DeepSeek-V3-0324 API by DeepSeek
deepseek-ai/DeepSeek-V3-0324
DeepSeek-V3-0324
DeepSeek's updated V3 model released on 03/24/2025.
Kodexempel
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)Installera
Installera det nödvändiga paketet för ditt programmeringsspråk.
bash
pip install requestsAutentisering
Alla API-förfrågningar kräver autentisering via en API key. Du kan hämta din API key från Atlas Cloud-instrumentpanelen.
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}"
}Håll din API key säker
Exponera aldrig din API key i klientkod eller publika arkiv. Använd miljövariabler eller en backend-proxy istället.
Skicka en förfrågan
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
Följande parametrar accepteras i förfrågningsinnehållet.
Totalt: 9Obligatorisk: 2Valfri: 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.
Exempel på förfrågningsinnehåll
json
{
"model": "deepseek-ai/DeepSeek-V3-0324",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 1024,
"temperature": 0.7,
"stream": false
}Output Schema
API:et returnerar ett ChatCompletion-kompatibelt svar.
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.
Exempelsvar
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 integrerar 300+ AI-modeller direkt i din AI-kodassistent. Ett kommando för att installera, sedan använd naturligt språk för att generera bilder, videor och chatta med LLM.
Stödda klienter
Claude Code
OpenAI Codex
Gemini CLI
Cursor
Windsurf
VS Code
Trae
GitHub Copilot
Cline
Roo Code
Amp
Goose
Replit
40+ stödda klienter
Installera
bash
npx skills add AtlasCloudAI/atlas-cloud-skillsKonfigurera API Key
Hämta din API key från Atlas Cloud-instrumentpanelen och ställ in den som en miljövariabel.
bash
export ATLASCLOUD_API_KEY="your-api-key-here"Funktioner
När det är installerat kan du använda naturligt språk i din AI-assistent för att komma åt alla Atlas Cloud-modeller.
BildgenereringGenerera bilder med modeller som Nano Banana 2, Z-Image och fler.
VideoskapandeSkapa videor från text eller bilder med Kling, Vidu, Veo m.fl.
LLM-chattChatta med Qwen, DeepSeek och andra stora språkmodeller.
MediauppladdningLadda upp lokala filer för bildredigering och bild-till-video-arbetsflöden.
MCP Server
Atlas Cloud MCP Server ansluter din IDE med 300+ AI-modeller via Model Context Protocol. Fungerar med alla MCP-kompatibla klienter.
Stödda klienter
Cursor
VS Code
Windsurf
Claude Code
OpenAI Codex
Gemini CLI
Cline
Roo Code
100+ stödda klienter
Installera
bash
npx -y atlascloud-mcpKonfiguration
Lägg till följande konfiguration i din IDE:s MCP-inställningsfil.
json
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Tillgängliga verktyg
atlas_generate_imageGenerera bilder från textpromptar.
atlas_generate_videoSkapa videor från text eller bilder.
atlas_chatChatta med stora språkmodeller.
atlas_list_modelsBläddra bland 300+ tillgängliga AI-modeller.
atlas_quick_generateInnehållsskapande i ett steg med automatiskt modellval.
atlas_upload_mediaLadda upp lokala filer för API-arbetsflöden.
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
