1:"$Sreact.fragment"
3:I[54118,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1737","static/chunks/fe207bbb-c84ed91deca4f888.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","144","static/chunks/144-1a048554a0613a1b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","528","static/chunks/528-7ef2006e50a52549.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2530","static/chunks/2530-9eb218eca5ffc00b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7177","static/chunks/app/layout-75dbb92d3cda2f1c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"Providers"]
4:I[98195,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1737","static/chunks/fe207bbb-c84ed91deca4f888.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","144","static/chunks/144-1a048554a0613a1b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","528","static/chunks/528-7ef2006e50a52549.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2530","static/chunks/2530-9eb218eca5ffc00b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7177","static/chunks/app/layout-75dbb92d3cda2f1c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"GoogleTagManager"]
5:I[4411,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1737","static/chunks/fe207bbb-c84ed91deca4f888.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","144","static/chunks/144-1a048554a0613a1b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","528","static/chunks/528-7ef2006e50a52549.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2530","static/chunks/2530-9eb218eca5ffc00b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7177","static/chunks/app/layout-75dbb92d3cda2f1c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"FilmAwardStrip"]
6:"$Sreact.suspense"
7:I[40459,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1737","static/chunks/fe207bbb-c84ed91deca4f888.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","144","static/chunks/144-1a048554a0613a1b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","528","static/chunks/528-7ef2006e50a52549.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2530","static/chunks/2530-9eb218eca5ffc00b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7177","static/chunks/app/layout-75dbb92d3cda2f1c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"Navbar"]
8:I[15848,[],""]
9:I[55256,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","8039","static/chunks/app/error-332e154bd557e323.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"default"]
a:I[62142,[],""]
19:I[79302,["4219","static/chunks/app/global-error-f07d85f704128170.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"default"]
:HL["/_next/static/media/7d4881bb7e1bf84d-s.p.woff2","font",{"crossOrigin":"","type":"font/woff2"}]
:HL["/_next/static/css/c91c557421edbcc1.css?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","style"]
:HL["/_next/static/css/9c4f0c3be44ead33.css?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","style"]
2:T412,
(function () {
  window.dataLayer = window.dataLayer || [];
  function gtag() { window.dataLayer.push(arguments); }

  gtag('consent', 'default', {
    ad_storage: 'denied',
    ad_user_data: 'denied',
    ad_personalization: 'denied',
    analytics_storage: 'denied',
    functionality_storage: 'denied',
    personalization_storage: 'denied',
    security_storage: 'granted'
  });

