Google’s Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.
Google’s Gemini models in DeepMask are all from the Gemini 3 Flash family. They are built for speed and share a 1M-token context window, up to 65K tokens of output, image and document input, and tool use. The Flash models are the stronger generalists; the Flash Lite models trade some depth for speed and lower cost.
Model
Reasoning
Best for
Gemini 3.8 Flash
Built-in thinking
The newest Flash model, for most everyday and analytical tasks
Gemini 3.7 Flash
Built-in thinking
General work where you want a proven Flash model
Gemini 3.5 Flash
Standard
Fast answers without a thinking step
Gemini 3.5 Flash Lite
Built-in thinking
High-volume summarizing, extraction, and classification
Gemini 3.1 Flash Lite
Built-in thinking
The lightest option for simple, quick tasks
Gemini 3.8 Flash
Gemini 3.7 Flash
Gemini 3.5 Flash
Gemini 3.5 Flash Lite
Gemini 3.1 Flash Lite
About
Gemini 3.8 Flash is the newest Gemini model in DeepMask. Its 1M-token context window makes it a good fit for reading large document sets, long transcripts, or many images in one conversation.
Specifications
Specification
Value
Model provider
Google
Hosting
EU
Context window
1M tokens
Max output
65K tokens
Image input
Yes
Tool use
Yes
Reasoning
Built-in thinking
About
Gemini 3.7 Flash is the previous Flash release, with the same limits and capabilities as 3.8 Flash.
Specifications
Specification
Value
Model provider
Google
Hosting
EU
Context window
1M tokens
Max output
65K tokens
Image input
Yes
Tool use
Yes
Reasoning
Built-in thinking
About
Gemini 3.5 Flash answers directly, without a separate thinking step. Use it when response time matters more than deep reasoning.
Specifications
Specification
Value
Model provider
Google
Hosting
EU
Context window
1M tokens
Max output
65K tokens
Image input
Yes
Tool use
Yes
Reasoning
Standard
About
Gemini 3.5 Flash Lite is a lighter, more cost-efficient Flash model. It suits repetitive, high-volume work such as summarizing many files or pulling fields out of documents.
Specifications
Specification
Value
Model provider
Google
Hosting
EU
Context window
1M tokens
Max output
65K tokens
Image input
Yes
Tool use
Yes
Reasoning
Built-in thinking
About
Gemini 3.1 Flash Lite is the lightest Gemini model in DeepMask. Use it for short, simple tasks where speed and cost come first.
Specifications
Specification
Value
Model provider
Google
Hosting
EU
Context window
1M tokens
Max output
65K tokens
Image input
Yes
Tool use
Yes
Reasoning
Built-in thinking
Google’s open-weight Gemma models are covered on the Gemma page.
{"docsConfig":{"theme":"luma","$schema":"https://mintlify.com/docs.json","name":"DeepMask","colors":{"primary":"#139058","light":"#cecece","dark":"#252525"},"logo":{"light":"https://mintcdn.com/deepmaskgmbh/wqYs4HgxrHF-vtoI/images/light-theme-logo-B6Sj8q9n.svg?fit=max\u0026auto=format\u0026n=wqYs4HgxrHF-vtoI\u0026q=85\u0026s=b2e82def8bcaaf56f11738b4e22b9748","dark":"https://mintcdn.com/deepmaskgmbh/wqYs4HgxrHF-vtoI/images/dark-theme-logo--PYJYRlW.svg?fit=max\u0026auto=format\u0026n=wqYs4HgxrHF-vtoI\u0026q=85\u0026s=9aa25f507641b624ce8abc85888b8c16"},"favicon":{"light":"https://mintcdn.com/deepmaskgmbh/IMUyo8_jXysaqNdQ/images/Untitleddesign(30).png?fit=max\u0026auto=format\u0026n=IMUyo8_jXysaqNdQ\u0026q=85\u0026s=02005d43e5d29ab31e5fb0bc8f0175d7","dark":"https://mintcdn.com/deepmaskgmbh/IMUyo8_jXysaqNdQ/images/DeepMaskIcononly1025x1025_white.png?fit=max\u0026auto=format\u0026n=IMUyo8_jXysaqNdQ\u0026q=85\u0026s=ab8caac67616c37907783c84cd4cb817"},"navbar":{"primary":{"type":"button","label":"Try DeepMask","href":"https://chat.deepmask.io/"}},"fonts":{"family":"Open