DeepSeek V4 Flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput applications, ideal for chat, summarization, and general-purpose tasks.

Quick Reference

Pricing

When to Use Flash vs Pro

Example

from openai import OpenAI

client = OpenAI(
    base_url="https://openapi.linkwo.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[
        {"role": "user", "content": "Summarize this article in 3 bullet points: ..."}
    ],
    temperature=0.5
)

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

Related

• DeepSeek V4 Pro — More capable for complex tasks
• DeepSeek Reasoner — Reasoning-focused model
• Model Overview — All available models