Skip to content
HostYourAI

01 Code $ hyai

Code with open-weight models
in Europe.

Install with one command, log in with your key, and your agent runs on the router.

Get started Rather keep your own tool
Screenshot of the Logs page: every request of the last 7 days with its model, key, team, tokens, first token and cost
  • GLM
  • DeepSeek
  • Qwen
  • Kimi
  • Mistral
  • Llama
  • gpt-oss
  • Gemma
  • Loes
  • Nemotron
  • Claude Code
  • Codex
  • OpenCode
  • Cursor
  • Cline
  • Loes
  • OpenAI SDK
  • Anthropic SDK

What it does

Keep your tools.
We run the rest.

hyai is a small open source command line. It reads the live model list, keeps your key in your system keychain and starts your agent only on models that are warm at that moment. It holds no agent of its own: it starts OpenCode by default, and Claude Code or Codex with hyai run claude or hyai run codex. You pay per token from prepaid credits.

Read more

~/project · bash 
# install, Node 20 or newer
$ curl -fsSL https://hostyourai.com/cli/install.sh | sh

# your router key, the input stays hidden
$ hyai login

# start in your project
$ cd your-project
$ hyai

hyai

Your code never leaves Europe

MIT licence. The install script is short and you can read it first: hostyourai.com/cli/install.sh
Latest version 0.12.0 · what's new

Works with

  • Claude Code
  • Cline
  • opencode
  • Codex
  • Anthropic SDK
  • OpenAI SDK
  • cURL
Two ways in

Let hyai set it up, or keep your own tool

Already working with Claude Code, Cline or opencode? Then you only swap the base URL: your tool stays the same, the models behind it become open-weight models on European GPUs. No migration, no SDK switch.

hyai

What hyai takes care of

  • Your key lives in the keychain, never in your project or a config file
  • Only warm, per token models that pass our daily tool calling test
  • Other providers in the agent are off, and so is session sharing
  • The agent's own update check and model catalogue are turned off
  • hyai run claude or hyai run codex starts the same setup in Claude Code or Codex
  • If you have a dedicated box of your own, hyai starts on it
  • hyai doctor checks your setup line by line
.zshrc · diff 
# keeping your own tool: Claude Code as the example
- export ANTHROPIC_BASE_URL="https://api.anthropic.com"
+ export ANTHROPIC_BASE_URL="https://hostyourai.com"
+ export ANTHROPIC_AUTH_TOKEN="hyai-rt-..."
+ export ANTHROPIC_MODEL="qwen3.6-27b-fp8"

The tool in your terminal stays the same. What changes: the model that answers, and where your code goes. View the API docs

OpenCode and Codex CLI are independent open source projects and Claude Code is a product of Anthropic. None of the three is made by or affiliated with HostYourAI; you install them yourself. What you pay shows in your dashboard.

API

The router speaks the Anthropic API and the OpenAI API

That is why you do not have to rewrite anything. A tool or SDK that talks to one of the two works with another base URL and your router key.

Anthropic API

For Claude Code and the Anthropic SDK

  • POST /v1/messages
  • POST /v1/messages/count_tokens
  • Token-by-token streaming (SSE)
  • Tool calling: read files, run commands
  • x-api-key and Bearer auth

OpenAI API

For the OpenAI SDK and everything around it

  • POST /v1/chat/completions
  • GET /v1/models with live context and tool info
  • Token-by-token streaming (SSE)
  • Tool calling (function calls)
  • Same key and credit balance as the Anthropic route
Dedicated

Works with your own dedicated box too

hyai models

If you run a GPU box of your own with us, hyai sees that model in your list and starts on it by itself, in every agent. That gives you the best performance and the most security: the box works for you alone, and your code goes to hardware nobody else is on. You pay the box per hour, the tokens cost nothing on top.

With a private connection (WireGuard) on the box, the model port is closed to the public internet. If you want a shared model for a session after all, you pick it with hyai config set model. See what a box of your own costs

~/project · bash 
$ hyai models
GLM 5.2   zai-org/GLM-5.2   your own instance, billed per minute

$ hyai
hyai code: OpenCode on model zai-org/GLM-5.2
(running on your own dedicated instance)
Open weights

You can see which model is running

Serve

You know which model answers, with how much context and whether it can call tools. GET /v1/models shows live what is being served, and hyai only offers the models that are warm and pass our daily tool calling test. When a better open coding model comes out, we test it and add it.

Why EU

For teams that may not send everything to the US

No training on your code

Your prompts and code are not used to train models.

European datacenters

Inference runs on GPUs in the EU. Your traffic never leaves Europe, not even for logging or analytics.

Data Processing Agreement

A DPA is available for teams that need this on paper. Email info@hostyourai.com.

Screenshot of a chart of requests per day per model over the last week
Pricing

You pay per token from prepaid credits

You top up credits from €5 by iDEAL or card and pay per token, priced per model. When the balance is used up the agent stops, so it can never spend more than you put in. An afternoon of work with a coding agent usually costs cents to a few euros.

Current token prices are on the pricing page.

THREE STEPS

  1. 1Create an account and top up credits
  2. 2Create a router key in the dashboard
  3. 3Install hyai and log in with hyai login
Get started
Questions

Questions we get

Can I still use the Claude or OpenAI models next to yours?

Yes, on your own key. In a hyai session every request goes to our router. If you link your own Anthropic or OpenAI account to your HostYourAI account, those models sit in the same list next to the open models, also in the model picker of Claude Code and Codex. That provider bills you for them, we do not. hyai never picks such a model by itself; the open models stay the default.

Do I need to change my tooling?

No. hyai starts OpenCode, Claude Code or Codex for you on the router. And anything that speaks the Anthropic API or the OpenAI API keeps working with another base URL and your router key.

Which model do I get?

hyai starts on the best coding model that is warm at that moment and tells you which one and why. If you have a dedicated box of your own, it starts on that. hyai models shows the whole list with prices, and with hyai config set model you choose yourself.

How fast is it?

hyai only uses models that are warm, so the first answer starts streaming within seconds. If you set a base URL yourself and ask for a cold model, your first question boots a GPU and takes a few minutes.

What does it cost?

Per token from your prepaid credit balance. An afternoon with a coding agent typically costs cents to a few euros; every request shows up live in your usage.

Am I locked into anything?

No. No subscription; you top up whenever you want and your balance stays. And because the APIs are standard, switching back is just as easy.

The platform

One platform, four layers

Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.

Code

Your coding agent on open models in Europe, set up with one command.

Open

Control

Keys, budgets and guardrails per team, and personal data stopped before any model sees it.

Open

Serve

Shared per token, or running for you alone, from European data centres.

Open

EU compute

Private GPUs in Europe, H100 to B300, sized for response time, generation speed and concurrent users.

Open

Try it in your own project

You need a router key and Node 20. Credits from €5, no subscription.

Get started More about Code
  • Jantine
  • Hans
  • Sander
  • Jos
  • Daan
  • Kyra
  • Margriet
  • Stan
The team behind HostYourAI