Sans"},"styling":{"latex":false},"navigation":{"languages":[{"language":"en","href":"introduction"},{"language":"de","href":"de/introduction"}]}},"deployment":{"deploymentMetadataValue":{"subdomain":"deepmaskgmbh","hasAudioNarration":false,"actualSubdomain":"deepmaskgmbh","customDomains":["documentation.deepmask.io"],"gitSource":{"type":"github","owner":"musmani22","repo":"docs","deployBranch":"main","contentDirectory":"","isPrivate":true,"mountPath":"","label":""},"entitlements":{"AI_CHAT":{"status":"DISABLED"}},"buildId":"6afb564be59e7a15fc0aa49f","clientVersion":"0.0.4227","searchFilterCounts":[{"language":"en","tag":"Documentation","count":67},{"language":"de","tag":"Dokumentation","count":67},{"language":"en","tag":"Connectors","count":44},{"language":"de","tag":"Konnektoren","count":44},{"language":"en","tag":"Models","count":24},{"language":"de","tag":"Modelle","count":24},{"language":"en","tag":"Outlook","count":16},{"language":"de","tag":"Outlook","count":16},{"language":"en","tag":"API","count":10},{"language":"en","tag":"SharePoint (Enterprise)","count":10},{"language":"de","tag":"API","count":10},{"language":"de","tag":"SharePoint (Enterprise)","count":10},{"language":"en","tag":"Salesforce (Enterprise)","count":9},{"language":"en","tag":"Google \u0026 Others","count":9},{"language":"de","tag":"Salesforce (Enterprise)","count":9},{"language":"de","tag":"Google \u0026 andere","count":9},{"language":"en","tag":"OneDrive (Personal)","count":8},{"language":"de","tag":"OneDrive (Persönlich)","count":8},{"language":"en","tag":"Core Features","count":7},{"language":"de","tag":"Kernfunktionen","count":7}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableContextualStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[],"googleFontsInlined":true},"customCss":[]}
{"page":{"pagePath":"models/gemini","slug":"/models/gemini","pageMetadata":{"title":"Gemini 3 Flash family","sidebarTitle":"Gemini","description":"Google's Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.","href":"/models/gemini"},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsx(_components.p, {\n children: \"Google’s Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.\"\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={a:`a`,p:`p`,strong:`strong`,tbody:`tbody`,td:`td`,th:`th`,thead:`thead`,tr:`tr`,..._provideComponents(),...props.components},{Heading,Info,Tab,Table,Tabs}=_components;if(!Heading)_missingMdxReference(`Heading`,true);if(!Info)_missingMdxReference(`Info`,true);if(!Tab)_missingMdxReference(`Tab`,true);if(!Table)_missingMdxReference(`Table`,true);if(!Tabs)_missingMdxReference(`Tabs`,true);return _jsxs(_Fragment,{children:[_jsx(_components.p,{children:`Google’s Gemini models in DeepMask are all from the Gemini 3 Flash family. They are built for speed and share a 1M-token context window, up to 65K tokens of output, image and document input, and tool use. The Flash models are the stronger generalists; the Flash Lite models trade some depth for speed and lower cost.`}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Model`}),_jsx(_components.th,{children:`Reasoning`}),_jsx(_components.th,{children:`Best for`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Gemini 3.8 Flash`})}),_jsx(_components.td,{children:`Built-in thinking`}),_jsx(_components.td,{children:`The newest Flash model, for most everyday and analytical tasks`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Gemini 3.7 Flash`})}),_jsx(_components.td,{children:`Built-in thinking`}),_jsx(_components.td,{children:`General work where you want a proven Flash model`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Gemini 3.5 Flash`})}),_jsx(_components.td,{children:`Standard`}),_jsx(_components.td,{children:`Fast answers without a thinking step`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Gemini 3.5 Flash Lite`})}),_jsx(_components.td,{children:`Built-in thinking`}),_jsx(_components.td,{children:`High-volume summarizing, extraction, and classification`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:_jsx(_components.strong,{children:`Gemini 