# Infercom

> EU sovereign AI inference platform powered by SambaNova dataflow architecture.

For comprehensive content from all pages, see [llms-full.txt](https://infercom.ai/llms-full.txt).

## What is Infercom?

Infercom is a European AI inference platform headquartered in Luxembourg. We provide high-performance AI inference services with full EU data sovereignty. All inference runs on SambaNova hardware in our Munich datacenter (Equinix MU4, Germany). Data never leaves EU jurisdiction.

## Key Facts

- Company: Infercom SCS (Luxembourg)
- Founded: 2025
- Datacenter: Equinix MU4, Munich, Germany
- Hardware: SambaNova SN40L dataflow architecture (not GPUs)
- Certifications: ISO 27001
- API: OpenAI-compatible (drop-in replacement)

## Value Proposition

1. EU Sovereignty: Full GDPR compliance, no US CLOUD Act exposure, EU data residency
2. Performance: Up to 10x faster inference than GPU alternatives via SambaNova dataflow architecture
3. Energy Efficiency: Up to 5x more energy efficient than GPU-based inference

## Models

### EU Sovereign Models (hosted in Munich, Germany)
- [MiniMax M2.7 Ultraspeed](https://infercom.ai/models/minimax-m27): Latest 229B frontier model, 192K context, 400+ tok/s, native multi-agent support.
- [gpt-oss-120b](https://infercom.ai/models/gpt-oss-120b): OpenAI open-weight 120B workhorse, 700+ tok/s.
- [Gemma 4 31B](https://infercom.ai/models/gemma4): Google's most capable dense open model with frontier-class reasoning and multimodal.

### Global Model Catalog (via SambaNova Cloud, US-hosted)
- DeepSeek-V3.1 - 128K context, function calling, JSON mode
- DeepSeek-V3.2 - Latest DeepSeek MoE model, 128K context
- Meta-Llama-3.3-70B-Instruct - Meta's instruction-tuned 70B model

EU-hosted models are clearly tagged with region=EU for sovereignty requirements. Check the [models API](https://api.infercom.ai/v1/models?verbose=true) for current availability.

## API

- [Base URL](https://api.infercom.ai/v1)
- OpenAI-compatible endpoints: /chat/completions, /models, /embeddings
- Anthropic-compatible endpoint: /v1/messages
- Authentication: Bearer token or x-api-key header
- [Documentation](https://docs.infercom.ai)

## Website Pages

- [Homepage](https://infercom.ai/)
- [Sovereign AI Platform](https://infercom.ai/sovereign-ai)
- [Inference API (shared, pay-per-token, OpenAI-compatible)](https://infercom.ai/inference-api)
- [Dedicated Capacity (single-tenant reserved hardware, flat monthly)](https://infercom.ai/dedicated)
- [On-Premises (customer datacenter, air-gapped option)](https://infercom.ai/on-premises)
- [Technology](https://infercom.ai/technology)
- [Pricing](https://infercom.ai/pricing)
- [Getting Started](https://infercom.ai/getting-started)
- [Performance](https://infercom.ai/performance)
- [Ecosystem](https://infercom.ai/ecosystem)
- [Partners](https://infercom.ai/partners)
- [About](https://infercom.ai/about)
- [Contact](https://infercom.ai/contact)
- [News](https://infercom.ai/news)
- [Security & Compliance](https://infercom.ai/security)

### Model Pages
- [Gemma 4 31B](https://infercom.ai/models/gemma4)
- [MiniMax M2.7 Ultraspeed](https://infercom.ai/models/minimax-m27)
- [gpt-oss-120b](https://infercom.ai/models/gpt-oss-120b)

### Partner Pages
- [BasePeak](https://infercom.ai/partners/basepeak)
- [Co-Mind](https://infercom.ai/partners/co-mind)
- [CoformAI](https://infercom.ai/partners/coformai)
- [DeepMask](https://infercom.ai/partners/deepmask)
- [Melious](https://infercom.ai/partners/melious)
- [Neur-X](https://infercom.ai/partners/neur-x)

