High-speed EU sovereign inference, served from Munich on SambaNova dataflow hardware instead of GPUs.
Infercom runs its own hardware in Munich and serves open-weight models under EU jurisdiction. The platform uses SambaNova RDUs, purpose-built AI chips with a dataflow architecture, not GPUs. That architecture is where the speed comes from. gpt-oss-120b sustains over 700 tokens per second per user, at about 0.05 seconds to first token. MiniMax M2.7 sustains over 400 tokens per second. Route to Infercom when a workload needs EU data residency and low latency at the same time, for example agents that burn millions of tokens per run.
Every model we route through Infercom. Compare residency, zero data retention, training posture and price at a glance, with full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| EU | No | 197K | $0.68 | $2.74 | ||
| US | No | 33K | $3.42 | $5.13 | ||
| US | No | 131K | $3.42 | $5.13 | ||
| EU | No | 131K | $0.25 | $0.67 | ||
| US | No | 131K | $0.68 | $1.37 | ||
| EU | No | 131K | $0.23 | $0.40 |
Infercom hosts on 2 routes. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.