3.1 Flash Lite`})}),_jsx(_components.td,{children:`Built-in thinking`}),_jsx(_components.td,{children:`The lightest option for simple, quick tasks`})]})]})]}),`\n`,_jsxs(Tabs,{children:[_jsxs(Tab,{title:`Gemini 3.8 Flash`,id:`gemini-3-8-flash`,\"data-child-heading-ids\":`[\"about\",\"specifications\"]`,children:[_jsx(Heading,{level:`2`,id:`about`,children:`About`}),_jsx(_components.p,{children:`Gemini 3.8 Flash is the newest Gemini model in DeepMask. Its 1M-token context window makes it a good fit for reading large document sets, long transcripts, or many images in one conversation.`}),_jsx(Heading,{level:`2`,id:`specifications`,children:`Specifications`}),_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Specification`}),_jsx(_components.th,{children:`Value`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Model provider`}),_jsx(_components.td,{children:`Google`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Hosting`}),_jsx(_components.td,{children:`EU`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Context window`}),_jsx(_components.td,{children:`1M tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Max output`}),_jsx(_components.td,{children:`65K tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Image input`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Tool use`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Reasoning`}),_jsx(_components.td,{children:`Built-in thinking`})]})]})]})]}),_jsxs(Tab,{title:`Gemini 3.7 Flash`,id:`gemini-3-7-flash`,\"data-child-heading-ids\":`[\"about-2\",\"specifications-2\"]`,children:[_jsx(Heading,{level:`2`,id:`about-2`,children:`About`}),_jsx(_components.p,{children:`Gemini 3.7 Flash is the previous Flash release, with the same limits and capabilities as 3.8 Flash.`}),_jsx(Heading,{level:`2`,id:`specifications-2`,children:`Specifications`}),_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Specification`}),_jsx(_components.th,{children:`Value`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Model provider`}),_jsx(_components.td,{children:`Google`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Hosting`}),_jsx(_components.td,{children:`EU`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Context window`}),_jsx(_components.td,{children:`1M tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Max output`}),_jsx(_components.td,{children:`65K tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Image input`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Tool use`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Reasoning`}),_jsx(_components.td,{children:`Built-in thinking`})]})]})]})]}),_jsxs(Tab,{title:`Gemini 3.5 Flash`,id:`gemini-3-5-flash`,\"data-child-heading-ids\":`[\"about-3\",\"specifications-3\"]`,children:[_jsx(Heading,{level:`2`,id:`about-3`,children:`About`}),_jsx(_components.p,{children:`Gemini 3.5 Flash answers directly, without a separate thinking step. Use it when response time matters more than deep reasoning.`}),_jsx(Heading,{level:`2`,id:`specifications-3`,children:`Specifications`}),_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Specification`}),_jsx(_components.th,{children:`Value`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Model provider`}),_jsx(_components.td,{children:`Google`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Hosting`}),_jsx(_components.td,{children:`EU`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Context window`}),_jsx(_components.td,{children:`1M tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Max output`}),_jsx(_components.td,{children:`65K tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Image input`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Tool use`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Reasoning`}),_jsx(_components.td,{children:`Standard`})]})]})]})]}),_jsxs(Tab,{title:`Gemini 3.5 Flash Lite`,id:`gemini-3-5-flash-lite`,\"data-child-heading-ids\":`[\"about-4\",\"specifications-4\"]`,children:[_jsx(Heading,{level:`2`,id:`about-4`,children:`About`}),_jsx(_components.p,{children:`Gemini 3.5 Flash Lite is a lighter, more cost-efficient Flash model. It suits repetitive, high-volume work such as summarizing many files or pulling fields out of documents.