15 models available
Dutch sovereign AI cloud (Nebul B.V., Leiden). OpenAI-compatible serverless inference on EU-only NVIDIA infrastructure; no training on customer data, no retention beyond operational needs. Not affiliated with Nebius.
All MiniLM L6 v2
$0.09 / $0.45
BGE M3
$0.12 / $0.60
GLM 5
$1.91 / $9.57
GLM 5.1
$1.91 / $9.57
GPT-OSS 120B
$1.36 / $6.78
INF Retriever v1
$0.09 / $0.45
Ministral 3 14B
$0.73 / $3.63
Mistral Large 3
$1.39 / $6.96
Multilingual E5 Large Instruct
$0.12 / $0.60
Nemotron 3 Nano Omni
$0.25 / $1.25
Nemotron 3 Super 120B A12B
$1.36 / $6.78
Qwen3 30B A3B Instruct
$0.50 / $2.52
Qwen3.5 397B A17B
$1.08 / $5.38
Qwen3 Embedding 8B
$0.26 / $0.10
Qwen3 VL 235B A22B Thinking
$1.08 / $5.38
You need AI that won’t create compliance headaches. Your data stays in the EU, GDPR is enforced by default, and every request is routed for the best balance of cost, latency, and uptime, reducing risk while improving performance.