Gemini 3.5 Fast API
低延遲 Gemini，適合程式碼 Agent 與聊天應用。
透過 OpenAI 相容端點呼叫 gemini-3.5-fast。Coding Plan 價格為每百萬 token 輸入 $0.90 / 輸出 $5.40，比 Google 官方價一律低 40%，只需一組 Hypereal API Key 即可使用。
Gemini 3.5 Fast pricing
Coding Plan price vs Google official token pricing
幾分鐘即可整合
標準 REST API，支援任何程式語言。一個 API 金鑰即可訪問所有模型。
- 所有模型統一端點
- Bearer token 身份驗證
- JSON 請求與響應
- 非同步任務 Webhook 回撥
- 提供 Python 和 Node.js SDK
curl https://api.hypereal.cloud/v1/chat/completions \
-H "Authorization: Bearer hyp-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-fast",
"messages": [
{"role": "user", "content": "Generate unit tests for this parser."}
]
}'為什麼選擇 Gemini 3.5 Fast
Coding Plan eligible
Spend Coding Plan credits on Gemini 3.5 Fast alongside Claude Opus, Sonnet, and GPT-5.5 — one prepaid pool, one API key.
Built for latency and volume
Sub-second first token — best for quick code review, chat, test generation, and iterative agent loops.
40% off official pricing
$0.90 input / $5.40 output per million tokens vs Google official $1.50 / $9.00. A flat 40% off, no tiers.
消耗的是哪種點數？
一個 API 金鑰兩種點數都能用。路由由你呼叫的模型決定，而非金鑰。
Claude Opus 4.7、Sonnet 4.6、GPT-5.5、Gemini 3.5 Thinking、Gemini 3.5 Fast 會先扣 Coding Credits（依到期日 FIFO），餘額不足時才會回落到 General Credits。
圖像、影片、音訊、3D 以及其他所有 LLM 只會扣 General Credits。Coding Credits 會保留給程式開發工作負載。
常見問題
Is Gemini 3.5 Fast included in the Coding Plan?
Yes. It is eligible for Coding Plan credits, so prepaid coding credits spend on it just like Claude Opus, Sonnet, and GPT-5.5.
What is the model ID?
Use gemini-3.5-fast in chat, /v1/chat/completions, and any OpenAI-compatible SDK call.
When should I use Fast instead of Thinking?
Use Fast for latency-sensitive coding loops, tests, and chat. Use Thinking for deeper review or multi-step reasoning. Both cost the same per token.
用 Coding Credits 呼叫 Gemini 3.5 Fast。
建立 API Key，將 base_url 指向 Hypereal，即可在 OpenAI 相容工具中呼叫 gemini-3.5-fast。