`}),_jsx(Heading,{level:`2`,id:`specifications-4`,children:`Specifications`}),_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Specification`}),_jsx(_components.th,{children:`Value`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Model provider`}),_jsx(_components.td,{children:`Google`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Hosting`}),_jsx(_components.td,{children:`EU`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Context window`}),_jsx(_components.td,{children:`1M tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Max output`}),_jsx(_components.td,{children:`65K tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Image input`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Tool use`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Reasoning`}),_jsx(_components.td,{children:`Built-in thinking`})]})]})]})]}),_jsxs(Tab,{title:`Gemini 3.1 Flash Lite`,id:`gemini-3-1-flash-lite`,\"data-child-heading-ids\":`[\"about-5\",\"specifications-5\"]`,children:[_jsx(Heading,{level:`2`,id:`about-5`,children:`About`}),_jsx(_components.p,{children:`Gemini 3.1 Flash Lite is the lightest Gemini model in DeepMask. Use it for short, simple tasks where speed and cost come first.`}),_jsx(Heading,{level:`2`,id:`specifications-5`,children:`Specifications`}),_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Specification`}),_jsx(_components.th,{children:`Value`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Model provider`}),_jsx(_components.td,{children:`Google`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Hosting`}),_jsx(_components.td,{children:`EU`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Context window`}),_jsx(_components.td,{children:`1M tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Max output`}),_jsx(_components.td,{children:`65K tokens`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Image input`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Tool use`}),_jsx(_components.td,{children:`Yes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`Reasoning`}),_jsx(_components.td,{children:`Built-in thinking`})]})]})]})]})]}),`\n`,_jsx(Info,{children:_jsxs(_components.p,{children:[`Google’s open-weight Gemma models are covered on the `,_jsx(_components.a,{href:`/models/gemma`,children:`Gemma`}),` page.`]})}),`\n`,_jsx(_components.p,{children:_jsx(_components.a,{href:`https://chat.deepmask.io/`,children:`Try Gemini in DeepMask →`})})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Gemini 3 Flash family","sidebarTitle":"Gemini","description":"Google's Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.","href":"/models/gemini"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"About","slug":"about","depth":2,"children":[],"tabId":"gemini-3-8-flash"},{"title":"Specifications","slug":"specifications","depth":2,"children":[],"tabId":"gemini-3-8-flash"},{"title":"About","slug":"about-2","depth":2,"children":[],"tabId":"gemini-3-7-flash"},{"title":"Specifications","slug":"specifications-2","depth":2,"children":[],"tabId":"gemini-3-7-flash"},{"title":"About","slug":"about-3","depth":2,"children":[],"tabId":"gemini-3-5-flash"},{"title":"Specifications","slug":"specifications-3","depth":2,"children":[],"tabId":"gemini-3-5-flash"},{"title":"About","slug":"about-4","depth":2,"children":[],"tabId":"gemini-3-5-flash-lite"},{"title":"Specifications","slug":"specifications-4","depth":2,"children":[],"tabId":"gemini-3-5-flash-lite"},{"title":"About","slug":"about-5","depth":2,"children":[],"tabId":"gemini-3-1-flash-lite"},{"title":"Specifications","slug":"specifications-5","depth":2,"children":[],"tabId":"gemini-3-1-flash-lite"}],"codeExamples":{}},"jsLinks":[],"subdomain":"deepmaskgmbh","siteName":"DeepMask","title":"Gemini 