LLM / Chat

Overview

Atlas Cloud provides access to industry-leading large language models through an OpenAI-compatible API. If you're already using the OpenAI SDK, just change the base URL and API key — no other code changes needed.

Key Capabilities

Text Generation: Generate coherent, context-aware content for any use case
Conversational AI: Build chatbots and assistants with multi-turn conversation support
Code Generation: Generate, review, and debug code in any programming language
Reasoning: Complex logical reasoning, math, and problem-solving
Translation: Cross-lingual understanding and generation across dozens of languages
Summarization: Extract key information and generate concise summaries

Featured Models

Model	Provider	Highlights
DeepSeek V3	DeepSeek	High-performance reasoning and coding, cost-effective
Qwen	Alibaba	Powerful multilingual model series
Kimi	MoonshotAI	Strong long-context understanding
GLM	Zhipu AI	Bilingual Chinese-English model
MiniMax	MiniMax	Optimized for multimedia applications
Doubao	ByteDance	Versatile general-purpose model

For a complete list of all LLM models and their specifications, visit the Model Library.

API Integration

Base URL

https://api.atlascloud.ai/v1

The LLM API supports both streaming and non-streaming modes, fully compatible with the OpenAI ChatCompletion format.

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.atlascloud.ai/v1"
)

# Non-streaming
response = client.chat.completions.create(
    model="deepseek-v3",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.7,
    max_tokens=1024
)
print(response.choices[0].message.content)

Python (Streaming)

stream = client.chat.completions.create(
    model="deepseek-v3",
    messages=[
        {"role": "user", "content": "Write a short story about a robot learning to paint."}
    ],
    stream=True
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Node.js / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-api-key",
  baseURL: "https://api.atlascloud.ai/v1",
});

// Non-streaming
const response = await client.chat.completions.create({
  model: "deepseek-v3",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain quantum computing in simple terms." },
  ],
});
console.log(response.choices[0].message.content);

// Streaming
const stream = await client.chat.completions.create({
  model: "deepseek-v3",
  messages: [{ role: "user", content: "Tell me a joke." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

cURL

curl https://api.atlascloud.ai/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Common Parameters

Parameter	Type	Description
`model`	string	Model identifier (e.g., `deepseek-v3`, `qwen-turbo`)
`messages`	array	Conversation messages with `role` and `content`
`temperature`	number	Controls randomness (0.0 - 2.0, default varies by model)
`max_tokens`	number	Maximum tokens in the response
`stream`	boolean	Enable streaming output
`top_p`	number	Nucleus sampling parameter

Using with Third-Party Tools

Since the API is OpenAI-compatible, it works with any tool that supports custom OpenAI endpoints:

Tool	Configuration
Chatbox	Set API Host to `https://api.atlascloud.ai/v1`
Cherry Studio	Add custom OpenAI provider
OpenWebUI	Configure OpenAI-compatible endpoint
LangChain	Use `ChatOpenAI` with custom `base_url`
LlamaIndex	Use OpenAI-compatible LLM class

Important: Always include the /v1 suffix in the base URL.

Model Selection Tips

Cost-effectiveness: DeepSeek V3 offers excellent performance at competitive pricing
Multilingual: Qwen excels at multilingual tasks, especially Chinese-English
Code: DeepSeek is a strong choice for code generation and review
Long context: Kimi excels at long-context tasks. Check each model's max context on the Model Library
Reasoning: Choose models with dedicated reasoning capabilities for complex tasks

For pricing details, see the API Pricing page. For the full API specification, see the API Reference.

On this page