The advanced LLM
Codebeispiel
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-r1-0528",
messages=[
{
"role": "user",
"content": "hello"
}
],
max_tokens=1024,
temperature=0.7
)
print(response.choices[0].message.content)Installieren
Installieren Sie das erforderliche Paket für Ihre Programmiersprache.
pip install requestsAuthentifizierung
Alle API-Anfragen erfordern eine Authentifizierung über einen API-Schlüssel. Sie können Ihren API-Schlüssel über das Atlas Cloud Dashboard erhalten.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP-Header
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Geben Sie Ihren API-Schlüssel niemals in clientseitigem Code oder öffentlichen Repositories preis. Verwenden Sie stattdessen Umgebungsvariablen oder einen Backend-Proxy.
Anfrage senden
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())Eingabe-Schema
Die folgenden Parameter werden im Anfragekörper akzeptiert.
Beispiel-Anfragekörper
{
"model": "deepseek-ai/deepseek-r1-0528",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 1024,
"temperature": 0.7,
"stream": false
}Ausgabe-Schema
Die API gibt eine ChatCompletion-kompatible Antwort zurück.
Beispielantwort
{
"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 integriert über 300 KI-Modelle direkt in Ihren KI-Coding-Assistenten. Ein Befehl zur Installation, dann verwenden Sie natürliche Sprache, um Bilder, Videos zu generieren und mit LLMs zu chatten.
Unterstützte Clients
Installieren
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI-Schlüssel einrichten
Erhalten Sie Ihren API-Schlüssel über das Atlas Cloud Dashboard und setzen Sie ihn als Umgebungsvariable.
export ATLASCLOUD_API_KEY="your-api-key-here"Funktionen
Nach der Installation können Sie natürliche Sprache in Ihrem KI-Assistenten verwenden, um auf alle Atlas Cloud Modelle zuzugreifen.
MCP-Server
Der Atlas Cloud MCP-Server verbindet Ihre IDE mit über 300 KI-Modellen über das Model Context Protocol. Funktioniert mit jedem MCP-kompatiblen Client.
Unterstützte Clients
Installieren
npx -y atlascloud-mcpKonfiguration
Fügen Sie die folgende Konfiguration zur MCP-Einstellungsdatei Ihrer IDE hinzu.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Verfügbare Werkzeuge
DeepSeek-R1-0528
1. Introduction
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro.
Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.
Beyond its improved reasoning capabilities, this version also offers a reduced hallucination rate, enhanced support for function calling, and better experience for vibe coding.
2. Evaluation Results
DeepSeek-R1-0528
For all our models, the maximum generation length is set to 64K tokens. For benchmarks requiring sampling, we use a temperature of , a top-p value of , and generate 16 responses per query to estimate pass@1.
| Category | Benchmark (Metric) | DeepSeek R1 | DeepSeek R1 0528 |
|---|---|---|---|
| General | |||
| MMLU-Redux (EM) | 92.9 | 93.4 | |
| MMLU-Pro (EM) | 84.0 | 85.0 | |
| GPQA-Diamond (Pass@1) | 71.5 | 81.0 | |
| SimpleQA (Correct) | 30.1 | 27.8 | |
| FRAMES (Acc.) | 82.5 | 83.0 | |
| Humanity's Last Exam (Pass@1) | 8.5 | 17.7 | |
| Code | |||
| LiveCodeBench (2408-2505) (Pass@1) | 63.5 | 73.3 | |
| Codeforces-Div1 (Rating) | 1530 | 1930 | |
| SWE Verified (Resolved) | 49.2 | 57.6 | |
| Aider-Polyglot (Acc.) | 53.3 | 71.6 | |
| Math | |||
| AIME 2024 (Pass@1) | 79.8 | 91.4 | |
| AIME 2025 (Pass@1) | 70.0 | 87.5 | |
| HMMT 2025 (Pass@1) | 41.7 | 79.4 | |
| CNMO 2024 (Pass@1) | 78.8 | 86.9 | |
| Tools | |||
| BFCL_v3_MultiTurn (Acc) | - | 37.0 | |
| Tau-Bench (Pass@1) | - | 53.5(Airline)/63.9(Retail) |
Note: We use Agentless framework to evaluate model performance on SWE-Verified. We only evaluate text-only prompts in HLE testsets. GPT-4.1 is employed to act user role in Tau-bench evaluation.
