HostYourAI Code

Code with open-weight models
in Europe.

Swapping one base URL is all it takes.

You keep your tool and swap the model: Claude Code, Cline and opencode keep working as-is, but you replace the Claude models behind them with open-weight models on European GPUs. No migration, no SDK switch. Pay per token from prepaid credits.

.zshrc · diff
- 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.

Your code never leaves Europe Verified with a real Claude Code session
Works with >_Claude Code >_Cline >_opencode >_Anthropic SDK >_OpenAI SDK >_cURL
Drop-in

Two APIs, same router, same key

The router speaks both the Anthropic and the OpenAI API in full. Nothing to rewrite: any tool or SDK that talks to either one works right away.

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
Verified

Tested with a real session, not a demo

Before we promise anything on this page we run it ourselves: a full Claude Code session against this router that reads a file through tools and returns the right answer. The example here is that test.

Fair is fair: the US frontier models remain better. This is the alternative for teams that want code and prompts to stay in Europe, with open weights you can inspect yourself.

~/project · bash
$ claude > Read hello.txt and tell me the secret code. ● Read(hello.txt) The secret code in hello.txt is: KAAS-42
QQwen3.6 27B FP8tools32k · EU
+Next verified coding modelscoming
Open weights

Open-weight models, honestly served

No black box: you know which model runs, with how much context and which tool support. GET /v1/models shows live what is being served. When a better open coding model appears we verify it and add it to the list.

Why EU

Built for teams that cannot send everything to the US

No training on your code

Your prompts and code are never used to train models. What you send is yours and stays yours.

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.

Pricing

Per token, prepaid, never a surprise bill

You top up credits from €5 by iDEAL or card and pay per token, priced per model. When it runs out it stops: your agent can never spend more than you set aside. An afternoon with a coding agent typically costs cents to a few euros.

Current token prices are on the pricing page.

UP AND RUNNING IN THREE MINUTES
1Create an account and top up credits
2Create a router key in the dashboard
3Set the base URL, key and model in your shell
Start in the dashboard
FAQ

Honest answers

Am I still using Claude models?

No. Claude Code is only the tool in your terminal; you replace the Claude models behind it with open-weight models such as Qwen, hosted by us in the EU. Your traffic no longer goes to Anthropic.

Do I need to change my tooling?

No. Anything that speaks the Anthropic or OpenAI API keeps working with a different base URL and key. Claude Code, Cline and opencode only need three environment variables.

Which model do I get?

Currently a Qwen3.6 coding model with tools and 32k context, the best open-weight model we have verified. The list grows as better open models appear.

How fast is it?

A warm GPU responds quickly and streams token by token. If the model is cold, your first question boots a GPU and takes a few minutes. After that it stays warm while you work.

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.

Swap the base URL and try it

Credits from €5, no subscription. Your first session runs within minutes.