模型定價文件指南應用場景對比關於
登入開始使用
返回模型市場
Google·Textnew比官方便宜 30%+

Gemini 3.6 FlashAPI

Google's newest Flash — thinking-by-default at Flash latency, 1M context, native audio input.

輸入價格

$1.05

per 1M tokens

輸出價格

$5.25

per 1M tokens

Prompt 快取

給穩定 prefix 加 cache_control，命中按 input 價的一小部分計費。cache_write 按 input 原價計費。

Cache read
$0.21

按 input × 0.2 自動派生

引數

模型 ID
gemini-3-6-flash
端點
POST /v1/chat/completions
類別
Text
供應商
Google
能力
visionfunctionstreamingthinkinglong-context

無縫相容 OpenAI SDK

把 OpenAI SDK 的 base_url 指向 api.kunavo.com/v1，換 model id 即可。流式、工具呼叫、SDK 行為完全一致。

檢視文件Gemini API pricing guide

立即試用

在 /app/keys 建立 API key，複製為 KUNAVO_API_KEY，然後任選下面一段程式碼執行。

curl
curl https://api.kunavo.com/v1/chat/completions \
  -H "Authorization: Bearer $KUNAVO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-6-flash",
    "messages": [
      {"role": "user", "content": "Hello, Gemini 3.6 Flash"}
    ],
    "stream": false
  }'

Kunavo 與直連 Google 的差異

同一個 Gemini 3.6 Flash，同樣的輸出。閘道改變的是帳號、SDK 與帳單——以下是如實對照。

Kunavo直連 Google
價格（per 1M tokens）$1.05 / $5.25 (−30%)$1.50 / $7.50
帳號一個 Kunavo 帳號，2 分鐘取得 Key，最低儲值 $5需要 Google 帳號，並另外設定其計費
SDK繼續用 OpenAI SDK——改 base_url，model 填 "gemini-3-6-flash"Google 官方 SDK，或其提供的 OpenAI 相容層
同一把 Key 還能呼叫Claude、Gemini、GPT 以及影像、影片、音訊模型僅 Google 自家模型
計費一個 Stripe 餘額，用多少付多少，餘額不過期；失敗請求不計費每家廠商一張獨立帳單
速率限制共享閘道容量，無帳號層級的合約限額Google 自家級距限額，可依用量或合約調升

若你需要合約級速率限制、企業 SLA，或首日就要用到廠商獨有功能，直連 Google 較合適。若你想要一把 Key、一張帳單，並在所有廠商上取得更低單價，就用 Kunavo。

FAQ

How much does Gemini 3.6 Flash cost?

On Kunavo, Gemini 3.6 Flash is $1.05 per 1M input tokens and $5.25 per 1M output tokens — about 30% under Google's official price. Failed requests are never billed, and it's pay-as-you-go — you only pay for successful calls.

Can I call Gemini 3.6 Flash with the OpenAI SDK?

Yes. Set base_url to https://api.kunavo.com/v1, pass your Kunavo key, and set model to "gemini-3-6-flash". Requests and responses are OpenAI-compatible.

What endpoint does Gemini 3.6 Flash use?

Gemini 3.6 Flash is called via POST /v1/chat/completions on Kunavo's OpenAI-compatible API.

What is Gemini 3.6 Flash good for?

Gemini 3.6 Flash is a text model from Google, with support for vision, function, streaming, thinking, long-context.

What is different from calling Google directly?

The model is the same, at about 30% under Google's list price. What changes is around it: one key and one Stripe balance instead of a Google account with its own billing, the OpenAI SDK with base_url swapped instead of a provider-specific SDK, and the same key also reaching Claude, Gemini, GPT, image, video and audio models. The tradeoff is that gateway capacity is shared — if you need a contractual rate limit or an enterprise SLA on Gemini 3.6 Flash specifically, go direct to Google.

Is Gemini 3.6 Flash cheaper on Kunavo?

Yes — Gemini 3.6 Flash is about 30% under Google's official list price on Kunavo, with no subscription and no minimum monthly spend. You pay per token from a $5 top-up, failed requests are never billed, and the balance never expires.

Related models