Open-model inference

Open models, one API.

Language models served from Europe, in Chat and through the API.

Read the docs
Launch offer · ends 1 Dec €19/month instead of €29 (or €16/month billed yearly) for your first year, excl. VAT.
Chat, CRM, automation and creative applications connect through a single API to three open models.
Your applications One API Open models
Access and pricing

Inference at a flat rate.

All models, in Chat and through the API, without counting tokens. Fair use: 2 requests at a time.

Launch offer · ends 1 December
Billing period
€19 Regular price: €29 / month

Per person, excl. VAT

First 12 months when you subscribe by 1 December (save €120), then €29 a month.

€16 Regular price: €24 / month

€192 billed yearly · per person, excl. VAT

First year when you subscribe by 1 December (save €96), then €288 a year (€24/month).

Cancel anytime.

Models

Choose a model for the job.

In production

EuroLLM 22B

eurollm-22b

Translation and writing in 35 languages, including every official EU language.

Context
32K tokens
Maximum output
16K tokens

GLiDE 9B

glide-9b

Yes or no, choice or score on a text, with probabilities.

Context
16K tokens
Questions / request
4

Why Vora Compute

  1. Inference in Europe

    Your requests run on GPUs in Europe, operated by a European provider.

  2. Private by default

    No prompts stored on the API. Saved chats are encrypted and yours to delete.

    How we handle your data
  3. Direct team support

    Talk directly to the engineers running the models and hardware.

Chat Included

Talk to the models in your browser.

chat.voracompute.com Open Chat →

What can I make for dinner with eggs, spinach and cheese?

A 10-minute spinach and cheese omelette, or baked eggs over sautéed spinach.

API

OpenAI-compatible for your SDK, OpenCode, Cline, Continue and Aider.

api.voracompute.com Agent guides →
curl https://api.voracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $VORA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'
▸ streaming from qwen3.8-27b
Hi! How can I help your team today?
✓ done
Our infrastructure partner

AI that also heats water.

Hotta puts server heat to use for hot water where it is needed: hotels, resorts and spas.

Meet Hotta
Illustrative isometric hotel and spa: servers inside the building connect to a heat recovery system, which supplies hot water to the shower and pool.
Servers in the building Recovered heat Hot water
Launch offer · ends 1 December

Start using Inference today.

Subscribe by 1 December for €19 a month, or €16 a month billed yearly (€192/year), during your first year — excl. VAT. Instant access to Chat and the API. Cancel anytime.

Read the docs
WhatsApp