[{"data":1,"prerenderedAt":46},["ShallowReactive",2],{"blog-post-one-token-per-teammate":3,"blog-index":16},{"slug":4,"title":5,"excerpt":6,"author":7,"authorBio":8,"publishedAt":9,"readMinutes":10,"tags":11,"coverImage":14,"body":15},"one-token-per-teammate","One token per teammate: share a local model safely","Passing around one API key works until it leaks or someone runs a job all night. Per-user tokens make a shared model safe to hand out.","The Tokmine team","We build Tokmine, a traffic manager for local AI models.","2026-09-30T09:00:00.000Z",4,[12,13],"Teams","Security","\u002Fblog\u002Fone-token-per-teammate.svg","\n      \u003Cp class=\"lead\">The moment a second person uses your local model, you have an access-control problem. Most setups solve it by pasting the same key into a chat.\u003C\u002Fp>\n\n      \u003Ch2>Why a shared key goes wrong\u003C\u002Fh2>\n      \u003Cp>One key for everyone means you cannot tell who is calling, you cannot cut off one person without cutting off all of them, and a leak means rotating the key for the whole team. When a job hammers the model at 3 a.m., nobody knows whose it was.\u003C\u002Fp>\n\n      \u003Ch2>Give each person their own token\u003C\u002Fh2>\n      \u003Cp>With Tokmine, every request needs a consumer token, and there are no open endpoints. Signed-in callers use their own account token, so usage is attributable to a person. Tokens are stored hashed, shown once, compared in constant time and never logged.\u003C\u002Fp>\n\n      \u003Ch2>What you get\u003C\u002Fh2>\n      \u003Cul>\n        \u003Cli>\u003Cstrong>Attribution.\u003C\u002Fstrong> Usage counts per day, on your dashboard.\u003C\u002Fli>\n        \u003Cli>\u003Cstrong>Revocation.\u003C\u002Fstrong> Remove one person without touching anyone else.\u003C\u002Fli>\n        \u003Cli>\u003Cstrong>Smaller blast radius.\u003C\u002Fstrong> A leaked token is one person's problem.\u003C\u002Fli>\n      \u003C\u002Ful>\n\n      \u003Ch2>Nothing extra exposed\u003C\u002Fh2>\n      \u003Cp>The CLI opens an outbound connection, so your machine accepts no inbound traffic from the internet. Callers cannot choose a host or an arbitrary path, only the allow-listed API paths of the model servers you exposed. Read the details on the \u003Ca href=\"\u002Fdocs\u002Fsecurity\">security page\u003C\u002Fa>.\u003C\u002Fp>\n\n      \u003Ch2>Practical habits\u003C\u002Fh2>\n      \u003Cp>Keep tokens in environment variables such as \u003Ccode>TOKMINE_TOKEN\u003C\u002Fcode> and out of version control. Give each person, and each CI job, a separate token. Review the dashboard now and then for anything unexpected.\u003C\u002Fp>\n\n      \u003Ch2>Try it\u003C\u002Fh2>\n      \u003Cp>Create an account, run \u003Ccode>tokmine login\u003C\u002Fcode>, and invite the people who need the model. Start from the \u003Ca href=\"\u002Fdocs\u002Faccount\">account docs\u003C\u002Fa>.\u003C\u002Fp>\n    ",[17,19,29,38],{"slug":4,"title":5,"excerpt":6,"author":7,"authorBio":8,"publishedAt":9,"readMinutes":10,"tags":18,"coverImage":14},[12,13],{"slug":20,"title":21,"excerpt":22,"author":7,"authorBio":8,"publishedAt":23,"readMinutes":24,"tags":25,"coverImage":28},"local-vs-hosted-ai-cost","Local or hosted AI? What running your own models costs","Hosted APIs bill per token. Local models bill in hardware, power and your time. Here is how to compare the two without fooling yourself.","2026-09-29T09:00:00.000Z",5,[26,27],"Cost","Local models","\u002Fblog\u002Flocal-vs-hosted-ai-cost.svg",{"slug":30,"title":31,"excerpt":32,"author":7,"authorBio":8,"publishedAt":33,"readMinutes":10,"tags":34,"coverImage":37},"use-ollama-from-anywhere","Use Ollama from anywhere, in three steps","Reach the models on your home GPU from a laptop, a CI job or a teammate's machine, without opening a single port or setting up a VPN.","2026-09-22T09:00:00.000Z",[35,36],"Ollama","Tutorial","\u002Fblog\u002Fuse-ollama-from-anywhere.svg",{"slug":39,"title":40,"excerpt":41,"author":7,"authorBio":8,"publishedAt":42,"readMinutes":24,"tags":43,"coverImage":45},"why-local-models-need-a-traffic-manager","Why local AI models need a traffic manager","One GPU box is a hobby. Three machines and five teammates is a routing problem. Here is what changes when your models live on your own hardware.","2026-09-15T09:00:00.000Z",[27,44],"Architecture","\u002Fblog\u002Fwhy-local-models-need-a-traffic-manager.svg",1790768272296]