HTML 77.2%
TypeScript 10.5%
Python 9.6%
JavaScript 2.5%
1<!doctype html>2<html lang="en" dir="ltr" class="docs-wrapper plugin-docs plugin-id-default docs-version-current docs-doc-page docs-doc-id-news/news260910" data-has-hydrated="false">3<head>4<meta charset="UTF-8">5<meta name="generator" content="Docusaurus v3.1.0">6<title data-rh="true">DeepSeek-V4.1-Flash: Smarter, Faster, More Efficient | DeepSeek API Docs</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:image" content="https://api-docs.deepseek.com/img/deepseek-social-card.jpeg"><meta data-rh="true" name="twitter:image" content="https://api-docs.deepseek.com/img/deepseek-social-card.jpeg"><meta data-rh="true" property="og:url" content="https://api-docs.deepseek.com/news/news260910"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" property="og:locale:alternate" content="zh_cn"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="DeepSeek-V4.1-Flash: Smarter, Faster, More Efficient | DeepSeek API Docs"><meta data-rh="true" name="description" content="🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient."><meta data-rh="true" property="og:description" content="🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient."><link data-rh="true" rel="icon" href="/img/favicon.svg"><link data-rh="true" rel="canonical" href="https://api-docs.deepseek.com/news/news260910"><link data-rh="true" rel="alternate" href="https://api-docs.deepseek.com/news/news260910" hreflang="en"><link data-rh="true" rel="alternate" href="https://api-docs.deepseek.com/zh-cn/news/news260910" hreflang="zh-cn"><link data-rh="true" rel="alternate" href="https://api-docs.deepseek.com/news/news260910" hreflang="x-default"><link rel="stylesheet" href="/assets/css/styles.93f66918.css">7<script src="/assets/js/runtime~main.84a181da.js" defer="defer"></script>8<script src="/assets/js/main.f3d559bd.js" defer="defer"></script>9</head>10<body class="navigation-with-keyboard">11<script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=function(){try{return new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}}()||function(){try{return localStorage.getItem("theme")}catch(t){}}();t(null!==e?e:"light")}(),function(){try{const c=new URLSearchParams(window.location.search).entries();for(var[t,e]of c)if(t.startsWith("docusaurus-data-")){var a=t.replace("docusaurus-data-","data-");document.documentElement.setAttribute(a,e)}}catch(t){}}()</script><div id="__docusaurus"><div role="region" aria-label="Skip to main content"><a class="skipToContent_xSgN" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><nav aria-label="Main" class="navbar navbar--fixed-top"><div class="navbar__inner"><div class="navbar__items"><button aria-label="Toggle navigation bar" aria-expanded="false" class="navbar__toggle clean-btn" type="button"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><div class="navbar__logo"><img src="https://cdn.deepseek.com/platform/favicon.png" alt="DeepSeek API Docs Logo" class="themedComponent_EBr5 themedComponent--light_FDat"><img src="https://cdn.deepseek.com/platform/favicon.png" alt="DeepSeek API Docs Logo" class="themedComponent_EBr5 themedComponent--dark_NU8c"></div><b class="navbar__title text--truncate">DeepSeek API Docs</b></a></div><div class="navbar__items navbar__items--right"><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link"><svg viewBox="0 0 24 24" width="20" height="20" aria-hidden="true" class="iconLanguage_B6X1"><path fill="currentColor" d="M12.87 15.07l-2.54-2.51.03-.03c1.74-1.94 2.98-4.17 3.71-6.53H17V4h-7V2H8v2H1v1.99h11.17C11.5 7.92 10.44 9.75 9 11.35 8.07 10.32 7.3 9.19 6.69 8h-2c.73 1.63 1.73 3.17 2.98 4.56l-5.09 5.02L4 19l5-5 3.11 3.11.76-2.04zM18.5 10h-2L12 22h2l1.12-3h4.75L21 22h2l-4.5-12zm-2.62 7l1.62-4.33L19.12 17h-3.24z"></path></svg>English</a><ul class="dropdown__menu"><li><a href="/news/news260910" target="_self" rel="noopener noreferrer" class="dropdown__link dropdown__link--active" lang="en">English</a></li><li><a href="/zh-cn/news/news260910" target="_self" rel="noopener noreferrer" class="dropdown__link" lang="zh-cn">中文（中国）</a></li></ul></div><a href="https://platform.deepseek.com/" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link">DeepSeek Platform<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_YH95"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a><div class="toggle_SQQt colorModeToggle_ulqQ"><button class="clean-btn toggleButton_Z4XR toggleButtonDisabled_lK4M" type="button" disabled="" title="Switch between dark and light mode (currently light mode)" aria-label="Switch between dark and light mode (currently light mode)" aria-live="polite"><svg viewBox="0 0 24 24" width="24" height="24" class="lightToggleIcon_JCQN"><path fill="currentColor" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" class="darkToggleIcon_R3EN"><path fill="currentColor" d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"></path></svg></button></div><div