LLM Pricing
PricingLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
al

Kolibri 1

aleph-alpha·aleph-alpha/kolibri-1·GA·Open weights·NEW
Aleph Alpha's German and English mixture-of-experts reasoning model (78B total, 3.46B active) for chat, RAG and agents

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Munito AIGateway
$0.13 / $0.51
Blended $0.23 · 1.3× spread
Context
262,144
Output limit
81,920
Knowledge cutoff
2026-06-18
Released / updated
2026-10-03 / 2026-10-03
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
License
Apache-2.0
Weights
Hugging Face

Kolibri 1 by aleph-alpha is offered by 4 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Munito AI at $0.13 / $0.51 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 1.3× across the providers that host it.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 262,144 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2026-06-18.

Available at 4 providers4 with public prices

  • ProviderInput / Output
  • Munito AIGateway
    $0.13 / $0.51
    Cache read $0.078Context 1,048,576 ⚠Output limit 943,718
  • Munito AI (EU)Gateway
    $0.16 / $0.56
    Cache read $0.094Context 1,048,576 ⚠Output limit 943,718
  • NanoGPTGateway
    $0.17 / $0.59
    Cache read $0.099Context 1,048,576 ⚠Output limit 1,048,576
  • CortecsGateway
    $0.17 / $0.61
    Cache read $0.084Context 262,144Output limit 81,920
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Munito AIGateway$0.13$0.51$0.078—1,048,576 ⚠943,718
Munito AI (EU)Gateway$0.16$0.56$0.094—1,048,576 ⚠943,718
NanoGPTGateway$0.17$0.59$0.099—1,048,576 ⚠1,048,576
CortecsGateway$0.17$0.61$0.084—262,14481,920

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = high

Interleaved thinking (reasoning between tool calls) is declared by 2 of 4 providers.

Your usage cost

Common scenarios
1Munito AI$45.26
2Munito AI (EU)$52.08
3Cortecs$54.09
4NanoGPT$54.68
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.23

Price history accumulates from each data sync; currently only 1 sample(s) (2026-10-25). Each future sync adds a point, and once accumulated a line is drawn here.

Data partly from models.dev (MIT)