Model garden Router · warm Dedicated · available

Llama 3.3 70B Instruct

Instantly via the EU router or as a dedicated GPU deployment. Data stays in Europe.

Llama 3.3 70B Instruct is an open-source language model from Meta with 71B parameters and a 131K-token context window, hosted on EU GPUs via an OpenAI-compatible API.

meta-llama/Llama-3.3-70B-Instruct vLLM ready
text->text · meta-llama · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
71B
Parameters
131K
Context window
170GB
Minimum VRAM
POST /api/v1/chat/completions 200 OK

Specifications

Parameters 71B
Context window 131,072 tokens
Minimum VRAM 170 GB
Architecture LlamaForCausalLM (vLLM)
License llama3.3
Modality text->text
Released November 2024
Publisher meta-llama ↗

Pricing

Shared router · per token
€1.04
Input (per 1M tokens)
€1.04
Output (per 1M tokens)
Dedicated GPU · per hour
from €4,06 per hour
Your own vLLM instance on European cloud (170 GB VRAM), billed hourly.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

✓ Verified working on 26-07-2026, responded in 292 ms on our EU infrastructure.

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.

46.7 / 100 · Measured

Measured by Epoch AI across 10 benchmarks, with a range.

Range 40.6 to 49.2 · Rank 172 of 270 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 23-10-2026

Every benchmark (10)
MMLU 81.7
MATH level 5 41.6
Fiction.LiveBench 33.3
DTBench 32.5
GPQA diamond 31.2
Balrog 23.0
LMCA 20.6
WeirdML 14.4
OTIS Mock AIME 2024-2025 5.0
SimpleBench 3.9

Call it now

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-3.3-70B-Instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run Llama 3.3 70B Instruct in the EU?

Yes. HostYourAI runs Llama 3.3 70B Instruct 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 3.3 70B Instruct 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 3.3 70B Instruct cost?

Via the shared EU router you pay €1.04 per million input tokens and €1.04 per million output tokens, with no fixed costs. For high volume or isolation you can also run Llama 3.3 70B Instruct as a dedicated hourly GPU instance.

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.

More models from Meta

Try Llama 3.3 70B Instruct for free

Creating an account takes a minute. Test Llama 3.3 70B Instruct straight away in the playground.

Start for free