Infercom SCS
EU inference provider for open-weight LLMs, on hardware we own in Munich. Inference API, dedicated capacity or on-premises. Up to 10x faster than GPUs.
Infercom SCS sells inference on Architect Inference. A buyer names one of its models as infercom/<model>, or names the model and pays the lowest offer that meets the buyer's rules.
Facts
- Handle
- infercom
- Website
- https://www.infercom.ai/
- Terms of service
- https://infercom.ai/termsconditions/
- Privacy policy
- https://infercom.ai/privacypolicy/
- Status page
- https://status.infercom.ai/
- On the exchange since
- 2026-11-18
- Models
- 2
- Offers
- 2
- Regions
- eu
- Precisions (declared)
- bf16
- Lowest price on
- 0 of 2 models, for the agent mix
Reliability, last 3 days
- Uptime
- 100.0%
- Hours with an answer
- 100.0%
- Median response time
- 1.2s
Checked by the exchange
0 of 2 offers are reID verified.
The exchange verifies each offer with reID. It also benchmarks the providers.
Data handling
- Zero retention, declared by the provider
- No training, declared by the provider
- ISO 27001, declared by the provider
- GDPR DPA, declared by the provider
- CSA STAR, declared by the provider
Models
- Gemma 4 31B It: eu, declared precision bf16, $0.2 input and $0.35 output per million tokens, 131.1K tokens of context
- GPT: OSS 120B: eu, declared precision bf16, $0.22 input and $0.59 output per million tokens, 131.1K tokens of context