class="navbarSearchContainer_uDFu"></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div></nav><div id="__docusaurus_skipToContent_fallback" class="main-wrapper mainWrapper_O4_m"><div class="docsWrapper_mcSy"><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_XdUj" type="button"></button><div class="docRoot_Dr47"><aside class="theme-doc-sidebar-container docSidebarContainer_baRN"><div class="sidebarViewport_VhFV"><div class="sidebar_pcuX"><nav aria-label="Docs sidebar" class="menu thin-scrollbar menu_r8D2"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="true" href="/">Quick Start</a></div><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/">Your First API Call</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/quick_start/pricing">Models & Pricing</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/quick_start/token_usage">Token & Token Usage</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/quick_start/rate_limit">Rate Limit & Isolation</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/quick_start/error_codes">Error Codes</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a href="https://deepseek-harness.github.io/deepseek-harness/en/guide/quickstart" target="_blank" rel="noopener noreferrer" class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0">Agent Integrations</a></div></li></ul></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="true" href="/guides/vision">API Guides</a></div><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/vision">Vision</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/thinking_mode">Thinking Mode</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/multi_round_chat">Multi-round Conversation</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/chat_prefix_completion">Chat Prefix Completion (Beta)</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/fim_completion">FIM Completion (Beta)</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/json_mode">JSON Output</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/tool_calls">Tool Calls</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/files_api">Files API</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/kv_cache">Context Caching</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/responses_api">Using the Responses API</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/guides/anthropic_api">Using the Anthropic API</a></li></ul></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/api/create-chat-completion">API Reference</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" aria-expanded="true" href="/news/news260910">News</a></div><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link menu__link--active" aria-current="page" tabindex="0" href="/news/news260910">DeepSeek-V4.1-Flash Release 2026/09/10</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news260821">DeepSeek-V4-Flash-Vision-Exp Release 2026/08/21</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news260813">DeepSeek-V4-Pro GA Release 2026/08/13</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news260424">DeepSeek-V4 Preview Release 2026/04/24</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news251201">DeepSeek-V3.2 Release 2025/12/01</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250929">DeepSeek-V3.2-Exp Release 2025/09/29</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250922">DeepSeek V3.1 Update 2025/09/22</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250821">DeepSeek V3.1 Release 2025/08/21</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250528">DeepSeek-R1-0528 Release 2025/05/28</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250325">DeepSeek-V3-0324 Release 2025/03/25</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250120">DeepSeek-R1 Release 2025/01/20</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news250115">DeepSeek APP 2025/01/15</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news1226">Introducing DeepSeek-V3 2024/12/26</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news1210">DeepSeek-V2.5-1210 Release 2024/12/10</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news1120">DeepSeek-R1-Lite Release 2024/11/20</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news0905">DeepSeek-V2.5 Release 2024/09/05</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news0802">Context Caching is Available 2024/08/02</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/news/news0725">New API Features 2024/07/25</a></li></ul></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a href="https://github.com/deepseek-ai/awesome-deepseek-integration/tree/main" target="_blank" rel="noopener noreferrer" class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false">Other Resources</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a