[{"data":1,"prerenderedAt":75},["ShallowReactive",2],{"help-article-byok-why-we-do-this":3},{"data":4},{"title":5,"excerpt":6,"content":7,"help_category":8,"seo":11},"Why m18t uses BYOK","BYOK means you bring your own keys: m18t routes AI, social, and CMS calls through your credentials at the provider's rate with no markup, no token resale, no","\u003Cp>\u003Cstrong>What you'll learn\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>What "bring your own key" (BYOK) means, and why m18t routes AI, social, and CMS calls through \u003Cem>your\u003C\u002Fem> credentials instead of bundling its own.\u003C\u002Fli>\n\u003Cli>The cost difference between a bundled-token SaaS and BYOK — who pays whom, and where markup hides.\u003C\u002Fli>\n\u003Cli>Where your keys go once you hand them over: the encrypted \u003Ca href=\"\u002Fhelp\u002Fthe-secret-vault\">Vault\u003C\u002Fa>.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Chr>\n\u003Ch2>The short version\u003C\u002Fh2>\n\u003Cp>m18t does not sell you AI tokens. It does not sell you social-publishing access. It does not resell CMS hosting. You bring your own keys from the providers you already use — OpenAI, Google (Gemini), Anthropic, Meta, your Strapi instance — and m18t makes the API calls on your behalf using \u003Cem>your\u003C\u002Fem> credentials.\u003C\u002Fp>\n\u003Cp>You pay each provider directly, at their published rate. m18t adds nothing to that bill. During beta, m18t itself is free to use — and that's not a promotion that expires into a markup later, it's a consequence of the architecture: there's no pooled token cost for m18t to recover.\u003C\u002Fp>\n\u003Cp>If you've used PostHog or a self-hostable tool before, the mental model is familiar: the tool is the workspace; the expensive third-party services stay in \u003Cem>your\u003C\u002Fem> account, on \u003Cem>your\u003C\u002Fem> terms.\u003C\u002Fp>\n\u003Ch2>A few terms, defined once\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>API\u003C\u002Fstrong> — the channel one server uses to talk to another. When m18t publishes a post to a Facebook Page or asks an AI model to draft copy, it sends a request over that provider's API.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>API key\u003C\u002Fstrong> — the credential that proves a request is authorized by your account. It's the thing you generate in a provider's dashboard and paste into m18t.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Token\u003C\u002Fstrong> (AI billing unit) — AI providers bill per token, roughly a few characters of text. You pay for the tokens you send (your prompt) and the tokens the model sends back (its answer). Image models bill per image instead. The point: the meter runs in \u003Cem>your\u003C\u002Fem> provider account, and you can watch it there.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>The bundled-SaaS model, and where it pinches\u003C\u002Fh2>\n\u003Cp>Most AI-flavoured SaaS tools bundle the cost. You pay a flat monthly fee and get "AI features" or a quota of generations. Under the hood, the platform buys tokens in bulk and resells them to you inside the subscription. That arrangement creates three structural frictions:\u003C\u002Fp>\n\u003Col>\n\u003Cli>\u003Cstrong>Markup.\u003C\u002Fstrong> The platform has to protect a margin on compute it bought wholesale. You pay above the raw provider rate, whether you use the AI heavily or barely touch it.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Artificial quotas.\u003C\u002Fstrong> To stop heavy users from eroding that margin, the platform caps usage — "200 generations a month," "AI credits," and so on. The cap exists to protect the platform's economics, not yours.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Vendor lag.\u003C\u002Fstrong> When a provider ships a new model, you wait for the platform to negotiate pricing and wire it in before you can use it.\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cp>None of those are villainy — they're what bundling \u003Cem>requires\u003C\u002Fem>. They're just costs you may not want to carry.