Mycelis
Mycelis
Transparent Pricing
No base fee. No minimum term. Transparent billing for all services.
Open Source Models
Scalable & Dynamic
Deploy models like DeepSeek or Gemma 4. Scale up or down instantly. Billed per hour of runtime.
Commercial Models
0% Markup
Managed or BYOK. Connect Claude 4.7, GPT-4o or Gemini with 0% markup on provider prices.
Knowledge Bases
$0.05 / h + $0.01 / GB / h
Secure RAG for your data. Fixed base price plus storage-based billing.
OpenWebUI
$0.05 / h
The world's best interface for your team. Fully managed and connected to all your models.
Calculate your real cost
For a self-hosted ~32B-parameter model. Prices below are live GPU rates from our catalog, not estimates.
Per hour
$0.78
Per month, always on
$567
Per month, 8h/day
$137
Illustrative sizing for a ~32B-parameter model (base VRAM + 0.5 GB per concurrent user). GPU prices are live; actual cost also depends on the specific model you deploy and how long it runs — you're billed only while it's running.
Example: 100k tokens/day with Smart Routing (Gemma 4 & Claude Sonnet 4.6)
65%
> 65% less cost
Savings: Over 65% with identical output quality through intelligent task delegation.