google/gemini-3-flash-preview
Preview of Google's Gemini 3 Flash. Near-flagship reasoning and coding at Flash latency and price, with 1M-token context and text, image, audio, and video input. Access it early through OneHop before GA. Best for high-volume agentic workflows and long-document tasks on a budget.
åºå ž: gemini_x0.5 · 確èªæ¥ 2026-07-21
ãã£ãã·ã¥èªã¿åã $0.025/M · ãã£ãã·ã¥æžã蟌㿠â/M
ã©ã¡ãã® ID ã䜿ã£ãŠã API ã§ãã®ã¢ãã«ãåŒã³åºããŸãã
google/gemini-3-flash-previewYou can use these names directly in the request model field.
ONEHOP_KEY ãã¬ãŒã¹ãã«ããŒããèªèº«ã® API Key ã«çœ®ãæããŠãã ããã äœæãã â
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-flash-preview",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)éå» 30 æ¥é㧠2 件ã®ãªã¯ãšã¹ã