\u003C\u002Fp>\n\u003Ch2>What BYOK changes\u003C\u002Fh2>\n\u003Cp>Under BYOK, the billing relationship is between you and the provider. m18t is the workspace that orchestrates the calls; it is removed from the money.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>No markup.\u003C\u002Fstrong> You pay OpenAI, Google, or Anthropic exactly their rate. m18t adds zero.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Your usage, your dashboard.\u003C\u002Fstrong> Every token you spend shows up in your provider's own console. You set the spending caps there.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>No platform quota on AI.\u003C\u002Fstrong> As long as your provider account is funded, m18t doesn't impose an artificial limit on how many drafts or images you generate. (Plan-level limits on \u003Cem>brands\u003C\u002Fem> and \u003Cem>connections\u003C\u002Fem> are a separate thing — that's m18t's own pricing axis, not an AI tax.)\u003C\u002Fli>\n\u003Cli>\u003Cstrong>New models when the provider ships them.\u003C\u002Fstrong> Because you point at the provider directly, you're not waiting on a middleman to resell the latest model.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>The honest trade-off: BYOK means setup. You have to create accounts and generate keys before the AI buttons light up — and until a key is in the Vault, AI features stay disabled with a tooltip telling you why. That's a real first-run cost. We think transparent pricing and direct control are worth it, and the setup is one-time per provider. The how-to guides (\u003Ca href=\"\u002Fhelp\u002Fget-an-openai-key\">OpenAI\u003C\u002Fa>, \u003Ca href=\"\u002Fhelp\u002Fget-a-gemini-key\">Gemini\u003C\u002Fa>, \u003Ca href=\"\u002Fhelp\u002Fget-an-anthropic-key\">Anthropic\u003C\u002Fa>) walk each one.\u003C\u002Fp>\n\u003Ch2>Where your keys live\u003C\u002Fh2>\n\u003Cp>Handing credentials to any tool deserves scrutiny. In m18t, keys don't sit in plain text. When you save one, it's encrypted at rest with AES-256-GCM in your workspace's \u003Ca href=\"\u002Fhelp\u002Fthe-secret-vault\">Vault\u003C\u002Fa>, referenced afterward by name rather than by value. The full mechanism — encryption, runtime resolution, rotation — is its own article.\u003C\u002Fp>\n\u003Cp>BYOK also fits m18t's shape: it's \u003Ca href=\"\u002Fhelp\u002Fper-brand-integrations\">multi-brand\u003C\u002Fa>. Each brand can carry its own keys, or several brands can share one. You decide which, per brand.\u003C\u002Fp>\n\u003Ch2>FAQ\u003C\u002Fh2>\n\u003Cp>\u003Cstrong>Does m18t make money on my AI usage?\u003C\u002Fstrong>\nNo. There's no markup. You pay the provider; m18t isn't in that transaction. m18t's eventual pricing is built on a different axis (brands and connections per account), not on reselling tokens.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Why is the AI button greyed out \u002F disabled?\u003C\u002Fstrong>\nBecause no AI key is configured for the active brand. AI features stay disabled, with a tooltip, until a provider key is in the \u003Ca href=\"\u002Fhelp\u002Fthe-secret-vault\">Vault\u003C\u002Fa> and wired to a connection. Add one via the \u003Ca href=\"\u002Fhelp\u002Fget-an-openai-key\">OpenAI\u003C\u002Fa>, \u003Ca href=\"\u002Fhelp\u002Fget-a-gemini-key\">Gemini\u003C\u002Fa>, or \u003Ca href=\"\u002Fhelp\u002Fget-an-anthropic-key\">Anthropic\u003C\u002Fa> guide.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Which provider should I start with?\u003C\u002Fstrong>\nAny of the three supported text providers works. Gemini carries a "Recommended" badge in the connection picker for fast, low-cost text work; pick whichever you already have an account with. You can wire more than one and choose per use case.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Is it really free during beta?\u003C\u002Fstrong>\nThe m18t workspace is free during beta. Your provider bills (OpenAI, Meta, etc.) are separate and always yours — that doesn't change when beta ends.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>What if I don't want to use any AI?