Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.
Llama 4 Maverick 17B 128E Instruct FP8 is an open-source language model from Meta with 17B parameters, hosted on EU GPUs via an OpenAI-compatible API.
This model needs 501 GB of VRAM, so several GPUs. That makes the shared router rate high. From roughly 50 million tokens a month a dedicated deployment costs less.
Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
curl https://hostyourai.com/api/v1/chat/completions \
-H "Authorization: Bearer hyai-..." \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"messages": [{"role": "user", "content": "Hello!"}]
}'Yes. HostYourAI runs Llama 4 Maverick 17B 128E Instruct FP8 on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.
Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.
Via the shared EU router you pay €0.40 per million input tokens and €0.60 per million output tokens, with no fixed costs. For high volume or isolation you can also run Llama 4 Maverick 17B 128E Instruct FP8 as a dedicated hourly GPU instance.
Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.
Creating an account takes a minute. Test Llama 4 Maverick 17B 128E Instruct FP8 straight away in the playground.
Start for free