  try {
    var match = document.cookie.match(/(?:^|;\s*)gdpr_consent=([^;]*)/);
    if (!match) return;
    var saved = JSON.parse(decodeURIComponent(match[1]));
    if (!saved || typeof saved !== 'object') return;
    gtag('consent', 'update', {
      analytics_storage: saved.analytics ? 'granted' : 'denied',
      ad_storage: saved.marketing ? 'granted' : 'denied',
      ad_user_data: saved.marketing ? 'granted' : 'denied',
      ad_personalization: saved.marketing ? 'granted' : 'denied',
      functionality_storage: saved.functional ? 'granted' : 'denied'
    });
  } catch (e) {
    /* malformed cookie â€” the denied default stands */
  }
})();
0:{"P":null,"b":"vX-6P7rGIK5v7u82yfIum","p":"","c":["","models","gemini-embedding-2"],"i":false,"f":[[["",{"children":["models",{"children":[["route","gemini-embedding-2","d"],{"children":["__PAGE__",{}]}]}]},"$undefined","$undefined",true],["",["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/c91c557421edbcc1.css?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","precedence":"next","crossOrigin":"$undefined","nonce":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/_next/static/css/9c4f0c3be44ead33.css?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","precedence":"next","crossOrigin":"$undefined","nonce":"$undefined"}]],["$","html",null,{"lang":"en","suppressHydrationWarning":true,"className":"__variable_8c25df","children":[["$","head",null,{"children":[["$","script",null,{"id":"consent-mode-default","dangerouslySetInnerHTML":{"__html":"$2"}}],["$","script",null,{"id":"film-award-dismissed","dangerouslySetInnerHTML":{"__html":"try{if(document.cookie.split(';').some(function(c){return c.trim()===\"film_award_2027_dismissed=1\"}))document.documentElement.setAttribute(\"data-film-award-dismissed\",'')}catch(e){}"}}],["$","link",null,{"rel":"preconnect","href":"https://images.segmind.com"}],["$","link",null,{"rel":"preconnect","href":"https://segmind-resources.s3.amazonaws.com"}],["$","link",null,{"rel":"preconnect","href":"https://www.googletagmanager.com"}],["$","link",null,{"rel":"preload","href":"/fonts/Satoshi-Variable.woff2","as":"font","type":"font/woff2","crossOrigin":"anonymous"}]]}],["$","body",null,{"className":"antialiased bg-background text-foreground","children":["$","$L3",null,{"children":[["$","$L4",null,{"gtmId":"GTM-MHW23H4Z"}],["$","div",null,{"className":"min-h-screen flex flex-col","children":[["$","$L5",null,{}],["$","$6",null,{"fallback":["$","div",null,{"className":"h-16 bg-background/95 backdrop-blur border-b border-border"}],"children":["$","$L7",null,{}]}],["$","main",null,{"className":"flex-1","children":["$","$L8",null,{"parallelRouterKey":"children","error":"$9","errorStyles":[],"errorScripts":[],"template":["$","$La",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","div",null,{"className":"min-h-screen bg-background flex items-center justify-center px-4 sm:px-6 lg:px-8","children":["$","div",null,{"className":"max-w-lg w-full text-center","children":[["$","div",null,{"className":"mb-8","children":["$","div",null,{"className":"relative","children":[["$","h1",null,{"className":"text-9xl font-bold text-muted/20 dark:text-muted/10 select-none","children":"404"}],["$","div",null,{"className":"absolute inset-0 flex items-center justify-center","children":["$","div",null,{"className":"relative","children":[["$","div",null,{"className":"absolute -top-8 -left-8 w-16 h-16 bg-brand-100 dark:bg-brand-950 rounded-full flex items-center justify-center animate-bounce","children":["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-zap w-8 h-8 text-brand-500","children":["$Lb","$undefined"]}]}],"$Lc","$Ld"]}]}]]}]}],"$Le","$Lf","$L10","$L11"]}]}],[]],"forbidden":"$undefined","unauthorized":"$undefined"}]}],"$L12"]}],"$L13","$L14"]}]}]]}]]}],{"children":["models","$L15",{"children":[["route","gemini-embedding-2","d"],"$L16",{"children":["__PAGE__","$L17",{},null,false]},null,false]},null,false]},null,false],"$L18",false]],"m":"$undefined","G":["$19",[]],"s":false,"S":true}
1a:I[75289,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6541","static/chunks/fb4e7fc9-e31ad622f5fde25d.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9761","static/chunks/998e86a0-e112630ec4db17dc.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6118","static/chunks/6118-7328b7d3f629a5ef.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","393","static/chunks/393-7cd2157fc3790475.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3985","static/chunks/3985-1f9bcb95de313d61.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4844","static/chunks/4844-011fe3465334e7d0.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9305","static/chunks/9305-0f5d0f2a661afddc.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","713","static/chunks/713-dcb3ca4f0233704d.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3504","static/chunks/3504-ae9bc2dc93d2ef47.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1885","static/chunks/1885-f206f5873f09b3e2.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5126","static/chunks/5126-bdde68ce894e4935.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5642","static/chunks/5642-c80cb7ee6e914a6a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6372","static/chunks/6372-3e2880fc7d769d1f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1289","static/chunks/1289-4fdf72847f7ef615.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","8382","static/chunks/8382-004a14550e3769cc.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1951","static/chunks/app/models/%5Broute%5D/page-c5fd4df0a8a5cab4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],""]
1b:I[4717,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1737","static/chunks/fe207bbb-c84ed91deca4f888.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","144","static/chunks/144-1a048554a0613a1b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","528","static/chunks/528-7ef2006e50a52549.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2530","static/chunks/2530-9eb218eca5ffc00b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7177","static/chunks/app/layout-75dbb92d3cda2f1c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"Footer"]
1c:I[35733,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","341","static/chunks/app/models/(catalogue)/loading-03c2017343ab8539.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"Toaster"]
1d:I[20659,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1737","static/chunks/fe207bbb-c84ed91deca4f888.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6397","static/chunks/6397-b7ccd1edf8aedf12.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","144","static/chunks/144-1a048554a0613a1b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","528","static/chunks/528-7ef2006e50a52549.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2530","static/chunks/2530-9eb218eca5ffc00b.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7177","static/chunks/app/layout-75dbb92d3cda2f1c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"LazyLayoutExtras"]
20:I[30661,[],"OutletBoundary"]
22:I[72272,[],"AsyncMetadataOutlet"]
24:I[30661,[],"ViewportBoundary"]
26:I[30661,[],"MetadataBoundary"]
b:["$","path","1xq2db",{"d":"M4 14a1 1 0 0 1-.78-1.63l9.9-10.2a.5.5 0 0 1 .86.46l-1.92 6.02A1 1 0 0 0 13 10h7a1 1 0 0 1 .78 1.63l-9.9 10.2a.5.5 0 0 1-.86-.46l1.92-6.02A1 1 0 0 0 11 14z"}]
c:["$","div",null,{"className":"absolute -top-4 -right-12 w-12 h-12 bg-brand-secondary-100 dark:bg-brand-secondary-950 rounded-full flex items-center justify-center animate-pulse","children":["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-search w-6 h-6 text-brand-secondary-500","children":[["$","circle","4ej97u",{"cx":"11","cy":"11","r":"8"}],["$","path","1qie3q",{"d":"m21 21-4.3-4.3"}],"$undefined"]}]}]
d:["$","div",null,{"className":"absolute -bottom-6 left-4 w-10 h-10 bg-green-100 dark:bg-green-950 rounded-full flex items-center justify-center animate-bounce delay-200","children":["$","div",null,{"className":"w-3 h-3 bg-green-500 rounded-full"}]}]
e:["$","div",null,{"className":"mb-8","children":[["$","h2",null,{"className":"text-2xl font-semibold text-foreground mb-4","children":"Page Not Found"}],["$","p",null,{"className":"text-muted-foreground text-lg mb-2","children":"Oops! The page you're looking for doesn't exist."}],["$","p",null,{"className":"text-muted-foreground","children":"It might have been moved, deleted, or you entered the wrong URL."}]]}]
f:["$","div",null,{"className":"flex flex-col sm:flex-row gap-4 justify-center items-center mb-12","children":[["$","$L1a",null,{"href":"/","className":"inline-flex items-center justify-center gap-2 px-6 py-3 bg-brand-600 dark:bg-brand-500 text-white rounded-lg hover:bg-brand-700 dark:hover:bg-brand-600 transition-colors font-medium text-base w-full sm:w-auto","children":[["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-house w-5 h-5","children":[["$","path","5wwlr5",{"d":"M15 21v-8a1 1 0 0 0-1-1h-4a1 1 0 0 0-1 1v8"}],["$","path","1d0kgt",{"d":"M3 10a2 2 0 0 1 .709-1.528l7-5.999a2 2 0 0 1 2.582 0l7 5.999A2 2 0 0 1 21 10v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2z"}],"$undefined"]}],"Go Home"]}],["$","$L1a",null,{"href":"/models","className":"inline-flex items-center justify-center gap-2 px-6 py-3 bg-surface border border-border text-foreground rounded-lg hover:bg-surface/80 transition-colors font-medium text-base w-full sm:w-auto","children":[["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-search w-5 h-5","children":[["$","circle","4ej97u",{"cx":"11","cy":"11","r":"8"}],["$","path","1qie3q",{"d":"m21 21-4.3-4.3"}],"$undefined"]}],"Browse Models"]}]]}]
10:["$","div",null,{"className":"border-t border-border pt-8","children":[["$","p",null,{"className":"text-sm text-muted-foreground mb-4","children":"Popular destinations:"}],["$","div",null,{"className":"flex flex-wrap justify-center gap-4 text-sm","children":[["$","$L1a",null,{"href":"/models/tags/image","className":"text-brand-600 dark:text-brand-400 hover:text-brand-700 dark:hover:text-brand-300 transition-colors","children":"Image Models"}],["$","span",null,{"className":"text-muted-foreground","children":"â€¢"}],["$","$L1a",null,{"href":"/models/tags/video","className":"text-brand-600 dark:text-brand-400 hover:text-brand-700 dark:hover:text-brand-300 transition-colors","children":"Video Models"}],["$","span",null,{"className":"text-muted-foreground","children":"â€¢"}],["$","$L1a",null,{"href":"/models/tags/llms","className":"text-brand-600 dark:text-brand-400 hover:text-brand-700 dark:hover:text-brand-300 transition-colors","children":"LLMs"}],["$","span",null,{"className":"text-muted-foreground","children":"â€¢"}],["$","$L1a",null,{"href":"/models","className":"text-brand-600 dark:text-brand-400 hover:text-brand-700 dark:hover:text-brand-300 transition-colors","children":"All Models"}]]}]]}]
11:["$","div",null,{"className":"mt-8","children":["$","$L1a",null,{"href":"/","className":"inline-flex items-center text-sm text-muted-foreground hover:text-foreground transition-colors","children":[["$","svg",null,{"ref":"$undefined","xmlns":"http://www.w3.org/2000/svg","width":24,"height":24,"viewBox":"0 0 24 24","fill":"none","stroke":"currentColor","strokeWidth":2,"strokeLinecap":"round","strokeLinejoin":"round","className":"lucide lucide-arrow-left w-4 h-4 mr-2","children":[["$","path","1l729n",{"d":"m12 19-7-7 7-7"}],["$","path","x3x0zl",{"d":"M19 12H5"}],"$undefined"]}],"Go back to homepage"]}]}]
12:["$","$L1b",null,{}]
13:["$","$L1c",null,{"closeButton":true,"toastOptions":{"duration":30000}}]
14:["$","$L1d",null,{}]
15:["$","$1","c",{"children":[null,["$","$L8",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$La",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","forbidden":"$undefined","unauthorized":"$undefined"}]]}]
16:["$","$1","c",{"children":[null,"$L1e"]}]
17:["$","$1","c",{"children":["$L1f",null,["$","$L20",null,{"children":["$L21",["$","$L22",null,{"promise":"$@23"}]]}]]}]
18:["$","$1","h",{"children":[null,[["$","$L24",null,{"children":"$L25"}],["$","meta",null,{"name":"next-size-adjust","content":""}]],["$","$L26",null,{"children":["$","div",null,{"hidden":true,"children":["$","$6",null,{"fallback":null,"children":"$L27"}]}]}]]}]
25:[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1"}]]
21:null
28:I[53921,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7213","static/chunks/7213-ed3acee0c865cd60.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7256","static/chunks/app/models/%5Broute%5D/layout-23522cb6540a765c.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"default"]
2c:I[4704,[],"IconMark"]
29:T1265,# Gemini Embedding 2 â€” Text Embedding API

