Platform

Products

Private AI infrastructure — from compute to agents.

Compute

GPU Instances
Dedicated GPUs, billed hourly
BYOK & Managed Keys
OpenAI, Anthropic, custom

Intelligence

Agents & Smart Routing
Virtual models, cost control
Fine-Tuning (LoRA)
Your data, your models
Knowledge Bases & RAG
Documents, vector search
Semantic Cache
Lower costs with AI caching

Integration

MCP Tools
Tools, APIs, external services
API Gateway
OpenAI-compatible endpoint
Data sovereignty
On-prem, EU hosting, GDPR

Target groups

Use Cases

For enterprise, SMBs, and individual developers.

Enterprise

Compliance & Privacy
GDPR, no US cloud provider
Team rollout
Workspace, roles, API gateway
Cost Control
Smart routing reduces token costs

SMB

Quick start with managed keys
No GPU required, start immediately
Your own assistants
Chatbot with RAG + system prompt
Fine-tuning with domain knowledge
Small model, precise answers

Developers & Individuals

OpenClaw / OpenCode
Private and on-prem agents
MCP Integration
Tools directly in model context
OpenAI compatibility
Drop-in replacement, no SDK switch

Knowledge & Support

Resources

Everything you need to succeed with Mycelis.

Learn

Documentation
API reference & guides
Learn
Tutorials & video courses
Quickstart
Be productive in 5 minutes

Community & Updates

Blog
News, guides & deep dives
Changelog
What is new in Mycelis?

Support

Status
Uptime & incidents
Contact
hello@mycelis.io

Pricing

Transparent. Pay-as-you-go.
No base fee.

You only pay for actual usage. GPU instances are billed hourly, managed keys per token. No subscription, no minimum term.

GPU Instances

Dedicated GPU hardware for open-source models.

from

0,39 €/h

  • RTX 4090, A6000, A100 80GB
  • Llama, Mistral, Mixtral, Qwen
  • OpenAI-compatible endpoint
  • Hourly billing
  • GDPR — EU data centers
Start for free
Popular

Managed Keys

GPT-4o, Claude 3.5, and Gemini via Mycelis.

from

0,0003 €/1k tokens

  • OpenAI, Anthropic, Google
  • No own API key required
  • GDPR-compliant proxy
  • Usage dashboard & budgets
  • BYOK as an alternative
Start for free

Enterprise

Custom SLAs, volume discounts, on-premise.

from

On request

  • Dedicated support
  • Custom SLA (99,9%+)
  • On-premise deployment
  • Data Processing Agreement (DPA)
  • Custom quotas
Contact us

GPU instances — full price table

GPU VRAM Recommended for Price / hour Price / day (24h)
NVIDIA RTX 4090 24 GB GDDR6X Llama 3.1 8B, Mistral 7B $0.42 $10.08
NVIDIA RTX A6000 48 GB GDDR6 Llama 3.1 70B (Q4), Mixtral 8x7B $0.85 $20.40
NVIDIA A100 80GB 80 GB HBM2e Llama 3.1 70B (FP16), 405B (Q4) $2.14 $51.36
NVIDIA H100 SXM 80 GB HBM3 Llama 3.1 405B, training On request On request

All prices are net, plus VAT. Hourly billing down to the minute.

Managed keys — prices per 1,000 tokens

Provider Model Input / 1k tokens Output / 1k tokens
OpenAI GPT-4o $0.0050 $0.0150
OpenAI GPT-4o mini $0.0003 $0.0006
OpenAI o1 $0.0180 $0.0720
Anthropic Claude 3.5 Sonnet $0.0040 $0.0120
Anthropic Claude 3 Haiku $0.0003 $0.0013
Google Gemini 1.5 Pro $0.0035 $0.0105
Google Gemini 1.5 Flash $0.0001 $0.0003

Prices in EUR net, plus VAT. No extra markups compared to direct provider pricing.

IntelligenceServicesTableTitle

Service Details Price
Managed OpenWebUI Vollständig gehostete Weboberfläche $0.05 / h
Knowledge Base (RAG) Basispreis für Vektorsuche & Dokument-Management $0.05 / h
Knowledge Base Storage Speicherkosten pro Gigabyte $0.01 / GB / h

Example calculation: real production setup

Scenario: 100k requests/month

70k short requests (Llama 8B, 24h/day) Llama 3.1 70B (RTX A6000)
30k complex requests (GPT-4o, 50M tokens) $149.60
Smart Routing (VirtualModel) ~$33.00
Total / month ~$182.60

Comparison: GPT-4o direct (100k requests)

100k requests × 1k tokens avg × 0,005 € $182.60
Output tokens (1,5× input × 0,015 €) $890.00
GPT-4o only $890.00
Savings with Mycelis: ~57 %

Frequently asked pricing questions

Is there a minimum term or base fee?

No. Mycelis is fully pay-as-you-go. No base fee, no minimum term. GPU instances are billed hourly (to the minute), managed keys per token.

How can I limit my budget?

In the dashboard, you can set monthly spending limits. Once the limit is reached, new requests are blocked — no overrun possible. Email alert at 80% of the limit.

Can I switch from GPU instances to managed keys?

Anytime. Both deployment types can be active at the same time. With Smart Routing, you can even switch automatically between both.

Are volume discounts available?

For volume above 500 €/month, we offer custom conditions. Contact sales@mycelis.io for a quote.

Start for free — pay only for what you use.

Starting credit included. No credit card required to get started.

Start for free Questions about Enterprise?