我们使用必要 Cookie 来保障开桥正常运行。经你同意，可选 Cookie 将帮我们记住你的偏好，并了解你如何使用我们的服务。你可以接受或拒绝可选 Cookie，也可以随时管理你的选择。详情请参阅我们的 隐私政策。
deepseek-r1-0528 vs deepseek-v4-pro
Compare deepseek-r1-0528 from deepseek and deepseek-v4-pro from deepseek side by side — pricing, context window, features, and provider availability.
deepseek-r1-0528
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.
deepseek-v4-pro
In addition to DeepSeek, TencentCloud and AlibabaCloud now also offer the official 0731 version, while other providers are still using the old 0424 version. . DeepSeek V4 Pro is DeepSeek’s flagship open-weight Mixture-of-Experts model, released in preview on April 24, 2026. It features 1.6 trillion total parameters, with 49 billion activated per token, and supports a one-million-token context window. Designed for advanced reasoning, coding, STEM tasks, and autonomous agents, it delivers state-of-the-art performance among open models and rivals leading proprietary systems. The model supports both thinking and non-thinking modes and is available through DeepSeek’s applications and APIs.
Model Overview
deepseek-r1-0528deepseek-v4-proAccess All Top AI Models via 开桥
Why limit yourself to one model? 开桥 gives you access to all leading AI models through a single, unified API. Compare, test, and switch between models effortlessly.
How to use deepseek-r1-0528 or deepseek-v4-pro
Simply change the model name to deepseek-r1-0528 or deepseek-v4-pro to adjust the model. 开桥 normalizes requests and responses across providers for you.
from openai import OpenAI
client = OpenAI(
base_url="https://openqiao.com/api/v1",
api_key="<OPENQIAO_API_KEY>",
)
# Chat Completion
completion = client.chat.completions.create(
model="deepseek-r1-0528",
messages=[
{
"role": "user",
"content": "What is the meaning of life?"
}
]
)
print(completion.choices[0].message.content)