## What is Gemini Embedding 2?

Gemini Embedding 2 is Google's state-of-the-art text embedding model, built to convert natural language into dense numerical vectors that capture semantic meaning. With the top MTEB score of 68.16 â€” outperforming OpenAI text-embedding-3-large (64.6) and Cohere embed-v4 (65.2) â€” it delivers industry-leading retrieval and similarity accuracy across 100+ languages.

Via the Segmind API, you send a text string and receive a float vector ready for indexing in any vector database (Pinecone, Qdrant, Weaviate, pgvector). Eight task-specific modes let you tune the embedding direction to exactly match your use case â€” from document retrieval to code search to fact verification.

## Key Features

- **SOTA MTEB performance:** 68.16 overall; 84.0 on code retrieval; 69.9 on multilingual tasks
- **8 task types:** RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING, QUESTION_ANSWERING, FACT_VERIFICATION, CODE_RETRIEVAL_QUERY
- **Configurable dimensionality:** Output vectors from 256 to 768 dimensions â€” balance quality vs. storage cost
- **100+ language support:** Strong cross-lingual retrieval without translation preprocessing
- **Synchronous API:** Immediate JSON response with no polling required
- **Segmind infrastructure:** Low-latency, scalable endpoint â€” no GCP project or quota setup needed

## Best Use Cases

**Retrieval-Augmented Generation (RAG):** Use `RETRIEVAL_DOCUMENT` to embed your knowledge base and `RETRIEVAL_QUERY` for user questions. The asymmetric task pairing significantly improves precision over single-task embeddings.

**Semantic search:** Embed a product catalog, documentation site, or support knowledge base. Users get semantically relevant results even when they phrase queries differently from how the content was written.

**Classification and clustering:** Feed embeddings into a lightweight classifier or k-means cluster to categorize support tickets, content tags, or customer feedback without fine-tuning a full LLM.

**Code search:** `CODE_RETRIEVAL_QUERY` produces embeddings tuned for function signatures, docstrings, and code snippets â€” ideal for developer tools and IDE assistants.

**Multilingual pipelines:** With 69.9 MTEB multilingual score, a single index handles queries and documents in different languages without separate per-language models.