href="https://static.deepseek.com/faq/index.html?lang=en#/category/4" target="_blank" rel="noopener noreferrer" class="menu__link menuExternalLink_kqFC">FAQ<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_YH95"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/updates">Change Log</a></li></ul></nav></div></div></aside><main class="docMainContainer_SNqp"><div class="container padding-top--md padding-bottom--lg"><div class="row"><div class="col docItemCol_GEdM"><div class="docItemContainer_OUCh"><article><nav class="theme-doc-breadcrumbs breadcrumbsContainer_gDTe" aria-label="Breadcrumbs"><ul class="breadcrumbs" itemscope="" itemtype="https://schema.org/BreadcrumbList"><li class="breadcrumbs__item"><a aria-label="Home page" class="breadcrumbs__link" href="/"><svg viewBox="0 0 24 24" class="breadcrumbHomeIcon_fbmM"><path d="M10 19v-5h4v5c0 .55.45 1 1 1h3c.55 0 1-.45 1-1v-7h1.7c.46 0 .68-.57.33-.87L12.67 3.6c-.38-.34-.96-.34-1.34 0l-8.36 7.53c-.34.3-.13.87.33.87H5v7c0 .55.45 1 1 1h3c.55 0 1-.45 1-1z" fill="currentColor"></path></svg></a></li><li class="breadcrumbs__item"><span class="breadcrumbs__link">News</span><meta itemprop="position" content="1"></li><li itemscope="" itemprop="itemListElement" itemtype="https://schema.org/ListItem" class="breadcrumbs__item breadcrumbs__item--active"><span class="breadcrumbs__link" itemprop="name">DeepSeek-V4.1-Flash Release 2026/09/10</span><meta itemprop="position" content="2"></li></ul></nav><div class="tocCollapsible_lKxX theme-doc-toc-mobile tocMobile_kO7c"><button type="button" class="clean-btn tocCollapsibleButton_KNXb">On this page</button></div><div class="theme-doc-markdown markdown"><div class="row"><div class="col col--12"><h1>DeepSeek-V4.1-Flash: Smarter, Faster, More Efficient</h1>12<p>🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.</p>13<p>🔹 Introducing the smallest model in our new architecture family, with native visual understanding.</p>14<p>🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.</p>15<div align="center"><img src="/img/v4.1_260910_benchmark.png" width="600"></div>16<hr>17<h2 class="anchor anchorWithStickyNavbar_YAqC" id="-asymmetric-architecture-more-intelligence-less-cost">🧠 Asymmetric architecture. More intelligence, less cost.<a href="#-asymmetric-architecture-more-intelligence-less-cost" class="hash-link" aria-label="Direct link to 🧠 Asymmetric architecture. More intelligence, less cost." title="Direct link to 🧠 Asymmetric architecture. More intelligence, less cost."></a></h2>18<p>🔹 552B-parameter MoE.</p>19<p>🔹 New Causal Encoder–Decoder architecture: just 8B active parameters for input, 16B for output.</p>20<p>🔹 New pre-training methods + larger-scale RL post-training deliver benchmark results ahead of flagship models, including DeepSeek-V4-Pro.</p>21<div align="center"><img src="/img/v4.1_260910_benchmark_table_en.png" width="600"></div>22<hr>23<h2 class="anchor anchorWithStickyNavbar_YAqC" id="-smaller-kv-cache-bigger-savings">💾 Smaller KV cache. Bigger savings.<a href="#-smaller-kv-cache-bigger-savings" class="hash-link" aria-label="Direct link to 💾 Smaller KV cache. Bigger savings." title="Direct link to 💾 Smaller KV cache. Bigger savings."></a></h2>24<p>Compared with the previous generation, V4.1-Flash's KV cache needs just:</p>25<p>🔹 1/4 the HBM</p>26<p>🔹 1/8 the SSD storage</p>27<p>Cache-hit charges often account for a large share of agent costs. Compressing the cache cuts those costs significantly.</p>28<div align="center"><img src="/img/v4.1_260910_kvcache.png" width="600"></div>29<hr>30<h2 class="anchor anchorWithStickyNavbar_YAqC" id="-v41-flash-is-now-live-on-the-deepseek-api-with-native-multimodal-support">⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support.<a href="#-v41-flash-is-now-live-on-the-deepseek-api-with-native-multimodal-support" class="hash-link" aria-label="Direct link to ⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support." title="Direct link to ⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support."></a></h2>31<p>Set your model to <code>deepseek-flash</code>.</p>32<p>🔹 V4-Flash & V4-Flash-Vision-Exp are retired. For compatibility, <code>deepseek-v4-flash</code> and <code>deepseek-v4-flash-vision-exp</code> temporarily route to V4.1-Flash.</p>33<p>🔹 Tests by multiple parties put V4.1-Flash ahead of V4-Pro on performance, cost, speed & total runtime. We're phasing out V4-Pro.</p>34<p>🔹 Starting at 04:00 UTC on Sept 14, 2026, all <code>deepseek-v4-pro</code> requests will route to V4.1-Flash at V4.1-Flash rates. This will continue until V4.1-Pro launches.</p>35<p>🤝 Official partners WorkBuddy (including CodeBuddy) & OpenCode now fully support V4.1-Flash. Try it today!</p>36<hr>37<h2 class="anchor anchorWithStickyNavbar_YAqC" id="-more-efficient-architecture-lower-api-prices">💰 More efficient architecture. Lower API prices.