Gemini 4 Carbon 登上 Vercel AI Gateway,至 11 月 30 日享 5 折
Gemini 4 Carbon now available on AI Gateway
Google 的 Gemini 4 Carbon 已在 Vercel AI Gateway 開放使用,至 11 月 30 日提供 5 折優惠。
- 用途與能力:Gemini 4 Carbon 面向複雜軟體工程、長時間 AI 助理工作與資安防禦,支援尋找漏洞、驗證風險及開發修補程式;Google 表示,它在多階段工程任務、編碼、全端網頁開發與科學推理方面有所改善,也更可靠地執行多步驟計畫、減少缺乏依據的主張,並能在需求模糊時改善協作。
- 上下文與使用方式:模型提供 1M token 上下文視窗,可處理大型程式碼庫與長輸入;模型名稱為
google/gemini-4-carbon,可在 Claude Code、Codex、Cursor 等工具中,安裝最新版 Vercel CLI 並完成設定後選用。 - AI Gateway:提供統一 API,可呼叫模型、追蹤用量與成本,以及設定重試、故障轉移與效能最佳化;另支援自訂報表、Zero Data Retention、API 金鑰預算、路由規則與 BYOK。Vercel 表示,AI Gateway 按供應商價格計費,不加價,也不對推論收取平臺費。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Gemini 4 Carbon from Google is now available on AI Gateway. It is available at 50% off through November 30, 2026:
Gemini 4 Carbon is built for complex software engineering, sustained agentic work, and cybersecurity defense. It has a 1M-token context window for working with large codebases and long inputs.
On engineering tasks, Carbon carries demanding work through multiple stages, with improvements in coding, full-stack web development, and scientific reasoning. Its cybersecurity capabilities span finding vulnerabilities, validating their risk, and developing patches. Google also reports more reliable execution of multi-step plans, fewer unsupported claims, and better collaboration when requirements are ambiguous, helping agents follow through while respecting project constraints.
Use google/gemini-4-carbon as the model name:
To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:
Then select google/gemini-4-carbon in the agent. See the coding agents guide for details.
Try Gemini 4 Carbon in the model playground.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
You can view all language models available on AI Gateway.