## Prompt Tips and Output Quality

- **Always pair task types correctly:** Index documents with `RETRIEVAL_DOCUMENT` and query with `RETRIEVAL_QUERY`. Mixing types degrades recall.
- **Chunk long documents:** Split text into 200â€“500 token segments before embedding. Each chunk should represent one coherent idea.
- **Dimensionality tradeoff:** 768 (default) gives optimal quality. Drop to 512 or 256 if your vector database costs or query latency are a concern â€” vectors are truncated, not re-encoded.
- **SEMANTIC_SIMILARITY is not for retrieval:** Use it only when comparing two texts directly (e.g., paraphrase detection, duplicate finding). It underperforms RETRIEVAL_* pairs in RAG pipelines.
- **Batch efficiently:** Embed multiple documents in sequence; the model is synchronous and fast enough for real-time pipelines at moderate scale.

## FAQs

**Q: What is the difference between RETRIEVAL_QUERY and RETRIEVAL_DOCUMENT?**
RETRIEVAL_QUERY embeds a user's question or search query; RETRIEVAL_DOCUMENT embeds the passages or documents in your index. Always use them as a matched pair â€” this asymmetric approach is how the model is optimised and produces the best recall.

**Q: Can I mix task types when comparing vectors?**
No. Cosine similarity is only meaningful between vectors produced with the same task type.

**Q: How does output_dimensionality work?**
The model produces a full-length vector and then truncates it to your specified size. A value of 768 is the recommended default. Smaller values (256, 512) reduce storage and query latency but may slightly lower retrieval accuracy.

**Q: Is Gemini Embedding 2 better than OpenAI text-embedding-3-large?**
On the MTEB leaderboard, Gemini Embedding 2 scores 68.16 vs. 64.6 for text-embedding-3-large. The quality gap is meaningful for multilingual workloads and code retrieval.

**Q: What vector databases work with Gemini Embedding 2 embeddings?**
Any database that accepts float arrays â€” Pinecone, Qdrant, Weaviate, Chroma, pgvector, Redis, Milvus. Set index dimensions to match your output_dimensionality setting (default: 768).

**Q: Does the model support batch input?**
The Segmind API accepts a single string per request. For batch workloads, send concurrent requests or loop through your corpus sequentially.2a:T783,## How to Use Gemini Embedding 2

Gemini Embedding 2 converts text into dense vectors for search, classification, and similarity tasks. Here is how to get the best results.

### Choosing the Right Task Type

The `task_type` parameter is the most impactful setting. Match it to your use case:

| Use Case | task_type for Documents | task_type for Queries |
|---|---|---|
| RAG / document search | RETRIEVAL_DOCUMENT | RETRIEVAL_QUERY |
| Q&A over a knowledge base | RETRIEVAL_DOCUMENT | QUESTION_ANSWERING |
| Semantic similarity / dedup | SEMANTIC_SIMILARITY | SEMANTIC_SIMILARITY |
| Content classification | CLASSIFICATION | CLASSIFICATION |
| Clustering / topic modeling | CLUSTERING | CLUSTERING |
| Code search | RETRIEVAL_DOCUMENT | CODE_RETRIEVAL_QUERY |
| Claim / fact verification | RETRIEVAL_DOCUMENT | FACT_VERIFICATION |

### Recommended Settings

Based on real testing, these parameters produce reliable, high-quality embeddings:

```json
{
  "input": "Your document or query text here",
  "task_type": "RETRIEVAL_DOCUMENT",
  "output_dimensionality": 768
}
```

Use `output_dimensionality: 512` or `256` if you need to reduce storage costs or query latency.

### Indexing a Document Corpus

Embed each chunk with `RETRIEVAL_DOCUMENT`, then store the resulting vector alongside the chunk text in your vector database. At query time, embed the user's question with `RETRIEVAL_QUERY` and retrieve the closest vectors by cosine similarity.

