescript
import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  baseURL: 'https://api.apiyi.com/v1'
});

const response = await openai.chat.completions.create({
  model: 'gpt-5.4-mini',
  messages: [{ role: 'user', content: 'Hello!' }],
  temperature: 0.7
});
```

--------------------------------

### Run OpenClaw Setup Wizard

Source: https://docs.apiyi.com/en/scenarios/agent/openclaw/config-cli

Initiates the interactive setup wizard for new users to configure OpenClaw. Follow the prompts to set up model providers, API keys, and other settings.

```bash
openclaw onboard
```

--------------------------------

### Start FastClaw Service

Source: https://docs.apiyi.com/en/scenarios/agent/fastclaw

Commands to start FastClaw in the foreground, as a background daemon, or install it as a system service.

```bash
fastclaw                    # Foreground (Ctrl+C to stop)
fastclaw daemon start       # Background (logs at ~/.fastclaw/daemon.log)
fastclaw daemon install     # Register as a launchd / systemd service
```

--------------------------------

### Quickstart with OpenAI-compatible API

Source: https://docs.apiyi.com/en/news/deepseek-v4-launch

Use this snippet to interact with Deepseek V4 models via an OpenAI-compatible API. Configure your API key and base URL. The `reasoning_effort` parameter can be set to 'max' for complex tasks.

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-apiyi-key",
    base_url="https://api.apiyi.com/v1"
)

# Flagship: V4-Pro at max reasoning effort for complex agents
resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "You are a senior full-stack engineer."},
        {"role": "user", "content": "Implement a circuit-breaker retry strategy for login in the existing repo."}
    ],
    extra_body={"reasoning_effort": "max"}
)
print(resp.choices[0].message.content)
```

--------------------------------

### Generate Product Photography with GPT-Image-1.5

Source: https://docs.apiyi.com/en/api-capabilities/gpt-image-1-5

This example demonstrates generating professional product photography. The prompt should detail the product, setting, lighting, and desired angle for optimal results.

```python
{/* Product showcase example */}
response = client.images.generate(
    model="gpt-image-1.5",
    prompt="Professional product photography of modern wireless earbuds case on white marble surface, soft studio lighting, 45-degree angle, clean background",
    size="1024x1024",
    quality="high"
)
```

--------------------------------

### Get Text Embedding with curl

Source: https://docs.apiyi.com/en/api-capabilities/text-embedding

Use this command-line example to quickly get a text embedding. Replace YOUR_API_KEY with your actual API key.

```bash
curl https://api.apiyi.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "input": "Artificial intelligence is changing the world",
    "model": "text-embedding-3-small"
  }'
```

--------------------------------

### Set Model ID in Setup

Source: https://docs.apiyi.com/en/scenarios/agent/openclaw/config-cli

Enter the desired model ID for your configuration during the OpenClaw setup. Examples include 'gpt-5.4', 'claude-sonnet-4-6', etc.

```text
gpt-5.4
```

--------------------------------

### Example of a Good Prompt for HTTP Middleware

Source: https://docs.apiyi.com/en/scenarios/programming/opencode

Use specific and detailed prompts to guide the AI in generating the desired code. This example shows how to request an HTTP middleware in TypeScript with logging capabilities.

```text
❌ Poor prompt: Help me write code

✅ Good prompt: Write an HTTP middleware in TypeScript that
logs requests, including request method, path,
response time, and status code, using pino for output
```

--------------------------------

### Structured Prompt Example

Source: https://docs.apiyi.com/en/scenarios/engineering/dify

This text example outlines a structured prompt format for Dify applications, including role definition, task description, output format, and constraints. This helps in guiding the model to produce desired outputs.

```text
# Structured Prompt
## Role Definition
You are a professional [specific role]

## Task Description
Please help users with [specific task]

## Output Format
Please output in the following format:
1. Overview
2. Detailed Analysis
3. Recommendations

## Constraints
- Answers must be accurate
- Language should be clear
- Keep length within 500 words
```

--------------------------------

### Install OpenCode via cURL

Source: https://docs.apiyi.com/en/scenarios/programming/opencode

Use this command for a quick and recommended installation of OpenCode.

```bash
curl -fsSL https://opencode.ai/install | bash
```

--------------------------------

### Start OpenCode in Current Directory

Source: https://docs.apiyi.com/en/scenarios/programming/opencode

Launches the OpenCode interactive terminal in the current working directory. No additional setup is required.

```bash
opencode
```

