Now in development
Localhost, but everywhere >-
Host your AI on your machine. Access it from anywhere with a single URL.
Showcase
Watch ink-ls work, end to end >-
An auto-playing tour of the site, host, and client. No clicks needed.
ink-ls
Loading…
Log in to ink-ls
••••••••
or
New around here? I'm new here
Log in to ink-ls Host
••••••••
or
New here? Create an account on the website
IDLE Dashboard
No endpoint running. Pick a model and press Run.
API
Model
Status
Idle
backend: native
Requests
0
since start
Tokens
0
total
Public URL
offline
ink-ls.com routes
System resources
idle22%
RAM
5%
CPU
0%
GPU
38%
DISK
Users1 active
Per-user context · per-user rate · no message content shown.
W
William
192.168.1.42 · 2m
Context
0 / 200K
Tokens0
Requests1
STREAMING Console
Live backend output · tunnel frames · request traces · tool lifecycle
Output appears here when hosting.
Log in to ink-ls Client
••••••••
or
New here? Create an account on the website
INK_AI
MY_API_INK · ink-ls.com
Requests: 0 / 2,500 hr
Compute: 0 / 10,000
Tier: Developer
0 / 200K
Pricing
Pay for the routing. Not the compute >-
Your hardware runs the model. ink-ls charges for the relay, the dashboard, and the limits you set per API.
Free
$0forever
Personal projects. One private endpoint.
Requests
100 / hour
Images
3 / hour
- 1 API endpoint
- 10 users per API
- Private hosting
- Compute points
- Mesh
Most popular
Developer
$5/ month
Real workloads. Configurable per-API limits.
Requests
2,500 / hour · configurable
Images
20 / hour
- 5 API endpoints
- 100 users per API
- Public hosting
- Compute points
- Mesh
Studio
$30/ month
Teams and businesses. Routing without limits.
Requests
50,000 / hour
Images
100 / hour
- 50 API endpoints
- 1,000 users per API
- Public hosting
- Compute points
- Mesh
Curious
Common questions, real answers >-
What is Ink-ls?
Ink-ls is a routing platform, where you create an API and then host AI on it. Perfect for small and large scale hosting.
Where does my data go through, and what happens to it in the process?
The host app runs on your hardware, it stores the conversations locally, Ink-ls does not have access to them. When sending a message from ink host to ink client, that message is relayed through ink's servers. We do not monitor or save the messages, they just get passed from the host to the client. We only enforce limits on the number of requests , not on the context size nor the context itself.
Who is behind Ink-ls?
Currently, a single developer (752) at the age of 18. I'm from Bulgaria, with the only intention of creating a platform that serves its users properly, stable and reliable.
What am I paying for with those tiers?
Simply, you pay for the routing and the ability to host with 1 button. The only case you would even need them in the first place is if you are a heavy user, or hosting it for a larger group of people. Prices are aimed to be affordable to anyone. Developer stands at 5$ per month and offers 2500 requests per hour. You would need it if you want to have multiple API's and multiple machines hosting different stuff at the same time, to multiple people. The apis limit the request count NOT their size, which means that even if you are a heavy user you wont be hit with a usage limit unless you deliberately spam.
How do I get the models, what models can I host?
Ink host allows you to host every single model that is in the .gguf format. Coding, uncensored or creative doesnt matter. The app has a built in search tab for models and pulls straight from HuggingFace! Of course if you have your own tuned model in the .gguf format you can place it in the models folder and host it. It's one click anyways!
Why do I use Ink-ls, what is its purpose?
Long story short, if you have two machines, one strong enough to host an ai (you dont really need a very strong machines, i was left surprised by how efficient local LLMs have gotten.) and another machine that is just not strong enough as an example, a Desktop and a Laptop , you host the AI on the powerful desktop and enjoy using it from the laptop. You can use it from anywhere really, its stable, reliable and secured. As mentioned Ink only routes, it doesnt store.
I need to know more about my privacy?
I will be very detailed on this but first a few recommendations, when using public APIs from the Public tab in the site, always read the description and never trust it enough with any important information. As of if you are using a private API, it's secured, it's on your own machine and all conversations are stored there (encrypted using both host key and account key, meaning every user on that host has their history encrypted in a different way, this is made deliberately so the chat history cannot be unlocked unless both keys are provided. having the .db file itself is useless.), on your host machine. It never gets stored on our servers (Yes that means if you reinstall the PC you will lose all of your conversations unless you manually do a backup of the .db file and the .key file.). While chatting the messages are relayed through the servers (fully transparent on it, it means that ink acts as a tunnel from point A to B, its not E2E but it uses TLS protocols). We do not access the context of the message, they dont get cached, stored or reviewed in any way. There is no censor or filter on the messages (simply because we only route them). They are secured and can only be accessed via your account(more specifically, a key bound to your account). Outside users cannot receive the content of the message.
What is mesh, and why is it advertised?
Mesh is a functionality that essentially allows the host to increase the capacity of their AI. To be clear if you host for many people, the load will get spread across all devices added on the mesh network. (Coming soon.)
Why is mesh not on the free tier?
The free tier is made for casual users that need the AI only for themselves or at most their friends, there is no need of mesh at such a low scale.
What are payouts?
Ink as a platform wants to encourage people to host locally! the payouts functionality allows people to pay wall their AI and publicly host it for other people at a certain price. This way while ink sells routing, the user can sell their compute to other people.
What does ls in Ink-ls stand for, why not just ink?
LS stands for Lost Sanches, just another very passioned project of mine. There is nothing else behind it. And the fact that it matches with the linux command is just a coincidence that i noticed recently.
Why does the site look like github?
The design is inspired mainly by github because it feel familiar to many people and I found it good looking and fitting the theme.
What is the stack of the project (for the non tech people, stack means stuff used.)?
The site uses Python(FastAPI,Jinjga2) while the Relay is in Rust. Both apps Ink Host and Ink Client , use Tauri which is again Rust.
What are compute points?
Compute points is a metric that can be set by the Host. When set it mesures how much resource the user uses and can apply stricter limits. It's available only on paid plans to allow users that want to host, more control over their network.
Any limits?
Limits can be set by the Host, other than this, usually limits are displayed on each API, so if you are using a public API you know if you are going to get limited.
No matching question — try different words.