Skip to content
03 Model garden Serve

Llama 3.1 405B FP8

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

curl
$ curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.1-405B-FP8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

Serve Model garden On request
meta-llama/Llama-3.1-405B-FP8

text->text · meta-llama · sovereign EU

Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain

Llama 3.1 405B FP8 is an open-source language model from Meta with 405B parameters, hosted on EU GPUs via an OpenAI-compatible API.

Router
Router · on request
Dedicated
Dedicated · available
405BParameters
585GBMinimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters405B
Minimum VRAM585 GB
ArchitectureLlamaForCausalLM (vLLM)
Licenseopen-weights
Modalitytext->text
ReleasedJuly 2024
Publishermeta-llama ↗

Pricing

Shared router · per token

On request Not available on the shared router. Pricing on request as a dedicated GPU deployment.

Dedicated GPU · per hour

from €23,76 per hourYour own vLLM instance on European cloud (585 GB VRAM), billed per minute.

Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

47.3 / 100 · Measured

Measured by Epoch AI across 15 benchmarks, with a range.

Range 43.7 to 50.6 · Rank 163 of 257 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 19-11-2026

Every benchmark (15)
ARC AI293.7
HellaSwag85.6
TriviaQA82.7
MMLU79.3
Winogrande78.4
BBH77.2
PIQA71.8
MATH level 549.8
GPQA diamond36.0
DTBench35.6
WeirdML21.4
OTIS Mock AIME 2024-20259.6
SimpleBench7.6
Cybench7.5
The Agent Company7.4
Questions

Frequently asked questions

Can I run Llama 3.1 405B FP8 in the EU?

Yes. HostYourAI runs Llama 3.1 405B 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.

Is hosting Llama 3.1 405B FP8 GDPR-compliant?

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.

How much does Llama 3.1 405B FP8 cost?

Llama 3.1 405B FP8 is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per minute. Tell us your use case and we will set it up for you.

Is the API OpenAI-compatible?

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.

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 Llama 3.1 405B FP8 for free

Creating an account takes a minute. Test Llama 3.1 405B FP8 straight away in the playground.

  • Jantine
  • Hans
  • Sander
  • Jos
  • Daan
  • Kyra
  • Margriet
  • Stan
The team behind HostYourAI