Novita AI

Novita AI

API 키 (API Keys)

API 키는 여기서 받을 수 있어요.

import os
os.environ["NOVITA_API_KEY"] = "your-api-key"

지원 OpenAI 파라미터 (Supported OpenAI Params)

• max_tokens
• stream
• stream_options
• n
• seed
• frequency_penalty
• presence_penalty
• repetition_penalty
• stop
• temperature
• top_p
• top_k
• min_p
• logit_bias
• logprobs
• top_logprobs
• tools
• response_format
• separate_reasoning

샘플 사용법 (Sample Usage)

• SDK
• PROXY

import os
from litellm import completion
os.environ["NOVITA_API_KEY"] = ""

response = completion(
    model="novita/deepseek/deepseek-r1-turbo",
    messages=[{"role": "user", "content": "List 5 popular cookie recipes."}]
)

content = response.get('choices', [{}])[0].get('message', {}).get('content')
print(content)

• config.yaml에 모델 추가

model_list:
  - model_name: deepseek-r1-turbo
    litellm_params:
      model: novita/deepseek/deepseek-r1-turbo
      api_key: os.environ/NOVITA_API_KEY

• 프록시 시작

$ litellm --config /path/to/config.yaml

• 요청 보내기!

curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer ***' \
-d '{
  "model": "deepseek-r1-turbo",
  "messages": [
      {"role": "user", "content": "List 5 popular cookie recipes."}
  ]
}
'

도구 호출 (Tool Calling)

from litellm import completion
import os
# set env
os.environ["NOVITA_API_KEY"] = ""

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA",
                    },
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                },
                "required": ["location"],
            },
        },
    }
]
messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]

response = completion(
    model="novita/deepseek/deepseek-r1-turbo",
    messages=messages,
    tools=tools,
)
# Add any assertions, here to check response args
print(response)
assert isinstance(response.choices[0].message.tool_calls[0].function.name, str)
assert isinstance(
    response.choices[0].message.tool_calls[0].function.arguments, str
)

JSON 모드 (JSON Mode)

• SDK
• PROXY

from litellm import completion
import json
import os

os.environ['NOVITA_API_KEY'] = ""

messages = [
    {
        "role": "user",
        "content": "List 5 popular cookie recipes."
    }
]

response = completion(
    model="novita/deepseek/deepseek-r1-turbo",
    messages=messages,
    response_format={"type": "json_object"} # 👈 KEY CHANGE
)

print(json.loads(response.choices[0].message.content))

• config.yaml에 모델 추가

model_list:
  - model_name: deepseek-r1-turbo
    litellm_params:
      model: novita/deepseek/deepseek-r1-turbo
      api_key: os.environ/NOVITA_API_KEY

• 프록시 시작

$ litellm --config /path/to/config.yaml

• 요청 보내기!

curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer ***" \
-d '{
  "model": "deepseek-r1-turbo",
  "messages": [
      {"role": "user", "content": "List 5 popular cookie recipes."}
  ],
  "response_format": {"type": "json_object"}
}
'

채팅 모델 (Chat Models)

🚨 LiteLLM은 모든 Novita AI 모델을 지원해요. model=novita/<your-novita-model>로 보내면 Novita AI로 전송돼요. 모든 Novita AI 모델은 여기서 확인하세요.

출처: 문서

본문

더 알아보기 (Learn more)

• Novita AI Docs
• Novita AI 모델 목록
• LiteLLM 공식 문서