Code Examples

Ready-to-use examples in your preferred language. All examples use the OpenAI SDK with our base URL.

💡 Before you begin
Replace YOUR_API_KEY with your actual API key. Get one free with code DEVSTARTER20.

Chat Completions

The most common use case: send a conversation and get a response.

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.7,
    max_tokens=500
)

print(response.choices[0].message.content)
print(f"Tokens used: {response.usage.total_tokens}")
javascript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1'
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'deepseek-ai/DeepSeek-V4-Pro',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Explain quantum computing in simple terms.' }
    ],
    temperature: 0.7,
    max_tokens: 500
  });

  console.log(response.choices[0].message.content);
  console.log(`Tokens used: ${response.usage.total_tokens}`);
}

main();
java
// Add to pom.xml: com.openai:openai-java:0.8.0
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;

public class ChatExample {
    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.builder()
            .apiKey("YOUR_API_KEY")
            .baseUrl("https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1")
            .build();

        ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
            .model("deepseek-ai/DeepSeek-V4-Pro")
            .addSystemMessage("You are a helpful assistant.")
            .addUserMessage("Explain quantum computing in simple terms.")
            .temperature(0.7)
            .maxTokens(500)
            .build();

        ChatCompletion completion = client.chat().completions().create(params);
        System.out.println(completion.choices().get(0).message().content());
    }
}
go
package main

import (
    "context"
    "fmt"
    "log"

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

func main() {
    config := openai.DefaultConfig("YOUR_API_KEY")
    config.BaseURL = "https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"

    client := openai.NewClientWithConfig(config)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "deepseek-ai/DeepSeek-V4-Pro",
            Messages: []openai.ChatCompletionMessage{
                {Role: openai.ChatMessageRoleSystem, Content: "You are a helpful assistant."},
                {Role: openai.ChatMessageRoleUser, Content: "Explain quantum computing in simple terms."},
            },
            Temperature: 0.7,
            MaxTokens:   500,
        },
    )
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(resp.Choices[0].Message.Content)
}
bash
curl https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

Streaming Responses

Get real-time token-by-token responses using Server-Sent Events.

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"
)

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Write a short poem about AI."}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()  # Final newline
javascript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1'
});

async function main() {
  const stream = await client.chat.completions.create({
    model: 'deepseek-ai/DeepSeek-V4-Pro',
    messages: [{ role: 'user', content: 'Write a short poem about AI.' }],
    stream: true
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
  }
  console.log();
}

main();
bash
curl https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [{"role": "user", "content": "Write a short poem about AI."}],
    "stream": true
  }'

Embeddings

Generate vector embeddings for semantic search, RAG, and clustering.

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"
)

# Single text embedding
response = client.embeddings.create(
    model="Qwen/Qwen3-Embedding-8B",
    input="The quick brown fox jumps over the lazy dog"
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")

# Batch embeddings
response = client.embeddings.create(
    model="Qwen/Qwen3-Embedding-8B",
    input=[
        "Machine learning is a subset of AI",
        "Deep learning uses neural networks",
        "Natural language processing handles text"
    ]
)

for item in response.data:
    print(f"[{item.index}] dims={len(item.embedding)}")
bash
curl https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-Embedding-8B",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Vision (Image Understanding)

Analyze images with Qwen-VL models. Send image URLs or base64-encoded images.

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"
)

response = client.chat.completions.create(
    model="qwen-vl-max",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe what you see in this image."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg"
                    }
                }
            ]
        }
    ]
)

print(response.choices[0].message.content)

Function Calling

Enable the model to call external tools and functions.

python
import json
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City name"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["location"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "What's the weather in Shanghai?"}],
    tools=tools,
    tool_choice="auto"
)

message = response.choices[0].message
if message.tool_calls:
    for call in message.tool_calls:
        args = json.loads(call.function.arguments)
        print(f"Calling: {call.function.name}({args})")
        # Execute your function here and return result

Multi-Turn Conversation

Maintain context across multiple exchanges by including previous messages.

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bb71d3f3506709ed-101-126-19-34.serveousercontent.com/v1"
)

messages = [
    {"role": "system", "content": "You are a Python programming tutor."}
]

# Simulate a conversation
questions = [
    "What is a list comprehension?",
    "Can you show an example?",
    "How is it different from map()?"
]

for question in questions:
    messages.append({"role": "user", "content": question})
    
    response = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V4-Pro",
        messages=messages
    )
    
    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    
    print(f"Q: {question}")
    print(f"A: {reply}\n")
    print("---")

🎁 Start Coding for Free

Use code DEVSTARTER20 to get ¥20 free credit — enough for thousands of API calls.

Get API Key →