Complete API Integration Guide

This tutorial covers production-grade integration patterns for the DeepSeek V4 API.

Streaming Output

stream = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Write a poem about AI"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Function Calling

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string"}
            }
        }
    }
}]

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "What's the weather in Beijing today?"}],
    tools=tools
)

Error Handling

from openai import RateLimitError, APIError
import time

for attempt in range(3):
    try:
        response = client.chat.completions.create(...)
        break
    except RateLimitError:
        time.sleep(2 ** attempt)
    except APIError as e:
        print(f"API error: {e}")

Production Recommendations

1. Store API keys in environment variables — never hardcode secrets
2. Set reasonable max_tokens limits to control cost
3. Use context compression or summarization for long conversations
4. DSpark acceleration is enabled by default on API to reduce latency