<a href="#-more-efficient-architecture-lower-api-prices" class="hash-link" aria-label="Direct link to 💰 More efficient architecture. Lower API prices." title="Direct link to 💰 More efficient architecture. Lower API prices."></a></h2>38<p>V4.1-Flash lets us serve more users at a lower cost. We're passing the savings on to you.</p>39<p>🔹 Peak/off-peak pricing continues to balance demand.</p>40<p>🔹 Off-peak rates are 50% of peak rates. Schedule flexible workloads off-peak to save.</p>41<p>🔹 New pricing takes effect at 04:00 UTC on Sept 10, 2026.</p>42<div align="center"><img src="/img/v4.1_260910_price_en.jpeg" width="600"></div>43<hr>44<h2 class="anchor anchorWithStickyNavbar_YAqC" id="-supporting-open-source-expanding-deployment-options">🌐 Supporting open source. Expanding deployment options.<a href="#-supporting-open-source-expanding-deployment-options" class="hash-link" aria-label="Direct link to 🌐 Supporting open source. Expanding deployment options." title="Direct link to 🌐 Supporting open source. Expanding deployment options."></a></h2>45<p>We'll work closely with the open-source community on V4.1-Flash inference support and explore more deployment options.</p>46<p>Planning a large-scale deployment with 2,000 GPUs + a storage cluster? Let's talk.</p>47<p>🔹 Model: <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash" target="_blank" rel="noopener noreferrer">https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash</a></p>48<p>🔹 Paper: <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/DeepSeek_V41_Tech_Report.pdf" target="_blank" rel="noopener noreferrer">https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/DeepSeek_V41_Tech_Report.pdf</a></p></div></div></div><div class="col col--12"></div></article><div class="col col--12"><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/api/delete-file"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Delete File</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/news/news260821"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">DeepSeek-V4-Flash-Vision-Exp Release: Multimodal API Now Live</div></a></nav></div></div></div><div class="col col--3"><div class="tableOfContents_QFHP thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#-asymmetric-architecture-more-intelligence-less-cost" class="table-of-contents__link toc-highlight">🧠 Asymmetric architecture. More intelligence, less cost.</a></li><li><a href="#-smaller-kv-cache-bigger-savings" class="table-of-contents__link toc-highlight">💾 Smaller KV cache. Bigger savings.</a></li><li><a href="#-v41-flash-is-now-live-on-the-deepseek-api-with-native-multimodal-support" class="table-of-contents__link toc-highlight">⚡ V4.1-Flash is now live on the DeepSeek API with native multimodal support.</a></li><li><a href="#-more-efficient-architecture-lower-api-prices" class="table-of-contents__link toc-highlight">💰 More efficient architecture. Lower API prices.</a></li><li><a href="#-supporting-open-source-expanding-deployment-options" class="table-of-contents__link toc-highlight">🌐 Supporting open source. Expanding deployment options.</a></li></ul></div></div></div></div></main></div></div></div><footer class="footer footer--dark"><div class="container container-fluid"><div class="row footer__links"><div class="col footer__col"><div class="footer__title">WeChat Official Account</div><ul class="footer__items clean-list"><li class="footer__item">49 <img src="https://cdn.deepseek.com/official_account.jpg" alt="WeChat QRcode" width="160px">50 </li></ul></div><div class="col footer__col"><div class="footer__title">Community</div><ul class="footer__items clean-list"><li class="footer__item"><a href="mailto:api-service@deepseek.com" target="_blank" rel="noopener noreferrer" class="footer__link-item">Email<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_YH95"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li class="footer__item"><a href="https://discord.gg/Tc7c45Zzu5" target="_blank" rel="noopener noreferrer" class="footer__link-item">Discord<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_YH95"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li class="footer__item"><a href="https://twitter.com/deepseek_ai" target="_blank" rel="noopener noreferrer" class="footer__link-item">Twitter<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_YH95"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li></ul></div><div class="col footer__col"><div class="footer__title">More</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://github.com/deepseek-ai" target="_blank" rel="noopener noreferrer" class="footer__link-item">GitHub<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_YH95"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li></ul></div></div><div class="footer__bottom text--center"><div class="footer__copyright">Copyright © 2026 DeepSeek, Inc.</div></div></div></footer></div>51</body>52</html>