devto 2026-09-10 원문 보기 ↗
Published: September 9, 2026 | Reading time: 10 minutes
On September 8, 2026, DeepSeek quietly launched a beta test for V4.1 Flash, an intermediate model with the identifier deepseek-v4.1-flash-expires-on-0910. The model name itself reveals the urgency—this beta expires on September 10, giving developers just 48 hours to test it.
What makes this launch remarkable isn't just the speed. It's that V4.1 Flash is DeepSeek's first native multimodal model, supporting both text and image input/output from the factory, not as an afterthought.
| Task | Speed Improvement |
|---|---|
| 49K Long Context Retrieval | 5.2x faster |
| SVG Code Generation | 6.0x faster |
| Manacher Palindrome Algorithm | 4.6x faster |
| Complex SQL Query Generation | 5.0x faster |
| Asyncio Architecture Refactoring | 3.9x faster |
Peak Performance: 420 tokens/second in long-text reasoning tasks, with end-to-end throughput reaching 409.5 tokens/second.
Real-World Test: A user sent a photo of a person in a striped suit. The model correctly identified the striped pattern, avoiding the hallucination issues that plagued earlier vision models.
Unlike V4 Flash Vision-Exp, which added a visual encoder as an "external plugin" on top of a text-only base, V4.1 Flash integrates text and image processing from the ground up. This means:
DeepSeek claims V4.1 Flash uses a "new model structure," but hasn't released a technical report. Community analysis suggests:
DeepSeek simultaneously announced hiring 150 senior engineers, focusing on:
As Cui Tianyi, DeepSeek Harness负责人, explained:
"When quantity increases, complexity explodes exponentially. Data volume, machine/container count, training tasks, evaluation tasks, Agent environments, user count, request volume—all are increasing dramatically. This creates complexity that old backend systems can't handle."
V4.1 Flash's speed isn't just a benchmark achievement. It enables:
from openai import OpenAI
client = OpenAI(
api_key="your-api-key",
base_url="https://api.deepseek.com/v1"
)
# Send an image with text prompt
response = client.chat.completions.create(
model="deepseek-v4.1-flash",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "What is the person wearing in this image?"},
{
"type": "image_url",
"image_url": {
"url": "https://example.com/person.jpg"
}
}
]
}
],
max_tokens=500
)
print(response.choices[0].message.content)
Despite the performance improvements, V4.1 Flash maintains the same pricing as V4 Flash. This is significant because:
Community reaction: When performance is high and price is low, Liang Wenfeng (DeepSeek's founder) becomes "梁圣" (Saint Liang). When prices rise, he becomes "梁子" (Little Liang). With V4.1 Flash, he's back to being 梁圣.
In the past month, Chinese AI models have been released at an unprecedented pace:
This "weekly release" rhythm is unprecedented in the AI industry.
| Model | Release Date | Key Feature |
|---|---|---|
| Kimi K3 | July 2026 | 2.8T parameters, native multimodal |
| GLM-5.3 | August 2026 | Post-training scaling, cyber security |
| DeepSeek V4 Pro | August 2026 | Million-token context, DSA attention |
| DeepSeek V4.1 Flash | September 2026 | Native multimodal, 420 tok/s |
import time
from openai import OpenAI
client = OpenAI(
api_key="your-api-key",
base_url="https://api.deepseek.com/v1"
)
def benchmark_model(prompt, model="deepseek-v4.1-flash"):
start = time.time()
response = client.chat.completions.create(
model=model,
messages=[{"role": "user", "content": prompt}],
max_tokens=1000
)
end = time.time()
tokens = len(response.choices[0].message.content.split())
duration = end - start
tps = tokens / duration
print(f"Model: {model}")
print(f"Tokens: {tokens}")
print(f"Duration: {duration:.2f}s")
print(f"Tokens/Second: {tps:.2f}")
return tps
# Test with a complex prompt
benchmark_model("""
Analyze the following code for performance issues:
python
def process_large_dataset(data):
results = []
for item in data:
result = complex_calculation(item)
results.append(result)
return results
Provide specific optimization suggestions with code examples.
""")
Speed Is a Feature: 420 tokens/second isn't just a benchmark—it enables real-time interaction that was previously impossible.
Multimodal Is the Future: Native multimodal support means better cross-modal reasoning and lower latency.
Price War Is Real: DeepSeek is using low prices to gain market share, forcing competitors to respond.
Open Source Will Follow: When V4.1 Flash weights are released (if they are), it could become the default for many applications.
This article is based on information from DeepSeek's beta announcement on September 8, 2026, and community testing reports. All benchmark figures are from community testing unless otherwise noted. The model is currently in beta and expires on September 10, 2026.