Simple prices. Europe shouldn’t cost more.

Running AI in Europe has cost about 30% more than in the US. We’re closing that gap.

InferenceEUR per 1M tokens · excl. VAT · billed per token
Qwen3 Embedding 8BQwenInput€0.01Cached—Output—
GLM-5.3 FlashZ.aiInput€0.10Cached€0.02Output€0.40
DeepSeek V4 FlashDeepSeekInput€0.10Cached€0.02Output€0.25
Qwen3.8 Flash NextQwenInput€0.17Cached€0.041Output€0.41
DeepSeek V4.1 FlashDeepSeekInput€0.20Cached€0.01Output€1.00
MiniMax M3MiniMaxInput€0.33Cached€0.081Output€1.62
Qwen3.8 27BQwenInput€0.33Cached€0.081Output€1.94
Kimi K2.7 CodeMoonshotInput€0.60Cached€0.15Output€3.60
GLM-5.3Z.aiInput€1.00Cached€0.13Output€3.00
GLM-5.2Z.aiInput€1.00Cached€0.13Output€3.00
DeepSeek V4 Pro 0813DeepSeekInput€1.62Cached€0.41Output€3.23
Qwen3.8 2.4T A95BQwenInput€2.02Cached€0.51Output€4.84
Kimi K3.1MoonshotInput€2.42Cached€0.61Output€12.08
Kimi K3MoonshotInput€2.42Cached€0.61Output€12.08
GPU computeEUR per GPU hour · excl. VAT · billed per second
NVIDIA B300288 GBOn demandContact sales
NVIDIA B200192 GBOn demandContact sales
NVIDIA H200141 GBOn demandContact sales
NVIDIA H10080 GBOn demandContact sales
NVIDIA A10080 GBOn demandContact sales
NVIDIA L40S48 GBOn demandContact sales
Sales

Need volume pricing or reserved GPUs?

Volume discounts, invoicing instead of prepaid credits, custom contracts and dedicated capacity. We reply within one business day.

Talk to sales

Move your AI to Europe.

One key, one endpoint. Your first call takes minutes.