### Tips for Better Results

- **Chunk documents** into 200â€“500 token segments. Each chunk should cover one topic.
- **Do not mix task types** on the same index â€” all stored vectors must use the same task type.
- **For multilingual corpora**, no preprocessing is needed. The model handles cross-lingual retrieval natively across 100+ languages.
- **For code search**, pair `CODE_RETRIEVAL_QUERY` queries against function/method text embedded with `RETRIEVAL_DOCUMENT`.1e:["$","$L28",null,{"route":"gemini-embedding-2","modelDetails":{"title":"Gemini Embedding 2","thumbnail_image":"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-2-6042.webp","type":"textToEmbed","model_type":"SG","is_depreciated":false,"meta_description":"Google's natively multimodal embedding model â€” embed text, images, audio, video and PDF into one shared vector space. 68.16 MTEB, 8 task types, 100+ languages, synchronous API.","seo_description":"$29","guide":"$2a","pricing_guide":null,"artifacts":[],"default_image_output":"Gemini Embedding 2","default_response":null,"parameters":{"input":{"isRequired":true,"affectsPricing":false,"type":"str","description":"Text string to embed; supports up to ~8,192 tokens. Use shorter, focused sentences for best retrieval accuracy.","isEnum":false,"hidden":false,"isAdvanced":false,"displayOrder":0,"component":"textarea","displayValue":"Segmind provides fast and affordable AI model APIs for image generation, video creation, and more.","default":"Segmind provides fast and affordable AI model APIs for image generation, video creation, and more.","label":"Input"},"task_type":{"isRequired":false,"affectsPricing":false,"type":"str","description":"Optimizes embedding direction for your use case. Use RETRIEVAL_DOCUMENT for corpus, RETRIEVAL_QUERY for user queries, SEMANTIC_SIMILARITY for pair comparison.","isEnum":true,"hidden":false,"isAdvanced":true,"displayOrder":1,"component":"autocomplete","values":["SEMANTIC_SIMILARITY","RETRIEVAL_DOCUMENT","RETRIEVAL_QUERY","CLASSIFICATION","CLUSTERING","QUESTION_ANSWERING","FACT_VERIFICATION","CODE_RETRIEVAL_QUERY"],"default":"RETRIEVAL_DOCUMENT","displayValue":"RETRIEVAL_DOCUMENT","label":"Task Type"},"output_dimensionality":{"isRequired":false,"affectsPricing":false,"type":"int","description":"Truncates vector length; 768 balances quality and storage. Use 256-512 for speed-sensitive pipelines.","isEnum":false,"hidden":false,"isAdvanced":true,"displayOrder":2,"component":"text_field","displayValue":768,"default":768,"label":"Output Dimensionality"},"image":{"isRequired":false,"affectsPricing":false,"type":"str","format":"uri","component":"textbox","isEnum":false,"hidden":false,"isAdvanced":false,"displayOrder":3,"label":"Image","description":"Optional image to embed into the same vector space as text (URL or base64). PNG/JPEG; up to 6 per request via the `images` array. Combined with `input` text into one aggregated vector."},"audio":{"isRequired":false,"affectsPricing":false,"type":"str","format":"uri","component":"textbox","isEnum":false,"hidden":false,"isAdvanced":true,"displayOrder":4,"label":"Audio","description":"Optional audio file to embed (URL or base64). MP3/WAV, up to 180 seconds."},"video":{"isRequired":false,"affectsPricing":false,"type":"str","format":"uri","component":"textbox","isEnum":false,"hidden":false,"isAdvanced":true,"displayOrder":5,"label":"Video","description":"Optional video file to embed (URL or base64). MP4/MOV, up to 120 seconds."},"pdf":{"isRequired":false,"affectsPricing":false,"type":"str","format":"uri","component":"textbox","isEnum":false,"hidden":false,"isAdvanced":true,"displayOrder":6,"label":"PDF","description":"Optional PDF file to embed (URL or base64). 1 file, up to 6 pages."}},"endpoints":{"main":"/v1/gemini-embedding-2"},"api_notes":[],"model_outputs":null,"llm_capabilities":null,"license":null,"github_link":null,"inference_provider":"GEMINI","created_ts":"2026-05-03 20:03:40.213108+00:00","slug":"gemini-embedding-2","name":"Gemini Embedding 2","description":"Natively multimodal embeddings â€” text, image, audio, video and PDF mapped into one vector space, with 8 task-specific modes.","category":"textToEmbed","modality":"embed","input":"text","output":"embedding","provider":"GOOGLE","thumbnail_url":"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-2-6042.webp","is_new":false,"coming_soon":false,"popularity_score":83,"category_percentile":100,"average_cost":0.000025296795120061965,"latency_seconds":1.02839,"created_at":"2026-05-03 20:03:40.213108+00:00","parameters_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"input":{"type":"string","title":"Input","description":"Text string to embed; supports up to ~8,192 tokens. Use shorter, focused sentences for best retrieval accuracy.","default":"Segmind provides fast and affordable AI model APIs for image generation, video creation, and more.","x-ui-metadata":{"order":0,"advanced":false,"hidden":false}},"task_type":{"type":"string","title":"Task Type","description":"Optimizes embedding direction for your use case. Use RETRIEVAL_DOCUMENT for corpus, RETRIEVAL_QUERY for user queries, SEMANTIC_SIMILARITY for pair comparison.","oneOf":[{"const":"SEMANTIC_SIMILARITY","title":"SEMANTIC_SIMILARITY"},{"const":"RETRIEVAL_DOCUMENT","title":"RETRIEVAL_DOCUMENT"},{"const":"RETRIEVAL_QUERY","title":"RETRIEVAL_QUERY"},{"const":"CLASSIFICATION","title":"CLASSIFICATION"},{"const":"CLUSTERING","title":"CLUSTERING"},{"const":"QUESTION_ANSWERING","title":"QUESTION_ANSWERING"},{"const":"FACT_VERIFICATION","title":"FACT_VERIFICATION"},{"const":"CODE_RETRIEVAL_QUERY","title":"CODE_RETRIEVAL_QUERY"}],"default":"RETRIEVAL_DOCUMENT","x-ui-metadata":{"order":1,"advanced":true,"hidden":false}},"output_dimensionality":{"type":"integer","title":"Output Dimensionality","description":"Truncates vector length; 768 balances quality and storage. Use 256-512 for speed-sensitive pipelines.","default":768,"x-ui-metadata":{"order":2,"advanced":true,"hidden":false}},"image":{"type":"string","format":"uri","x-file-metadata":{"allowed-types":["image/*"]},"title":"Image","description":"Optional image to embed into the same vector space as text (URL or base64). PNG/JPEG; up to 6 per request via the `images` array. Combined with `input` text into one aggregated vector.","x-ui-metadata":{"order":3,"advanced":false,"hidden":false}},"audio":{"type":"string","format":"uri","x-file-metadata":{"allowed-types":["audio/*"]},"title":"Audio","description":"Optional audio file to embed (URL or base64). MP3/WAV, up to 180 seconds.","x-ui-metadata":{"order":4,"advanced":true,"hidden":false}},"video":{"type":"string","format":"uri","x-file-metadata":{"allowed-types":["video/*"]},"title":"Video","description":"Optional video file to embed (URL or base64). MP4/MOV, up to 120 seconds.","x-ui-metadata":{"order":5,"advanced":true,"hidden":false}},"pdf":{"type":"string","format":"uri","x-file-metadata":{"allowed-types":["application/pdf"]},"title":"PDF","description":"Optional PDF file to embed (URL or base64). 1 file, up to 6 pages.","x-ui-metadata":{"order":6,"advanced":true,"hidden":false}}},"required":["input"],"examples":[{"input":"Segmind provides fast and affordable AI model APIs for image generation, video creation, and more.","task_type":"RETRIEVAL_DOCUMENT","output_dimensionality":768}]}},"metrics":{"total_requests":null,"latency":1.02839},"children":"$L2b"}]
