Large Language Models

Model Capabilities

Large Language Models (LLMs) are types of AI model built using deep learning and natural language processing techniques. After being trained on massive amounts of text data, they can understand, generate, and process human language. LLMs have the following main capabilities:

Text GenerationLLMs can generate logically coherent content based on context and adjust output style as needed.
Language UnderstandingLLMs can accurately understand the meaning of input text and support context-aware conversation.
Text TranslationLLMs are capable of cross-lingual understanding and generation, enabling translation between different languages.
Knowledge-based Q&AWith extensive knowledge basis, LLMs can answer questions across domains such as culture, science, and history.
Code Understanding & GenerationLLMs can understand and generate code (Python, Java, C++ and so on), detect code errors, and offer suggestions.
Text Classification & SummarizationLLMs can understand complex sentences, categorize and extract information, and summarize key points.

Model Selection

On the LLM Service Page, you can browse the list of supported models, learn model basics and pricing. Click on a specific model, and you can open its detail page for an online demo. After trying different models with your task, you can compare and choose the most suitable one.

API Integration

AtlasCloud provides fast, reliable APIs for open-source models, combining the ease and reliability of top-tier LLM APIs with the flexibility and cost-efficiency of open source LLMs.

ChatCompletion: Supports both streaming and non-streaming modes.

If you’re already using OpenAI’s ChatCompletion API, simply set your base URL to: api.atlascloud.ai, get and set your API key, update the model name as needed to start using LLM services.

For how to get API key, refer to the API Key Management.

API Examples

Python

import requests

url = "https://api.atlascloud.ai/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "deepseek-ai/DeepSeek-V3.1",
    "messages": [
        {
            "role": "user",
            "content": "what is difference between http and https"
        }
    ],
    "max_tokens": 32767,
    "temperature": 1,
    "top_p": 0.9,
    "top_k": 50,
    "repetition_penalty": 1.1,
    "stream": True,
    "systemPrompt": "",
    "thinking": {
        "type": "enabled"
    }
}
  
response = requests.post(url, headers=headers, json=data)
print(response.json())

cURL

curl -X POST "https://api.atlascloud.ai/v1/chat/completions" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-ai/DeepSeek-V3.1",
  "messages": [
    {
      "role": "user",
      "content": "what is difference between http and https"
    }
  ],
  "max_tokens": 32767,
  "temperature": 1,
  "top_p": 0.9,
  "top_k": 50,
  "repetition_penalty": 1.1,
  "stream": true,
  "systemPrompt": "",
  "thinking": {
    "type": "enabled"
  }
}'

TypeScript

const url = 'https://api.atlascloud.ai/v1/chat/completions';

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: 'Bearer $ATLASCLOUD_API_KEY',
  },
  body: JSON.stringify(    {
        "model": "deepseek-ai/DeepSeek-V3.1",
        "messages": [
            {
                "role": "user",
                "content": "what is difference between http and https"
            }
        ],
        "max_tokens": 32767,
        "temperature": 1,
        "top_p": 0.9,
        "top_k": 50,
        "repetition_penalty": 1.1,
        "stream": true,
        "systemPrompt": "",
        "thinking": {
            "type": "enabled"
        }
    }),
});

const json = await response.json();

const output = json.choices[0].message.content;
console.log(output);