Does Kolibri 1 support zero data retention?

The zero data retention posture of the routes serving Kolibri 1 is not yet established. See the per-route data-handling section.

Where is Kolibri 1 hosted?

Kolibri 1 runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Kolibri 1 trained on prompts and outputs?

Training behaviour varies by route. See the per-route data-handling section for each provider's training posture.

Kolibri 1

by Aleph Alpha

Kolibri 1 is Aleph Alpha's mixture-of-experts reasoning model, released on 3 October 2026 under the Apache 2.0 license. It has 78 billion parameters in total but activates only about 3.5 billion per token, which keeps serving cost low while the full model holds the capacity of a much larger one. It was built bilingual by design: a tokenizer tailored to German word structure and a training corpus of roughly 62% English, 24% German and 14% code. The model reasons before answering, with effort levels from low to high, and thinking can be switched off for an immediate reply. It supports tool calling and structured output, and combines both with reasoning. Its native context is 262,144 tokens, and Aleph Alpha has validated it up to one million. Aleph Alpha positions Kolibri for multi-step reasoning, retrieval-augmented generation, agentic tool use, coding and German- and English-language assistants, particularly in public administration and regulated industries. It is meant for systems where a person reviews the output before it is acted on, and Aleph Alpha reports that it matches models with up to four times its active parameter count on math, coding, grounding and long-context tasks.

Call Kolibri 1 on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

131K

Input price

$0.17 /1M

Output price

$0.69 /1M

EU residency available

Available routes

Kolibri 1 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Nodion. See every model hosted in the EU.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Nodion	EU	—Not established	—	$0.17	$0.69	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=nodion%2Fkolibri-1

Data handling per route

Each route hosting Kolibri 1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Nodion — EU🇪🇺

Zero data retention posture is not established for this route. Training posture pending review. EU.

Zero data retention: Not established.
GDPR DPA: No DPA
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Kolibri 1 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Kolibri 1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "nodion/kolibri-1",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);