\u003C\u002Fstrong>\nThen you don't need AI keys at all. The AI-driven surfaces stay disabled and the rest of m18t — content, publishing, \u003Ca href=\"\u002Fhelp\u002Fconnect-strapi\">CMS push\u003C\u002Fa>, assets — works without them.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>What's next\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Understand the storage layer: \u003Ca href=\"\u002Fhelp\u002Fthe-secret-vault\">The Secret Vault\u003C\u002Fa>.\u003C\u002Fli>\n\u003Cli>Get your first key: \u003Ca href=\"\u002Fhelp\u002Fget-an-openai-key\">Get an OpenAI API Key\u003C\u002Fa>, \u003Ca href=\"\u002Fhelp\u002Fget-a-gemini-key\">Get a Gemini API Key\u003C\u002Fa>, or \u003Ca href=\"\u002Fhelp\u002Fget-an-anthropic-key\">Get an Anthropic API Key\u003C\u002Fa>.\u003C\u002Fli>\n\u003Cli>See how keys map across brands: \u003Ca href=\"\u002Fhelp\u002Fper-brand-integrations\">Per-Brand Integrations\u003C\u002Fa>.\u003C\u002Fli>\n\u003Cli>If you run an \u003Ca href=\"\u002Ffor\u002Fagencies\">agency\u003C\u002Fa>, BYOK is how you bill clients cleanly — their keys, their invoices.\u003C\u002Fli>\n\u003C\u002Ful>\n",{"slug":9,"title":10},"connections-and-keys","Connections & API Keys",{"meta_title":12,"meta_description":6,"keywords":13,"canonical_url":14,"og_title":5,"og_description":15,"og_image":16,"robots":17,"json_ld":18},"Why m18t uses BYOK | m18t Help","BYOK, bring your own key, no markup, provider billing, AI tokens, api key, m18t pricing model","https:\u002F\u002Fm18t.com\u002Fhelp\u002Fbyok-why-we-do-this","You bring your own keys and pay providers directly — m18t adds no markup and imposes no AI quota. Here's why.","https:\u002F\u002Fm18t.com\u002Fog-default.png","index, follow",{"@context":19,"@graph":20},"https:\u002F\u002Fschema.org",[21,34,59],{"@type":22,"headline":5,"description":6,"articleSection":10,"inLanguage":23,"datePublished":24,"dateModified":24,"image":16,"author":25,"publisher":29,"mainEntityOfPage":32},"Article","en","2026-06-25",{"@type":26,"name":27,"url":28},"Organization","m18t","https:\u002F\u002Fm18t.com",{"@type":26,"name":27,"url":28,"logo":30},{"@type":31,"url":16},"ImageObject",{"@type":33,"@id":14},"WebPage",{"@type":35,"mainEntity":36},"FAQPage",[37,43,47,51,55],{"@type":38,"name":39,"acceptedAnswer":40},"Question","Does m18t make money on my AI usage?",{"@type":41,"text":42},"Answer","No. There's no markup. You pay the provider; m18t isn't in that transaction. m18t's eventual pricing is built on a different axis (brands and connections per account), not on reselling tokens.",{"@type":38,"name":44,"acceptedAnswer":45},"Why is the AI button greyed out \u002F disabled?",{"@type":41,"text":46},"Because no AI key is configured for the active brand. AI features stay disabled, with a tooltip, until a provider key is in the Vault and wired to a connection. Add one via the OpenAI, Gemini, or Anthropic guide.",{"@type":38,"name":48,"acceptedAnswer":49},"Which provider should I start with?",{"@type":41,"text":50},"Any of the three supported text providers works. Gemini carries a Recommended badge in the connection picker for fast, low-cost text work; pick whichever you already have an account with. You can wire more than one and choose per use case.",{"@type":38,"name":52,"acceptedAnswer":53},"Is it really free during beta?",{"@type":41,"text":54},"The m18t workspace is free during beta. Your provider bills (OpenAI, Meta, etc.) are separate and always yours — that doesn't change when beta ends.",{"@type":38,"name":56,"acceptedAnswer":57},"What if I don't want to use any AI?",{"@type":41,"text":58},"Then you don't need AI keys at all. The AI-driven surfaces stay disabled and the rest of m18t — content, publishing, CMS push, assets — works without them.",{"@type":60,"itemListElement":61},"BreadcrumbList",[62,66,70,73],{"@type":63,"position":64,"name":65,"item":28},"ListItem",1,"Home",{"@type":63,"position":67,"name":68,"item":69},2,"Help","https:\u002F\u002Fm18t.com\u002Fhelp",{"@type":63,"position":71,"name":10,"item":72},3,"https:\u002F\u002Fm18t.com\u002Fhelp\u002Fcategories\u002Fconnections-and-keys",{"@type":63,"position":74,"name":5,"item":14},4,1786312168923]