← All providers
Nebius pricing
verified 2026-09-02European AI cloud with serverless open-model endpoints and budget-friendly token rates.
data residency & retention
from Nebius's own policies · verified 2026-09-02Headquarters
🇳🇱 Netherlands (EU)
Where inference runs
EU, US, Other
Nebius (Dutch entity) runs inference in EU datacenters (Finland, France), Israel, and the US, with each model's location shown via country flags in the console before use.
Region pinning
Yes, self-serve
Per-model datacenter location is disclosed in the console; dedicated endpoints offer contractually fixed regional deployment in EU or US datacenters with no multi-region routing.
Prompt retention
Retained · no fixed window (inference cache)
By default inputs and outputs are kept to speed up inference via speculative decoding (stored in Finland, EU); with ZDR enabled, prompts and responses are not stored after each request.
Trains on API data
No
Content is not used to train any models in either mode — retained data serves speculative decoding only.
Zero data retention
Available
ZDR is a self-serve toggle in account settings, with a warning it may impact inference speed.
current models · $ per 1M tokens
| Model | Input /1M | Cached in | Output /1M | Context |
|---|---|---|---|---|
gpt-oss-120b GPT-OSS | $0.15 | — | $0.60 | — |
GLM-5.3-Flash GLM | $0.15 | — | $0.50 | — |
GLM-5.2 GLM | $1.40 | — | $4.40 | — |
DeepSeek-V4-Flash DeepSeek | $0.14 | — | $0.28 | 1.0M |
DeepSeek-V4-Flash-0731 DeepSeek | $0.14 | — | $0.28 | 1.0M |
DeepSeek-V4-Pro DeepSeek | $1.75 | — | $3.50 | — |
Qwen3.5-397B-A17B Qwen | $0.60 | — | $3.60 | — |
Kimi-K3 Kimi | $3 | — | $15 | 1.0M |
MiniMax-M3 MiniMax | $0.30 | — | $1.20 | 1.0M |
Qwen3-235B-A22B-Instruct-2507 Qwen | $0.20 | — | $0.60 | — |
Kimi-K2.7-Code Kimi | $0.95 | — | $4 | — |
Kimi-K2.6 Kimi | $0.95 | — | $4 | — |
Nebius totals · 1M in + 1M out
DeepSeek-V4-Flash
$0.4200
DeepSeek-V4-Flash-0731
$0.4200
GLM-5.3-Flash
$0.6500
gpt-oss-120b
$0.7500
Qwen3-235B-A22B-Instruct-2507
$0.8000
MiniMax-M3
$1.50
Qwen3.5-397B-A17B
$4.20
Kimi-K2.7-Code
$4.95
Kimi-K2.6
$4.95
DeepSeek-V4-Pro
$5.25
GLM-5.2
$5.80
Kimi-K3
$18.00
Cost of 1M input + 1M output tokens. Bar length is square-root scaled so cheap models stay visible next to premium ones.