DeepSeek-R1-0528 on SiliconFlow

May 29, 2025

DeepSeek-R1-0528 is now live on SiliconFlow:

Enhanced throughput, reduced hallucination, and improved reasoning — built for high-performance, high-reliability generative AI tasks.

High concurrency support: Up to 30K RPM / 5M TPM
Smarter output: 50% fewer hallucinations, better reasoning
Stronger generation: Creative writing, code, math – all upgraded
Competitive price: $0.58/M tokens (input), $2.29/M tokens (output)

Quick Start

Try the DeepSeek-R1-0528 on the SiliconFlow playground.

Quick Access to API

The following Python example demonstrates how to call the DeepSeek-R1-0528 model via SiliconFlow’s API endpoint. For full API specifications, see the developer documentation.

import requests

url = "https://api.siliconflow.com/v1/chat/completions"

payload = {
    "model": "Pro/deepseek-ai/DeepSeek-R1-0528",
    "messages": [
        {
            "role": "user",
            "content": "What opportunities and challenges will the Chinese large model industry face in 2025?"
        }
    ],
    "stream": False,
    "max_tokens": 512,
    "enable_thinking": False,
    "thinking_budget": 4096,
    "min_p": 0.05,
    "stop": None,
    "temperature": 0.7,
    "top_p": 0.7,
    "top_k": 50,
    "frequency_penalty": 0.5,
    "n": 1,
    "response_format": {"type": "text"}
}

headers = {
    "Authorization": "Bearer YOUR_SILICONFLOW_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

import requests

url = "https://api.siliconflow.com/v1/chat/completions"

payload = {
    "model": "Pro/deepseek-ai/DeepSeek-R1-0528",
    "messages": [
        {
            "role": "user",
            "content": "What opportunities and challenges will the Chinese large model industry face in 2025?"
        }
    ],
    "stream": False,
    "max_tokens": 512,
    "enable_thinking": False,
    "thinking_budget": 4096,
    "min_p": 0.05,
    "stop": None,
    "temperature": 0.7,
    "top_p": 0.7,
    "top_k": 50,
    "frequency_penalty": 0.5,
    "n": 1,
    "response_format": {"type": "text"}
}

headers = {
    "Authorization": "Bearer YOUR_SILICONFLOW_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

import requests

url = "https://api.siliconflow.com/v1/chat/completions"

payload = {
    "model": "Pro/deepseek-ai/DeepSeek-R1-0528",
    "messages": [
        {
            "role": "user",
            "content": "What opportunities and challenges will the Chinese large model industry face in 2025?"
        }
    ],
    "stream": False,
    "max_tokens": 512,
    "enable_thinking": False,
    "thinking_budget": 4096,
    "min_p": 0.05,
    "stop": None,
    "temperature": 0.7,
    "top_p": 0.7,
    "top_k": 50,
    "frequency_penalty": 0.5,
    "n": 1,
    "response_format": {"type": "text"}
}

headers = {
    "Authorization": "Bearer YOUR_SILICONFLOW_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

DeepSeek-R1-0528 improves speed, accuracy, and scalability for generative AI applications. Explore, compare, and combine models on SiliconFlow to fit your use cases.

Now go build something amazing on SiliconFlow！