跳到正文
Vercel Blog(vercel.com)· Jerilyn Zheng·· 16 天前品質評分57

DeepSeek V4.1 Flash 1017 Ultrafast 開放於 Vercel AI Gateway 公開預覽

DeepSeek V4.1 Flash 1017 Ultrafast now available on AI Gateway

重點導讀

DeepSeek V4.1 Flash 1017 Ultrafast 現已透過 Fireworks 在 Vercel AI Gateway 開放公開預覽,生成速度可達每秒 1,000 個以上 token。

  • 模型與使用情境:此版本提供 DeepSeek V4.1 Flash 的 10 月 17 日更新,透過 Fireworks 加速的無伺服器端點提供;適用於互動式程式開發、推理與 AI 助理工作流程。
  • 上下文與可用性:上下文視窗為 1M token,可處理大型程式碼庫與長輸入;公開預覽無候補名單,也沒有工作階段時間限制。
  • 接入方式:模型名稱為 deepseek/deepseek-v4.1-flash-1017-ultrafast。在 Claude Code、Codex、Cursor 等工具中,安裝最新版 Vercel CLI 並執行設定後,即可在AI 助理中選取此模型;詳情見 coding agents guide,也可至 model playground 試用。
  • AI Gateway 費用與功能:提供統一 API,可呼叫模型、追蹤用量與成本,並設定重試、故障切換與效能最佳化。服務依供應商定價,不加價,也不對推論收取平臺費用,包含 BYOK 請求。

AI 伴隨問答

自備 Key 深度分析

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:

正文

DeepSeek V4.1 Flash 1017 Ultrafast is now available on AI Gateway through Fireworks. This model can generate upwards of 1,000 tokens per second.

Ultrafast serves the October 17 update of DeepSeek V4.1 Flash through Fireworks' accelerated serverless endpoint. It is suited to interactive coding, reasoning, and agentic workflows where applications need to generate output and move to the next step quickly.

The model has a 1M-token context window for working with large codebases and long inputs. It is available in public preview without a waitroom or session time limit.

Use it by setting deepseek/deepseek-v4.1-flash-1017-ultrafast as the model name:

To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:

Then select deepseek/deepseek-v4.1-flash-1017-ultrafast in the agent. See the coding agents guide for details.

Try DeepSeek V4.1 Flash 1017 Ultrafast 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.

Read more

來源: Vercel Blog (vercel.com)
開啟原文

讀者討論

理性交流 · 即時討論