LLM API 빠른 시작: 2분 만에 하는 첫 chat completion

curl -s "https://llmwithcrypto.com/api/v1/chat/completions" \
  -H "Authorization: Bearer $LLMWITHCRYPTO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "Answer in two sentences."},
      {"role": "user", "content": "What is a context window?"}
    ],
    "max_tokens": 200
  }'

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://llmwithcrypto.com/api/v1",
    api_key=os.environ["LLMWITHCRYPTO_API_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "Answer in two sentences."},
        {"role": "user", "content": "What is a context window?"},
    ],
    max_tokens=200,
)
print(resp.choices[0].message.content)
print(resp.usage.prompt_tokens, "in,", resp.usage.completion_tokens, "out")

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://llmwithcrypto.com/api/v1',
  apiKey: process.env.LLMWITHCRYPTO_API_KEY,
});

const resp = await client.chat.completions.create({
  model: 'deepseek-v4-pro',
  messages: [
    { role: 'system', content: 'Answer in two sentences.' },
    { role: 'user', content: 'What is a context window?' },
  ],
  max_tokens: 200,
});
console.log(resp.choices[0].message.content);
console.log(resp.usage.prompt_tokens, 'in,', resp.usage.completion_tokens, 'out');

{
  "id": "chatcmpl-8f2c41d0a7b94e1c",
  "object": "chat.completion",
  "created": 1792742400,
  "model": "deepseek-v4-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A context window is the maximum number of tokens a model can read and write in one request. Anything beyond it must be cut or summarized before the call."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 27,
    "completion_tokens": 34,
    "total_tokens": 61
  }
}