google/gemini-3.1-flash-lite
Google's cheapest GA model in the 3.x series. Matches Gemini 2.5 Flash quality at a fraction of the cost. Optimized for low-latency, high-volume workloads: classification, summarization, simple generation, and RAG at scale.
์ถ์ฒ: gemini_x0.5 ยท 2026-06-05 ํ์ธ
์บ์ ์ฝ๊ธฐ $0.0125/M ยท ์บ์ ์ฐ๊ธฐ โ/M
API ํธ์ถ ์ ์ด๋ค ID๋ ์ฌ์ฉํ ์ ์์ต๋๋ค.
google/gemini-3.1-flash-liteONEHOP_KEY ์๋ฆฌ ํ์์๋ฅผ ๊ทํ์ API key๋ก ๊ต์ฒดํ์ธ์. ์์ฑํ๊ธฐ โ
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="google/gemini-3.1-flash-lite",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)์ต๊ทผ 30์ผ๊ฐ ์์ฒญ 456๊ฑด