DeepSeek-V3-0324 Sekarang Tayang di SiliconFlow

27 Mar 2025

Daftar Isi

DeepSeek-V3-0324 (671B) sekarang tersedia di SiliconFlow — memberikan peningkatan besar dalam pemikiran, penulisan, dan kinerja matematika.

Pembelajaran penguatan meningkatkan kinerja pada tugas-tugas pemikiran yang kompleks
Jendela konteks 8K token
Harga bersaing: $0,29/M tokens (input), $1,15/M tokens (output)

DeepSeek-V3-0324 mempertahankan ukuran model, harga, dan kompatibilitas API yang sama — tetapi membawa peningkatan besar dalam pemikiran, penulisan, dan matematika. Dengan dukungan untuk Function Calling, JSON Mode, Prefix, FIM, ini adalah versi kecil yang memberikan peningkatan besar.

Mulai Cepat

Coba DeepSeek-V3-0324 di Playground SiliconFlow.

Akses Cepat ke API

Contoh Python berikut ini menunjukkan cara memanggil model DeepSeek-V3-0324 melalui endpoint API SiliconFlow. Spesifikasi API yang lebih rinci untuk pengembang.

from openai import OpenAI

url = 'https://api.siliconflow.com/v1/'
api_key = 'your api_key'

client = OpenAI(
    base_url=url,
    api_key=api_key
)

# Send a request with streaming output
content = ""
reasoning_content = ""
messages = [
    {"role": "user", "content": "Prove the Pythagorean theorem and provide a simple example."}
]
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    stream=True,  # Enable streaming output
    max_tokens=4096,
    extra_body={
        "thinking_budget": 1024
    }
)
# Gradually receive and process the response
for chunk in response:
    if chunk.choices[0].delta.content:
        content += chunk.choices[0].delta.content
    if chunk.choices[0].delta.reasoning_content:
        reasoning_content += chunk.choices[0].delta.reasoning_content

# Round 2
messages.append({"role": "assistant", "content": content})
messages.append({'role': 'user', 'content': "Continue"})
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    stream=True
)

from openai import OpenAI

url = 'https://api.siliconflow.com/v1/'
api_key = 'your api_key'

client = OpenAI(
    base_url=url,
    api_key=api_key
)

# Send a request with streaming output
content = ""
reasoning_content = ""
messages = [
    {"role": "user", "content": "Prove the Pythagorean theorem and provide a simple example."}
]
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    stream=True,  # Enable streaming output
    max_tokens=4096,
    extra_body={
        "thinking_budget": 1024
    }
)
# Gradually receive and process the response
for chunk in response:
    if chunk.choices[0].delta.content:
        content += chunk.choices[0].delta.content
    if chunk.choices[0].delta.reasoning_content:
        reasoning_content += chunk.choices[0].delta.reasoning_content

# Round 2
messages.append({"role": "assistant", "content": content})
messages.append({'role': 'user', 'content': "Continue"})
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    stream=True
)

from openai import OpenAI

url = 'https://api.siliconflow.com/v1/'
api_key = 'your api_key'

client = OpenAI(
    base_url=url,
    api_key=api_key
)

# Send a request with streaming output
content = ""
reasoning_content = ""
messages = [
    {"role": "user", "content": "Prove the Pythagorean theorem and provide a simple example."}
]
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    stream=True,  # Enable streaming output
    max_tokens=4096,
    extra_body={
        "thinking_budget": 1024
    }
)
# Gradually receive and process the response
for chunk in response:
    if chunk.choices[0].delta.content:
        content += chunk.choices[0].delta.content
    if chunk.choices[0].delta.reasoning_content:
        reasoning_content += chunk.choices[0].delta.reasoning_content

# Round 2
messages.append({"role": "assistant", "content": content})
messages.append({'role': 'user', 'content': "Continue"})
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=messages,
    stream=True
)

Dioptimalkan untuk pemikiran yang menuntut dan penggunaan di dunia nyata, DeepSeek-V3-0324 siap membantu Anda membangun alat yang lebih pintar, agen yang lebih baik, dan asisten jangka panjang.

Coba DeepSeek-V3 di SiliconFlow sekarang dan lihat apa yang bisa Anda buat.

Sebelumnya