Aleph Alpha logo

Aleph Alpha: Kolibri 1

Aleph Alpha's German and English mixture-of-experts reasoning model (78B total, 3.46B active) for chat, RAG and agents

Source-linked Open weights Apache-2.0 Released 2026-10-03
API record Report
InputT
OutputT
Input price$0.13/M
Output price$0.51/M
Context1.04858M
Max outputNot documented
Providers3
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Kolibri 1
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Munito AI aleph-alpha/kolibri-1 1.04858M 943.718K $0.13 $0.51 $0.078 ReasoningToolsJSON Docs ↗
Munito AI (EU) aleph-alpha/kolibri-1 1.04858M 943.718K $0.16 $0.56 $0.094 ReasoningToolsJSON Docs ↗
NanoGPT aleph-alpha/kolibri-1 1.04858M 1.04858M $0.168 $0.588 $0.099 ReasoningToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.13/M

Across 3 priced providers

Median input $0.16/M

Midpoint of listed rates

Highest input $0.168/M

1.3× the lowest listed rate

Output range $0.51 – $0.588

Per million output tokens

Munito AI $0.13/MLowest
Munito AI (EU) $0.16/M
NanoGPT $0.168/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.
Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
× Attachments No
× Vision input No
✓ Open weights Yes
Model family
Not documented
Knowledge cutoff
2026-06-18
License
Apache-2.0
Release date
2026-10-03
Model ID
aleph-alpha/kolibri-1

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://modelbench.lol/api/v1/models/aleph-alpha/kolibri-1
curl
curl "https://modelbench.lol/api/v1/models/aleph-alpha/kolibri-1"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Kolibri 1?

Aleph Alpha's German and English mixture-of-experts reasoning model (78B total, 3.46B active) for chat, RAG and agents. It is published by Aleph Alpha and catalogued here from Models.dev.

How much does Kolibri 1 cost?

Listed input pricing starts at $0.13 per million tokens from Munito AI, rising to $0.168 across 3 listed providers.

What is the context length of Kolibri 1?

Kolibri 1 accepts up to 1.04858M tokens of context.

Does Kolibri 1 support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, and reasoning.

Which providers serve Kolibri 1?

3 providers list this model: Munito AI, Munito AI (EU), NanoGPT.

Are the weights for Kolibri 1 open?

Yes. The weights are published and downloadable from Hugging Face under the Apache-2.0 license.

When was Kolibri 1 released?

The catalog records a release date of 2026-10-03, last verified Oct 25, 2026.