23:{"metadata":[["$","title","0",{"children":"Gemini Embedding 2 API | Segmind"}],["$","meta","1",{"name":"description","content":"Google's natively multimodal embedding model â€” embed text, images, audio, video and PDF into one shared vector space. 68.16 MTEB, 8 task types, 100+ languages"}],["$","link","2",{"rel":"canonical","href":"https://www.segmind.com/models/gemini-embedding-2"}],["$","meta","3",{"property":"og:title","content":"Gemini Embedding 2 API | Segmind"}],["$","meta","4",{"property":"og:description","content":"Google's natively multimodal embedding model â€” embed text, images, audio, video and PDF into one shared vector space. 68.16 MTEB, 8 task types, 100+ languages"}],["$","meta","5",{"property":"og:image","content":"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-2-6042.webp"}],["$","meta","6",{"name":"twitter:card","content":"summary_large_image"}],["$","meta","7",{"name":"twitter:title","content":"Gemini Embedding 2 API | Segmind"}],["$","meta","8",{"name":"twitter:description","content":"Google's natively multimodal embedding model â€” embed text, images, audio, video and PDF into one shared vector space. 68.16 MTEB, 8 task types, 100+ languages"}],["$","meta","9",{"name":"twitter:image","content":"https://www.segmind.com/og/home.jpg"}],["$","link","10",{"rel":"shortcut icon","href":"/favicon.ico"}],["$","link","11",{"rel":"icon","href":"/favicon.ico","sizes":"any"}],["$","link","12",{"rel":"icon","href":"/favicon-48x48.png","type":"image/png","sizes":"48x48"}],["$","link","13",{"rel":"icon","href":"/favicon-192x192.png","type":"image/png","sizes":"192x192"}],["$","link","14",{"rel":"icon","href":"/favicon.svg","type":"image/svg+xml"}],["$","link","15",{"rel":"apple-touch-icon","href":"/favicon-48x48.png"}],["$","$L2c","16",{}]],"error":null,"digest":"$undefined"}
27:"$23:metadata"
2b:["$","$L8",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$La",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","forbidden":"$undefined","unauthorized":"$undefined"}]
2e:I[68382,["6693","static/chunks/fba4ba2d-460e04194f22506f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3009","static/chunks/6a7d804d-a5cc510ceffe206f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7505","static/chunks/c02d83f4-5637599209ef9447.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6541","static/chunks/fb4e7fc9-e31ad622f5fde25d.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9761","static/chunks/998e86a0-e112630ec4db17dc.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9509","static/chunks/9509-6125acd3006111c1.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4378","static/chunks/4378-3f82908971052aa9.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5289","static/chunks/5289-131715863bbab062.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4094","static/chunks/4094-eaa6158623fe27ff.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4982","static/chunks/4982-a4b2ee93ffd82ffd.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1810","static/chunks/1810-cf4ca0391c1ddf2a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6118","static/chunks/6118-7328b7d3f629a5ef.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","7979","static/chunks/7979-1799576a8e82a4f3.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","393","static/chunks/393-7cd2157fc3790475.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3985","static/chunks/3985-1f9bcb95de313d61.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","2610","static/chunks/2610-c41f461a4ed7cf24.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4844","static/chunks/4844-011fe3465334e7d0.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9305","static/chunks/9305-0f5d0f2a661afddc.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","713","static/chunks/713-dcb3ca4f0233704d.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","3504","static/chunks/3504-ae9bc2dc93d2ef47.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1742","static/chunks/1742-0ea812562873537a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1172","static/chunks/1172-89020d82938322e4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9919","static/chunks/9919-b585857c6e10fb85.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","9326","static/chunks/9326-103822841b140d80.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1885","static/chunks/1885-f206f5873f09b3e2.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","4077","static/chunks/4077-cba4e88bdb106467.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5126","static/chunks/5126-bdde68ce894e4935.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","5642","static/chunks/5642-c80cb7ee6e914a6a.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1924","static/chunks/1924-8c4ee98e9b0dbf83.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","6372","static/chunks/6372-3e2880fc7d769d1f.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1289","static/chunks/1289-4fdf72847f7ef615.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","8382","static/chunks/8382-004a14550e3769cc.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x","1951","static/chunks/app/models/%5Broute%5D/page-c5fd4df0a8a5cab4.js?dpl=dpl_CPYCfxesaX7RKfJUQZpH2JDib41x"],"default",1]
2d:T7aa,{"@context":"https://schema.org","@type":"FAQPage","@id":"https://www.segmind.com/models/gemini-embedding-2#faq","mainEntity":[{"@type":"Question","name":"What is the difference between RETRIEVAL_QUERY and RETRIEVAL_DOCUMENT?","acceptedAnswer":{"@type":"Answer","text":"RETRIEVAL_QUERY embeds a user's question or search query; RETRIEVAL_DOCUMENT embeds the passages or documents in your index. Always use them as a matched pair â€” this asymmetric approach is how the model is optimised and produces the best recall."}},{"@type":"Question","name":"Can I mix task types when comparing vectors?","acceptedAnswer":{"@type":"Answer","text":"No. Cosine similarity is only meaningful between vectors produced with the same task type."}},{"@type":"Question","name":"How does output_dimensionality work?","acceptedAnswer":{"@type":"Answer","text":"The model produces a full-length vector and then truncates it to your specified size. A value of 768 is the recommended default. Smaller values (256, 512) reduce storage and query latency but may slightly lower retrieval accuracy."}},{"@type":"Question","name":"Is Gemini Embedding 2 better than OpenAI text-embedding-3-large?","acceptedAnswer":{"@type":"Answer","text":"On the MTEB leaderboard, Gemini Embedding 2 scores 68.16 vs. 64.6 for text-embedding-3-large. The quality gap is meaningful for multilingual workloads and code retrieval."}},{"@type":"Question","name":"What vector databases work with Gemini Embedding 2 embeddings?","acceptedAnswer":{"@type":"Answer","text":"Any database that accepts float arrays â€” Pinecone, Qdrant, Weaviate, Chroma, pgvector, Redis, Milvus. Set index dimensions to match your output_dimensionality setting (default: 768)."}},{"@type":"Question","name":"Does the model support batch input?","acceptedAnswer":{"@type":"Answer","text":"The Segmind API accepts a single string per request. For batch workloads, send concurrent requests or loop through your corpus sequentially."}}]}2f:T1265,# Gemini Embedding 2 â€” Text Embedding API

