11 models available
Swedish AI inference provider running open-weight models on its own GPUs in Stockholm, with zero data retention by default and an OpenAI-compatible API for chat, embeddings, reranking and transcription.
BGE Reranker v2 M3
$0.10 / $0.10
Faster Whisper Large V3
$0 / $0
Gemma 4
$0.10 / $0.20
GLM 5.3 Flash
$0.10 / $0.35
KB-Whisper Large
$0 / $0
Kimi K3
$3.00 / $15.00
Mistral Small 3.2 24B
$0.09 / $0.28
Multilingual E5 Large
$0.03 / $0
Multilingual E5 Large Instruct
$0.03 / $0.02
NB-Whisper Large
$0 / $0
Qwen3.8 27B
$0.10 / $0.40
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.