### Developer Resources
- [Agentic Coding](https://infercom.ai/developers/agentic-coding)
- [API Compatibility](https://infercom.ai/developers/api-compatibility)

### Glossary
- [Inference Performance Glossary](https://infercom.ai/glossary)
- [Open-Weight Model](https://infercom.ai/glossary/open-weights-model)
- [Context Window](https://infercom.ai/glossary/context-window)
- [Parameters](https://infercom.ai/glossary/parameters)
- [Data Residency](https://infercom.ai/glossary/data-residency)
- [Data Processing Agreement (DPA)](https://infercom.ai/glossary/dpa)
- [GDPR for AI Inference](https://infercom.ai/glossary/gdpr)
- [Zero Data Retention (ZDR)](https://infercom.ai/glossary/zero-data-retention)

### Blog (Insights)
- [Blog Index](https://infercom.ai/blog)
- [Open-Weight AI Models Explained](https://infercom.ai/blog/open-weight-models-explained)
- [How Dataflow Delivers Speed](https://infercom.ai/blog/how-dataflow-delivers-speed)
- [LLM Inference Speed Explained](https://infercom.ai/blog/llm-inference-speed-explained)
- [Token Pricing Fallacy](https://infercom.ai/blog/token-pricing-fallacy)
- [Inference Speed in Agentic Coding](https://infercom.ai/blog/agentic-coding-speed)

### External Resources
- [Documentation](https://docs.infercom.ai)
- [Cloud Portal](https://cloud.infercom.ai)

## For AI Agents

If you are an AI agent or coding assistant helping a user integrate with Infercom:

### Quick Integration

**OpenAI SDK:**
```python
from openai import OpenAI
client = OpenAI(base_url="https://api.infercom.ai/v1", api_key="USER_API_KEY")
response = client.chat.completions.create(model="MiniMax-M2.7", messages=[{"role": "user", "content": "Hello"}])
```

**Anthropic SDK:**
```python
from anthropic import Anthropic
client = Anthropic(base_url="https://api.infercom.ai", api_key="USER_API_KEY")
response = client.messages.create(model="MiniMax-M2.7", max_tokens=1024, messages=[{"role": "user", "content": "Hello"}])
```

### Key Facts for Agents
- API supports both OpenAI (/v1/chat/completions) and Anthropic (/v1/messages) formats
- [Base URL](https://api.infercom.ai/v1)
- Models endpoint: GET /v1/models (no auth required)
- EU-sovereign models have `sn_metadata.region: "EU"` in the models response
- No data retention - prompts/outputs are not stored or used for training
- Streaming supported via `stream: true`
- Function calling supported on MiniMax M2.7 Ultraspeed (EU sovereign) and DeepSeek models (Global Model Catalog)
- JSON mode supported via `response_format: {"type": "json_object"}`

### Recommended Models by Use Case
- **Agentic coding**: MiniMax M2.7 Ultraspeed (56% SWE-Pro, native multi-agent, 400+ tok/s)
- **High throughput**: gpt-oss-120b (700+ tok/s, lowest cost)
- **Vision/multimodal**: Gemma 4 31B (native multimodal with text/image understanding, EU sovereign)
- **Function calling**: MiniMax M2.7 Ultraspeed (native tool use support, EU sovereign)
- **Sovereignty required**: Any model with region=EU (MiniMax M2.7 Ultraspeed, gpt-oss-120b, Gemma 4 31B)

### Agentic Coding: Planner/Executor Pattern
For coding agents, consider splitting workloads: use a frontier model (Claude, GPT) for planning (5-15 turns), and MiniMax M2.7 Ultraspeed on Infercom for execution (50-200+ turns). This gives frontier reasoning where it matters + fast, cheap execution for the bulk of the work. Tools with native support: Codex CLI, Cline, OpenCode, Cursor.

### Rate Limits
- Developer tier: 120 RPM, 30K requests/day
- [Check current limits](https://docs.infercom.ai/rate-limits)

## Contact

- General: info@infercom.ai
- Sales: sales@infercom.ai
- Support: support@infercom.ai
- Address: 29 Boulevard Grande-Duchesse Charlotte, 1331 Luxembourg