DeepSeek-R1-0528 pada SiliconFlow

29 Mei 2025

Daftar Isi

DeepSeek-R1-0528 sekarang tersedia di SiliconFlow:

Peningkatan throughput, pengurangan halusinasi, dan peningkatan penalaran — dibangun untuk tugas AI generatif berkinerja tinggi dan keandalan tinggi.

Dukungan konkurensi tinggi: Hingga 30K RPM / 5M TPM
Output lebih cerdas: 50% lebih sedikit halusinasi, penalaran lebih baik
Generasi lebih kuat: Penulisan kreatif, kode, matematika – semua ditingkatkan
Harga kompetitif: $0.58/M tokens (input), $2.29/M tokens (output)

Mulai Cepat

Coba DeepSeek-R1-0528 di SiliconFlow playground.

Akses Cepat ke API

Contoh Python berikut menunjukkan cara memanggil model DeepSeek-R1-0528 melalui endpoint API SiliconFlow. Untuk spesifikasi API lengkap, lihat dokumentasi pengembang.

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 meningkatkan kecepatan, akurasi, dan skalabilitas untuk aplikasi AI generatif. Jelajahi, bandingkan, dan gabungkan model di SiliconFlow untuk menyesuaikan dengan kasus penggunaan Anda.

Sekarang bangun sesuatu yang menakjubkan di SiliconFlow！

Sebelumnya