--- title: Gemini 3.8 Flash now available on AI Gateway | daily.dev description: Google's Gemini 3.8 Flash model is now available through Vercel's AI Gateway, offering a 1M token context window, multimodal input (text, image, PDF, video),... canonical: https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Gemini 3.8 Flash now available on AI Gateway | daily.dev og:description: Google's Gemini 3.8 Flash model is now available through Vercel's AI Gateway, offering a 1M token context window, multimodal input (text, image, PDF, video),... og:url: https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj og:image: https://api.daily.dev/og/posts/0snitq5qJ.png og:image:alt: Gemini 3.8 Flash now available on AI Gateway og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 3.8 Flash now available on AI Gateway **[Vercel](https://daily.dev/sources/vercel)** · 1 min read · 1 upvotes · 0 comments ## Summary Google's Gemini 3.8 Flash model is now available through Vercel's AI Gateway, offering a 1M token context window, multimodal input (text, image, PDF, video), tool calling, and web search support with a 65,536 token max output. It's priced 50% off through December 31st and matches the previous Flash release's speed and cost while improving software engineering, agent work, and multi-step reasoning, with thinking enabled by default. Developers can access it via the model string 'google/gemini-3.8-flash' in the AI SDK, or configure it in coding agents like Claude Code, OpenCode, and Cursor using the Vercel CLI setup command. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I use Gemini 3.8 Flash through Vercel AI Gateway? Set the model parameter to google/gemini-3.8-flash in the AI SDK, for example using streamText with model: 'google/gemini-3.8-flash'. The model supports text, image, PDF, and video input, returns text, supports tool calling and web search, has a 1M token context window, and a 65,536 token max output, with thinking enabled by default. _Developers wiring new models into their stack track releases like this one on daily.dev._ ### What are the pricing and specs for Gemini 3.8 Flash on Vercel AI Gateway? Gemini 3.8 Flash is offered at 50% off through December 31st on Vercel AI Gateway, with pricing reflecting provider rates and no additional platform markup, even for Bring Your Own Key requests. It matches the speed and cost of the previous Flash release while improving on software engineering, agent work, and multi-step reasoning tasks. _Teams comparing model costs and capabilities can follow pricing changes like this via daily.dev._ ### How do I connect Gemini 3.8 Flash to a coding agent like Claude Code or Cursor? Run vercel ai-gateway coding-agents setup to connect supported coding agents such as Claude Code, OpenCode, Cursor, and Pi to Vercel AI Gateway, then select google/gemini-3.8-flash as the model inside the agent. A dedicated coding agents guide covers the full setup process. _Developers configuring coding agents with new models keep track of setups like this on daily.dev._ ## Similar posts on daily.dev - [Gemini 3.5 Flash on AI Gateway](https://daily.dev/posts/gemini-3-5-flash-on-ai-gateway-ik3r5yhkf) · Vercel · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#google-gemini](https://daily.dev/tags/google-gemini), [#ai-sdk](https://daily.dev/tags/ai-sdk) [View this post on daily.dev](https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Gemini 3.8 Flash now available on AI Gateway","url":"https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj"},"datePublished":"2026-09-02T16:11:01.513Z","dateModified":"2026-09-02T19:51:58.381Z","description":"Google's Gemini 3.8 Flash model is now available through Vercel's AI Gateway, offering a 1M token context window, multimodal input (text, image, PDF, video),...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f55977f0aa1a35e0d458e0cc8a16a6d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f55977f0aa1a35e0d458e0cc8a16a6d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Vercel","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Vercel","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/04cca7235cf84db092f24b7ba427b3e1","url":"https://daily.dev/sources/vercel"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,google-gemini,ai-sdk","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Vercel","item":"https://daily.dev/sources/vercel"},{"@type":"ListItem","position":3,"name":"Gemini 3.8 Flash now available on AI Gateway"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/gemini-3-8-flash-now-available-on-ai-gateway-0snitq5qj#faq","mainEntity":[{"@type":"Question","name":"How do I use Gemini 3.8 Flash through Vercel AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Set the model parameter to google/gemini-3.8-flash in the AI SDK, for example using streamText with model: 'google/gemini-3.8-flash'. The model supports text, image, PDF, and video input, returns text, supports tool calling and web search, has a 1M token context window, and a 65,536 token max output, with thinking enabled by default. Developers wiring new models into their stack track releases like this one on daily.dev."}},{"@type":"Question","name":"What are the pricing and specs for Gemini 3.8 Flash on Vercel AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.8 Flash is offered at 50% off through December 31st on Vercel AI Gateway, with pricing reflecting provider rates and no additional platform markup, even for Bring Your Own Key requests. It matches the speed and cost of the previous Flash release while improving on software engineering, agent work, and multi-step reasoning tasks. Teams comparing model costs and capabilities can follow pricing changes like this via daily.dev."}},{"@type":"Question","name":"How do I connect Gemini 3.8 Flash to a coding agent like Claude Code or Cursor?","acceptedAnswer":{"@type":"Answer","text":"Run vercel ai-gateway coding-agents setup to connect supported coding agents such as Claude Code, OpenCode, Cursor, and Pi to Vercel AI Gateway, then select google/gemini-3.8-flash as the model inside the agent. A dedicated coding agents guide covers the full setup process. Developers configuring coding agents with new models keep track of setups like this on daily.dev."}}]} ```