DeepSeek-V3-0324 API by DeepSeek
deepseek-ai/DeepSeek-V3-0324
DeepSeek-V3-0324
DeepSeek's updated V3 model released on 03/24/2025.
Contoh kode
import os
from openai import OpenAI
client = OpenAI(
api_key=os.getenv("ATLASCLOUD_API_KEY"),
base_url="https://api.atlascloud.ai/v1"
)
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3-0324",
messages=[
{
"role": "user",
"content": "hello"
}
],
max_tokens=1024,
temperature=0.7
)
print(response.choices[0].message.content)Instalasi
Instal paket yang diperlukan untuk bahasa pemrograman Anda.
bash
pip install requestsAutentikasi
Semua permintaan API memerlukan autentikasi melalui API key. Anda bisa mendapatkan API key dari dasbor Atlas Cloud.
bash
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP Headers
python
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Jaga keamanan API key Anda
Jangan pernah mengekspos API key Anda di kode sisi klien atau repositori publik. Gunakan variabel lingkungan atau proxy backend sebagai gantinya.
Kirim permintaan
import requests
url = "https://api.atlascloud.ai/v1/chat/completions"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "your-model",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 1024
}
response = requests.post(url, headers=headers, json=data)
print(response.json())Input Schema
Parameter berikut diterima di isi permintaan.
Total: 9Wajib: 2Opsional: 7
modelstringrequired
The model ID to use for the completion.
messagesarray[object]required
A list of messages comprising the conversation so far.
rolestringrequired
The role of the message author. One of "system", "user", or "assistant".
systemuserassistant
contentstringrequired
The content of the message.
max_tokensinteger
The maximum number of tokens to generate in the completion.
temperaturenumber
Sampling temperature between 0 and 2. Higher values make output more random, lower values more focused and deterministic.
top_pnumber
Nucleus sampling parameter. The model considers the tokens with top_p probability mass.
streamboolean
If set to true, partial message deltas will be sent as server-sent events.
stoparray[string]
Up to 4 sequences where the API will stop generating further tokens.
frequency_penaltynumber
Penalizes new tokens based on their existing frequency in the text so far. Between -2.0 and 2.0.
presence_penaltynumber
Penalizes new tokens based on whether they appear in the text so far. Between -2.0 and 2.0.
Contoh Isi Permintaan
json
{
"model": "deepseek-ai/DeepSeek-V3-0324",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 1024,
"temperature": 0.7,
"stream": false
}Output Schema
API mengembalikan respons yang kompatibel dengan ChatCompletion.
idstringrequired
Unique identifier for the completion.
objectstringrequired
Object type, always "chat.completion".
createdintegerrequired
Unix timestamp of when the completion was created.
modelstringrequired
The model used for the completion.
choicesarray[object]required
List of completion choices.
indexintegerrequired
Index of the choice.
messageobjectrequired
The generated message.
finish_reasonstringrequired
The reason generation stopped.
stoplengthcontent_filter
usageobjectrequired
Token usage statistics.
prompt_tokensintegerrequired
Number of tokens in the prompt.
completion_tokensintegerrequired
Number of tokens in the completion.
total_tokensintegerrequired
Total tokens used.
Contoh Respons
json
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1700000000,
"model": "model-name",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 20,
"total_tokens": 30
}
}Atlas Cloud Skills
Atlas Cloud Skills mengintegrasikan 300+ model AI langsung ke asisten pengkodean AI Anda. Satu perintah untuk menginstal, lalu gunakan bahasa alami untuk menghasilkan gambar, video, dan mengobrol dengan LLM.
Klien yang Didukung
Claude Code
OpenAI Codex
Gemini CLI
Cursor
Windsurf
VS Code
Trae
GitHub Copilot
Cline
Roo Code
Amp
Goose
Replit
40+ klien yang didukung
Instalasi
bash
npx skills add AtlasCloudAI/atlas-cloud-skillsAtur API Key
Dapatkan API key dari dasbor Atlas Cloud dan atur sebagai variabel lingkungan.
bash
export ATLASCLOUD_API_KEY="your-api-key-here"Kemampuan
Setelah diinstal, Anda dapat menggunakan bahasa alami di asisten AI Anda untuk mengakses semua model Atlas Cloud.
Pembuatan GambarBuat gambar dengan model seperti Nano Banana 2, Z-Image, dan lainnya.
Pembuatan VideoBuat video dari teks atau gambar dengan Kling, Vidu, Veo, dll.
Obrolan LLMMengobrol dengan Qwen, DeepSeek, dan model bahasa besar lainnya.
Unggah MediaUnggah file lokal untuk pengeditan gambar dan alur kerja gambar-ke-video.
Pelajari lebih lanjut
MCP Server
Atlas Cloud MCP Server menghubungkan IDE Anda dengan 300+ model AI melalui Model Context Protocol. Berfungsi dengan klien apa pun yang kompatibel dengan MCP.
Klien yang Didukung
Cursor
VS Code
Windsurf
Claude Code
OpenAI Codex
Gemini CLI
Cline
Roo Code
100+ klien yang didukung
Instalasi
bash
npx -y atlascloud-mcpKonfigurasi
Tambahkan konfigurasi berikut ke file pengaturan MCP di IDE Anda.
json
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Alat yang Tersedia
atlas_generate_imageBuat gambar dari prompt teks.
atlas_generate_videoBuat video dari teks atau gambar.
atlas_chatMengobrol dengan model bahasa besar.
atlas_list_modelsJelajahi 300+ model AI yang tersedia.
atlas_quick_generatePembuatan konten satu langkah dengan pemilihan model otomatis.
atlas_upload_mediaUnggah file lokal untuk alur kerja API.
Pelajari lebih lanjut
DeepSeek-V3-0324
Features
DeepSeek-V3-0324 demonstrates notable improvements over its predecessor, DeepSeek-V3, in several key aspects.
Reasoning Capabilities
- Significant improvements in benchmark performance:
- MMLU-Pro: 75.9 → 81.2 (+5.3)
- GPQA: 59.1 → 68.4 (+9.3)
- AIME: 39.6 → 59.4 (+19.8)
- LiveCodeBench: 39.2 → 49.2 (+10.0)
Front-End Web Development
- Improved the executability of the code
- More aesthetically pleasing web pages and game front-ends
Chinese Writing Proficiency
-
Enhanced style and content quality:
- Aligned with the R1 writing style
- Better quality in medium-to-long-form writing
-
Feature Enhancements
- Improved multi-turn interactive rewriting
- Optimized translation quality and letter writing
Chinese Search Capabilities
- Enhanced report analysis requests with more detailed outputs
Function Calling Improvements
- Increased accuracy in Function Calling, fixing issues from previous V3 versions
