kolibri-1
kolibri-1
Kolibri-1 is Aleph Alpha’s open-weight English-German MoE language model, designed for enterprise use with efficient inference and advanced reasoning.
Specification
most-agreed values
Context
262K
Max output
82K
Released
2026-10-03
Knowledge cutoff
2026-06-18
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.167
Output
$0.613
Cache read
$0.084
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| munito · aleph-alpha | $0.13 | $0.51 | $0.078 | — | 1M | 944K | — |
| munito-eu · aleph-alpha | $0.16 | $0.56 | $0.094 | — | 1M | 944K | — |
| cortecs | $0.167 | $0.613 | $0.084 | — | 262K | 82K | — |
| nano-gpt · aleph-alpha | $0.168 | $0.588 | $0.0987 | — | 1M | 944K | — |