## What is Gemini Embedding 2?

Gemini Embedding 2 is Google's state-of-the-art text embedding model, built to convert natural language into dense numerical vectors that capture semantic meaning. With the top MTEB score of 68.16 â€” outperforming OpenAI text-embedding-3-large (64.6) and Cohere embed-v4 (65.2) â€” it delivers industry-leading retrieval and similarity accuracy across 100+ languages.

Via the Segmind API, you send a text string and receive a float vector ready for indexing in any vector database (Pinecone, Qdrant, Weaviate, pgvector). Eight task-specific modes let you tune the embedding direction to exactly match your use case â€” from document retrieval to code search to fact verification.

## Key Features

- **SOTA MTEB performance:** 68.16 overall; 84.0 on code retrieval; 69.9 on multilingual tasks
- **8 task types:** RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING, QUESTION_ANSWERING, FACT_VERIFICATION, CODE_RETRIEVAL_QUERY
- **Configurable dimensionality:** Output vectors from 256 to 768 dimensions â€” balance quality vs. storage cost
- **100+ language support:** Strong cross-lingual retrieval without translation preprocessing
- **Synchronous API:** Immediate JSON response with no polling required
- **Segmind infrastructure:** Low-latency, scalable endpoint â€” no GCP project or quota setup needed

## Best Use Cases

**Retrieval-Augmented Generation (RAG):** Use `RETRIEVAL_DOCUMENT` to embed your knowledge base and `RETRIEVAL_QUERY` for user questions. The asymmetric task pairing significantly improves precision over single-task embeddings.

**Semantic search:** Embed a product catalog, documentation site, or support knowledge base. Users get semantically relevant results even when they phrase queries differently from how the content was written.

**Classification and clustering:** Feed embeddings into a lightweight classifier or k-means cluster to categorize support tickets, content tags, or customer feedback without fine-tuning a full LLM.

**Code search:** `CODE_RETRIEVAL_QUERY` produces embeddings tuned for function signatures, docstrings, and code snippets â€” ideal for developer tools and IDE assistants.

**Multilingual pipelines:** With 69.9 MTEB multilingual score, a single index handles queries and documents in different languages without separate per-language models.

## Prompt Tips and Output Quality

- **Always pair task types correctly:** Index documents with `RETRIEVAL_DOCUMENT` and query with `RETRIEVAL_QUERY`. Mixing types degrades recall.
- **Chunk long documents:** Split text into 200â€“500 token segments before embedding. Each chunk should represent one coherent idea.
- **Dimensionality tradeoff:** 768 (default) gives optimal quality. Drop to 512 or 256 if your vector database costs or query latency are a concern â€” vectors are truncated, not re-encoded.
- **SEMANTIC_SIMILARITY is not for retrieval:** Use it only when comparing two texts directly (e.g., paraphrase detection, duplicate finding). It underperforms RETRIEVAL_* pairs in RAG pipelines.
- **Batch efficiently:** Embed multiple documents in sequence; the model is synchronous and fast enough for real-time pipelines at moderate scale.

## FAQs

**Q: What is the difference between RETRIEVAL_QUERY and RETRIEVAL_DOCUMENT?**
RETRIEVAL_QUERY embeds a user's question or search query; RETRIEVAL_DOCUMENT embeds the passages or documents in your index. Always use them as a matched pair â€” this asymmetric approach is how the model is optimised and produces the best recall.

**Q: Can I mix task types when comparing vectors?**
No. Cosine similarity is only meaningful between vectors produced with the same task type.

**Q: How does output_dimensionality work?**
The model produces a full-length vector and then truncates it to your specified size. A value of 768 is the recommended default. Smaller values (256, 512) reduce storage and query latency but may slightly lower retrieval accuracy.

**Q: Is Gemini Embedding 2 better than OpenAI text-embedding-3-large?**
On the MTEB leaderboard, Gemini Embedding 2 scores 68.16 vs. 64.6 for text-embedding-3-large. The quality gap is meaningful for multilingual workloads and code retrieval.

**Q: What vector databases work with Gemini Embedding 2 embeddings?**
Any database that accepts float arrays â€” Pinecone, Qdrant, Weaviate, Chroma, pgvector, Redis, Milvus. Set index dimensions to match your output_dimensionality setting (default: 768).

**Q: Does the model support batch input?**
The Segmind API accepts a single string per request. For batch workloads, send concurrent requests or loop through your corpus sequentially.30:T783,## How to Use Gemini Embedding 2

Gemini Embedding 2 converts text into dense vectors for search, classification, and similarity tasks. Here is how to get the best results.

### Choosing the Right Task Type

The `task_type` parameter is the most impactful setting. Match it to your use case:

| Use Case | task_type for Documents | task_type for Queries |
|---|---|---|
| RAG / document search | RETRIEVAL_DOCUMENT | RETRIEVAL_QUERY |
| Q&A over a knowledge base | RETRIEVAL_DOCUMENT | QUESTION_ANSWERING |
| Semantic similarity / dedup | SEMANTIC_SIMILARITY | SEMANTIC_SIMILARITY |
| Content classification | CLASSIFICATION | CLASSIFICATION |
| Clustering / topic modeling | CLUSTERING | CLUSTERING |
| Code search | RETRIEVAL_DOCUMENT | CODE_RETRIEVAL_QUERY |
| Claim / fact verification | RETRIEVAL_DOCUMENT | FACT_VERIFICATION |

### Recommended Settings

Based on real testing, these parameters produce reliable, high-quality embeddings:

```json
{
  "input": "Your document or query text here",
  "task_type": "RETRIEVAL_DOCUMENT",
  "output_dimensionality": 768
}
```

Use `output_dimensionality: 512` or `256` if you need to reduce storage costs or query latency.