--------------------------------

### Install google-genai SDK

Source: https://docs.apiyi.com/en/api-capabilities/gemini/native

Install the official Google unified SDK for Gemini. Use this SDK for the native Gemini API.

```bash
pip install google-genai
```

--------------------------------

### Start Hermes Agent TUI

Source: https://docs.apiyi.com/en/scenarios/agent/hermes-agent

After installation, reload your shell and use this command to launch the Hermes Agent's Text-based User Interface (TUI).

```bash
source ~/.bashrc    # or source ~/.zshrc
hermes              # Launches the TUI, ready to chat
```

--------------------------------

### Quick Start: Gemini Native Format in Python

Source: https://docs.apiyi.com/en/api-capabilities/gemini/native

Initialize the Gemini client with your APIYI key and the APIYI base URL. Then, generate content using the specified model.

```python
from google import genai

client = genai.Client(
    api_key="YOUR_API_KEY",  # your APIYI key
    http_options={"base_url": "https://api.apiyi.com"}
)

response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Introduce yourself in one sentence"
)
print(response.text)
```

--------------------------------

### Prompt Optimization Example

Source: https://docs.apiyi.com/en/scenarios/chat/chatgpt-next-web

Structure your prompts effectively by defining a role, task, and output requirements. This helps in getting more precise and relevant responses from the AI.

```markdown
# Role Setting
You are an experienced [specific role]

# Task Description
Please help me [specific task]

# Output Requirements
- Requirement 1
- Requirement 2
```

--------------------------------

### Install OpenClaw using Quick Install Script

Source: https://docs.apiyi.com/en/scenarios/agent/openclaw/installation

Execute a curl command to download and run the OpenClaw installation script on Linux/macOS.

```bash
curl -fsSL https://openclaw.ai/install.sh | bash
```

--------------------------------

### Prompt Optimization Examples

Source: https://docs.apiyi.com/en/api-capabilities/gpt-image-1

Examples demonstrating how to improve image generation results by providing more detailed prompts, specifying artistic styles, and defining composition and perspective.

```python
# Basic prompt
prompt_basic = "a cat"

# Optimized prompt
prompt_detailed = "a fluffy white Persian cat sitting on a vintage velvet cushion, soft natural lighting, professional photography, shallow depth of field"
```

```python
styles = [
    "in the style of Studio Ghibli anime",
    "photorealistic, professional photography",
    "digital art, concept art style",
    "oil painting, impressionist style",
    "minimalist, flat design illustration"
]
```

```python
compositions = [
    "close-up portrait, centered composition",
    "wide angle landscape shot, rule of thirds",
    "aerial view, bird's eye perspective",
    "low angle shot, dramatic perspective"
]
```

--------------------------------

### Get Programming Assistance from OpenClaw

Source: https://docs.apiyi.com/en/scenarios/agent/openclaw/usage

Examples of how to ask OpenClaw for help with programming tasks, including script generation, code debugging, and HTML creation.

```text
> Write a Python script to batch rename files

> What's wrong with this code: [paste code]

> Create a simple HTML page for me
```

--------------------------------

### Code Generation: Go Concurrent Cache

Source: https://docs.apiyi.com/en/scenarios/programming/roo-code

Example of Roo Code generating Go code for a concurrent-safe cache with Set, Get, Delete, and expired data clearing functionalities.

```go
// Requirement: Implement a concurrent-safe cache
// Support Set, Get, Delete, clear expired data

// Roo Code generates complete Go code
package cache

import (
	"sync"
	time
)

type Cache struct {
	// ... complete implementation
}
```

--------------------------------

### OpenCode Command Execution Examples

Source: https://docs.apiyi.com/en/scenarios/programming/opencode

Examples of how to instruct OpenCode to execute terminal commands and analyze their output. Useful for running tests or managing dependencies.

```text
> Run npm test and analyze the failed tests
```

```text
> Execute npm install and check for dependency conflicts
```

--------------------------------

### Good Prompt Example for High-Res Images

Source: https://docs.apiyi.com/en/news/nano-banana-pro-launch

This example illustrates a good prompt for generating high-resolution images, focusing on detail and professional quality. Vague prompts should be avoided.

```text
✅ Good Prompt:
"A 4K ultra-HD product photo, rich details, professional photography,
studio lighting, white background, centered product, soft shadows"

❌ Avoid:
"Product photo"  # Lacks detail
```