Skip to content
Dashboard

Nebius models

Inference at enterprise scale, from open models to governed production.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$3/M
$15/M
0.7 s65 tps——
+3
07/16/2026
1M
$1.40/M
$4.40/M
0.5 s172 tps——
+1
06/16/2026
1M
$0.30/M
$1.20/M
0.7 s268 tps——
+2
05/31/2026
131K
$0.15/M
$0.60/M
0.4 s339 tps——
08/05/2025
41K
$0.01/M
—
————
06/05/2025