### Indexing a Document Corpus

Embed each chunk with `RETRIEVAL_DOCUMENT`, then store the resulting vector alongside the chunk text in your vector database. At query time, embed the user's question with `RETRIEVAL_QUERY` and retrieve the closest vectors by cosine similarity.

### Tips for Better Results

- **Chunk documents** into 200â€“500 token segments. Each chunk should cover one topic.
- **Do not mix task types** on the same index â€” all stored vectors must use the same task type.
- **For multilingual corpora**, no preprocessing is needed. The model handles cross-lingual retrieval natively across 100+ languages.
- **For code search**, pair `CODE_RETRIEVAL_QUERY` queries against function/method text embedded with `RETRIEVAL_DOCUMENT`.1f:[["$","script",null,{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"{\"@context\":\"https://schema.org\",\"@type\":\"SoftwareApplication\",\"@id\":\"https://www.segmind.com/models/gemini-embedding-2\",\"name\":\"Gemini Embedding 2\",\"description\":\"Google's natively multimodal embedding model â€” embed text, images, audio, video and PDF into one shared vector space. 68.16 MTEB, 8 task types, 100+ languages\",\"url\":\"https://www.segmind.com/models/gemini-embedding-2\",\"applicationCategory\":\"AI Model\",\"applicationSubCategory\":\"textToEmbed\",\"operatingSystem\":\"Any\",\"image\":\"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-2-6042.webp\",\"offers\":{\"@type\":\"Offer\",\"availability\":\"https://schema.org/InStock\",\"priceCurrency\":\"USD\",\"price\":\"0.000025296795120061965\"},\"provider\":{\"@type\":\"Organization\",\"@id\":\"https://www.segmind.com/#organization\",\"name\":\"Segmind\",\"url\":\"https://www.segmind.com\",\"logo\":\"https://www.segmind.com/favicon.svg\"}}"}}],["$","script",null,{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"$2d"}}],null,["$","$L2e",null,{"route":"gemini-embedding-2","modelDetails":{"title":"Gemini Embedding 2","thumbnail_image":"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-2-6042.webp","type":"textToEmbed","model_type":"SG","is_depreciated":false,"meta_description":"Google's natively multimodal embedding model â€” embed text, images, audio, video and PDF into one shared vector space. 68.16 MTEB, 8 task types, 100+ languages, synchronous API.","seo_description":"$2f","guide":"$30","pricing_guide":null,"artifacts":"$1e:props:modelDetails:artifacts","default_image_output":"Gemini Embedding 2","default_response":null,"parameters":"$1e:props:modelDetails:parameters","endpoints":"$1e:props:modelDetails:endpoints","api_notes":"$1e:props:modelDetails:api_notes","model_outputs":null,"llm_capabilities":null,"license":null,"github_link":null,"inference_provider":"GEMINI","created_ts":"2026-05-03 20:03:40.213108+00:00","slug":"gemini-embedding-2","name":"Gemini Embedding 2","description":"Natively multimodal embeddings â€” text, image, audio, video and PDF mapped into one vector space, with 8 task-specific modes.","category":"textToEmbed","modality":"embed","input":"text","output":"embedding","provider":"GOOGLE","thumbnail_url":"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-2-6042.webp","is_new":false,"coming_soon":false,"popularity_score":83,"category_percentile":100,"average_cost":0.000025296795120061965,"latency_seconds":1.02839,"created_at":"2026-05-03 20:03:40.213108+00:00","parameters_schema":"$1e:props:modelDetails:parameters_schema"},"relatedTemplates":[],"popularModels":[{"slug":"gemini-embedding-001","title":"Gemini Embedding 001","description":"MTEB #1 text embeddings for RAG, search, and clustering.","type":"textToEmbed","partner":"GOOGLE","thumbnail_image":"https://segmind-resources.s3.amazonaws.com/output/gemini-embedding-001-5648.webp","default_image_output":"","is_new":false,"coming_soon":false,"is_visible":true,"segmind":true,"is_depreciated":false,"parameters":null,"latency":0.94589,"average_cost":0.00000355,"created_at":"2026-05-03 20:03:39.642015+00:00","popularity_score":0,"popularity_scale":"score","category_percentile":0},{"slug":"nano-banana-2.1","title":"Nano Banana 2.1","description":"Generate and edit images with legible text and infographics.","type":"imageToImage","partner":"GOOGLE","thumbnail_image":"https://segmind-resources.s3.amazonaws.com/output/nano-banana-2.1-8326.webp","default_image_output":"","is_new":true,"coming_soon":false,"is_visible":true,"segmind":true,"is_depreciated":false,"parameters":null,"latency":48.50829,"average_cost":0.10738071575738464,"created_at":"2026-10-06 17:22:47.588375+00:00","popularity_score":82,"popularity_scale":"score","category_percentile":96},{"slug":"nano-banana-2","title":"Nano Banana 2","description":"Fast photorealistic images â€” ideal for marketing and ads.","type":"imageToImage","partner":"GOOGLE","thumbnail_image":"https://segmind-resources.s3.amazonaws.com/output/nano-banana-2-6794.png","default_image_output":"","is_new":false,"coming_soon":false,"is_visible":true,"segmind":true,"is_depreciated":false,"parameters":null,"latency":24.19877,"average_cost":0.12625002308737496,"created_at":"2026-02-26 18:57:20.965623+00:00","popularity_score":95,"popularity_scale":"score","category_percentile":98},{"slug":"nano-banana-pro","title":"Nano Banana Pro","description":"High-fidelity images with accurate multilingual text rendering.","type":"imageToImage","partner":"GOOGLE","thumbnail_image":"https://segmind-resources.s3.amazonaws.com/output/nano-banana-pro-7992.png","default_image_output":"","is_new":false,"coming_soon":false,"is_visible":true,"segmind":true,"is_depreciated":false,"parameters":null,"latency":36.85706,"average_cost":0.16489339935294706,"created_at":"2025-11-20 06:04:51.464447+00:00","popularity_score":95,"popularity_scale":"score","category_percentile":99}]}]]
