google/gemini-3.1-pro-preview
Google's GA flagship model. Ranks #1 on 12 of 18 tracked benchmarks. 2x+ reasoning improvement over Gemini 3 Pro. 1M-token context with strong coding, math, and multimodal input. Best for complex reasoning, advanced coding pipelines, and research-grade tasks.
來源：gemini_x0.5 · 核驗於 2026-06-05
快取讀取 $0.1/M · 快取寫入 —/M
| 檔位 | 輸入 | 快取讀取 | 快取寫入 | 輸出 |
|---|---|---|---|---|
| Standard ≤200K | $1 | $0.1 | — | $6 |
| Standard >200K | $2 | $0.2 | — | $9 |
API 呼叫時用任一 ID 都可以。
google/gemini-3.1-pro-preview把 ONEHOP_KEY 佔位符替換為你的 API Key。 建立 →
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-pro-preview",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)最近 30 天 92 次請求