3 Flash family - DeepMask","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{"en":{"href":"/models/gemini","matchLevel":0},"de":{"href":"/de/models/gemini","matchLevel":1}}},"lastModified":"2026-11-16T19:15:27.990Z","originalFileLocation":"models/gemini.mdx","locale":"en"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Google\u0026#x27;s Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.\">\u003cmeta data-mint-head name=\"application-name\" content=\"DeepMask\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Gemini 3 Flash family - DeepMask\">\u003cmeta data-mint-head property=\"og:description\" content=\"Google\u0026#x27;s Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"DeepMask\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://documentation.deepmask.io/models/gemini\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://deepmaskgmbh.mintlify.site/_mintlify/api/og/v2?division=Google+%26+Others\u0026amp;title=Gemini+3+Flash+family\u0026amp;description=Google%27s+Gemini+3+models+in+DeepMask%3A+Gemini+3.8%2C+3.7%2C+and+3.5+Flash+and+the+Flash+Lite+models%2C+all+with+a+1M-token+context+window%2C+image+input%2C+and+tool+use.\u0026amp;theme=e567b27b7b33e40a3da35b7a\u0026amp;signature=a3e9bf1605bb9f81008b4c7a5a3ca564c396e13c58c6f6ff3125461173f45f28\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Gemini 3 Flash family - DeepMask\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Google\u0026#x27;s Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://deepmaskgmbh.mintlify.site/_mintlify/api/og/v2?division=Google+%26+Others\u0026amp;title=Gemini+3+Flash+family\u0026amp;description=Google%27s+Gemini+3+models+in+DeepMask%3A+Gemini+3.8%2C+3.7%2C+and+3.5+Flash+and+the+Flash+Lite+models%2C+all+with+a+1M-token+context+window%2C+image+input%2C+and+tool+use.\u0026amp;theme=e567b27b7b33e40a3da35b7a\u0026amp;signature=a3e9bf1605bb9f81008b4c7a5a3ca564c396e13c58c6f6ff3125461173f45f28\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/deepmaskgmbh/hwlc6glwRXpXRbmg/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"DeepMask\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#139058\">\u003clink data-mint-head rel=\"canonical\" href=\"https://documentation.deepmask.io/models/gemini\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/models/gemini.md\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"en\" href=\"https://documentation.deepmask.io/models/gemini\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"de\" href=\"https://documentation.deepmask.io/de/models/gemini\">\u003clink data-mint-head rel=\"alternate\" hreflang=\"x-default\" href=\"https://documentation.deepmask.io/models/gemini\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://documentation.deepmask.io/#organization\",\"name\":\"DeepMask\",\"url\":\"https://documentation.deepmask.io\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/deepmaskgmbh/wqYs4HgxrHF-vtoI/images/light-theme-logo-B6Sj8q9n.svg?fit=max\u0026auto=format\u0026n=wqYs4HgxrHF-vtoI\u0026q=85\u0026s=b2e82def8bcaaf56f11738b4e22b9748\"}},{\"@type\":\"WebSite\",\"@id\":\"https://documentation.deepmask.io#website\",\"name\":\"DeepMask\",\"url\":\"https://documentation.deepmask.io\",\"publisher\":{\"@id\":\"https://documentation.deepmask.io/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://documentation.deepmask.io/models/gemini#webpage\",\"url\":\"https://documentation.deepmask.io/models/gemini\",\"name\":\"Gemini 3 Flash family\",\"description\":\"Google's Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.