Skip to content
03 Model garden Serve

Kolibri 1

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

curl
$ curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Aleph-Alpha/Kolibri-1",
    "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
Aleph-Alpha/Kolibri-1

text->text · aleph-alpha · sovereign EU

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

Kolibri is Aleph Alpha's mixture-of-experts (MoE) reasoning model, with a focus on German and English. The model supports an explicit reasoning mode and tool calling. It is optimized for long-context and inference efficiency.

Router
Router · warm
Dedicated
Dedicated · available
Input (per 1M tokens)
€0.17
Output (per 1M tokens)
€0.63
262KContext window
140GBMinimum VRAM
POST /api/v1/chat/completions 200 OK

Specifications

Context window262,144 tokens
Minimum VRAM140 GB
ArchitectureKolibri1ForCausalLM (vLLM)
Licenseopen-weights
Modalitytext->text
ReleasedOctober 2026
Publisheraleph-alpha ↗

Pricing

Shared router · per token

€0.17Input (per 1M tokens)
€0.63Output (per 1M tokens)

€0.09 per million cached input tokens

Dedicated GPU · per hour

from €5,70 per hourYour own vLLM instance on European cloud (140 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.

~68.0 / 100 · Estimate

No public benchmark yet: estimated from size and release date.

Range 56.5 to 79.5

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 21-11-2026

Questions

Frequently asked questions

Can I run Kolibri 1 in the EU?

Yes. HostYourAI runs Kolibri 1 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 Kolibri 1 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 Kolibri 1 cost?

Via the shared EU router you pay €0.17 per million input tokens and €0.63 per million output tokens, with no fixed costs. For high volume or isolation you can also run Kolibri 1 on a dedicated GPU instance, billed per minute.

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 Kolibri 1 for free

Creating an account takes a minute. Test Kolibri 1 straight away in the playground.

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