Dedicated hardware. Pre-configured. Running in minutes.
BYOK agents for development and small workloads
2 vCPU / 4 GB RAM / 40 GB NVMe
Production agents with higher throughput
4 vCPU / 16 GB RAM / 80 GB NVMe
Local inference with NVIDIA L4
8 vCPU / 32 GB RAM / 160 GB NVMe / NVIDIA L4 24 GB
NVIDIA GPUs in European datacenters. Run any open-source model. Your data never leaves your server.
Run Llama 70B, Mixtral, DeepSeek locally
~$2,549/mo
NVIDIA A100 80 GB SXM4
10 vCPU / 120 GB RAM / 200 GB NVMe
Fastest inference for demanding workloads
~$3,999/mo
NVIDIA H100 80 GB SXM5
20 vCPU / 200 GB RAM / 400 GB NVMe
Maximum VRAM for the largest models
~$4,999/mo
NVIDIA H200 141 GB SXM5
20 vCPU / 200 GB RAM / 400 GB NVMe
GPU tiers billed per hour. All instances on dedicated hardware in EU datacenters. Prices exclude VAT.
We handle server provisioning, security hardening, TLS, monitoring, and updates. You get a running Solon instance with a web dashboard. Your server, your data — we just keep it running.
Starter and Pro tiers use your existing API keys (Anthropic, OpenAI, etc.) for inference — affordable and fast to start. GPU tiers run open-source models locally on dedicated NVIDIA hardware — no API costs, full data sovereignty.
CPU tiers (Starter, Pro, GPU L4) run on Hetzner in Germany, Finland, or US East. GPU tiers (A100, H100, H200) run on dedicated NVIDIA hardware in Finland or Iceland.
Every customer gets a dedicated server. No shared compute, no noisy neighbors. Full tenant isolation with automatic TLS and firewall.
Yes. Upgrade or downgrade anytime. We'll migrate your instance to the new server type with minimal downtime.
GPU tiers (A100, H100, H200) are billed per hour. You pay only while the instance is running. CPU tiers are billed monthly at a flat rate.
Absolutely. Solon is open source (MIT). Install it anywhere with one command. Managed hosting is for teams who'd rather focus on building than managing infrastructure.
Already running Solon? Connect your instances to the cloud dashboard for remote access, team management, and monitoring.
Get a managed AI agent instance running in minutes. No infrastructure experience needed.