\",\"dateModified\":\"2026-11-16T19:15:27.990Z\",\"isPartOf\":{\"@id\":\"https://documentation.deepmask.io#website\"},\"breadcrumb\":{\"@id\":\"https://documentation.deepmask.io/models/gemini#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://documentation.deepmask.io/models/gemini#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"DeepMask\",\"item\":\"https://documentation.deepmask.io\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Gemini 3 Flash family\",\"item\":\"https://documentation.deepmask.io/models/gemini\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://documentation.deepmask.io/models/gemini#article\",\"headline\":\"Gemini 3 Flash family\",\"name\":\"Gemini 3 Flash family\",\"description\":\"Google's Gemini 3 models in DeepMask: Gemini 3.8, 3.7, and 3.5 Flash and the Flash Lite models, all with a 1M-token context window, image input, and tool use.\",\"url\":\"https://documentation.deepmask.io/models/gemini\",\"mainEntityOfPage\":{\"@id\":\"https://documentation.deepmask.io/models/gemini#webpage\"},\"dateModified\":\"2026-11-16T19:15:27.990Z\",\"publisher\":{\"@id\":\"https://documentation.deepmask.io/#organization\"},\"isPartOf\":{\"@id\":\"https://documentation.deepmask.io#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"DeepMask\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"DeepMask\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/models/gemini.md","siteName":"DeepMask","nav":{"global":null,"languages":[{"language":"en","tabs":[{"tab":"Documentation","pages":[{"title":"Documentation","href":"/introduction"}]},{"tab":"Models","groups":[{"group":"Model Guide","pages":[{"title":"AI Models","href":"/models/overview"},{"title":"Choosing the right model","sidebarTitle":"Choosing a model","href":"/models/choosing-a-model"},{"title":"DeepMask D1 \u0026 D2","sidebarTitle":"DeepMask D1 \u0026 D2","href":"/models/deepmask"}]},{"group":"OpenAI","pages":[{"title":"GPT-6 Series","sidebarTitle":"GPT-6 Series","href":"/models/gpt-6"},{"title":"GPT-5 Series","href":"/models/gpt-5"},{"title":"GPT-4o","href":"/models/gpt-4o"},{"title":"GPT-4.1 ","href":"/models/gpt-4-1"},{"title":"GPT-o3 Mini","href":"/models/gpt-o3-mini"},{"title":"GPT-OSS 120B","href":"/models/gpt-oss-120b"}]},{"group":"Anthropic","pages":[{"title":"Opus 5.5, Sonnet 5.5 \u0026 Haiku 5.5","sidebarTitle":"Claude 5.5 family","href":"/models/claude-5-5"},{"title":"Opus 5","href":"/models/opus-5"},{"title":"Opus (4.8, 4.7, 4.6, 4.5)","href":"/models/opus"},{"title":"Sonnet 5","href":"/models/sonnet-5"},{"title":"Sonnet (4.6, 4.5)","href":"/models/sonnet"},{"title":"Haiku 4.5","description":"Claude Haiku 4.5 by Anthropic — fastest Anthropic model. 200K context, GPQA 73.2%, 0.20s TTFT, 180+ tok/s. Ideal for high-volume tasks and real-time agents.","href":"/models/haiku"}]},{"group":"Google \u0026 Others","pages":[{"title":"Gemini 3 Flash family","sidebarTitle":"Gemini","href":"/models/gemini"},{"title":"Gemma","sidebarTitle":"Gemma","description":"Google's open-weight Gemma models in DeepMask, hosted in Germany: Gemma 4 31B with tool use, and Gemma 3 27B on StackIT, both with image input.","href":"/models/gemma"},{"title":"DeepSeek","sidebarTitle":"DeepSeek","href":"/models/deepseek"},{"title":"Mistral Large 3","href":"/models/mistral"},{"title":"Kimi","href":"/models/kimi-k2"},{"title":"Qwen","sidebarTitle":"Qwen","href":"/models/qwen"},{"title":"MiniMax M3, M2.5 \u0026 M2.1","href":"/models/minimax"},{"title":"GLM","href":"/models/glm"},{"title":"Nemotron 3 Super","sidebarTitle":"Nemotron","href":"/models/nemotron"}]}]},{"tab":"API","pages":[{"title":"API","href":"/api/overview"}]}]},{"language":"de","pages":[{"title":"de","href":"/de/models/gemini"}]}]},"basePath":"","title":"Gemini 3 Flash family - DeepMask","deploymentId":"dpl_vSEmv961Ncyvz1psVwgUnTXQMSYk","buildId":"dpl_vSEmv961Ncyvz1psVwgUnTXQMSYk","dynamics":[],"chunks":[]}