Platform

Products

Private AI infrastructure — from compute to agents.

Target groups

Use Cases

For enterprise, SMBs, and individual developers.

Knowledge & Support

Resources

Everything you need to succeed with Mycelis.

Guide · 10 min min read

Deployment Guide

Deployment types

Type Description Cost
GPU Instance Dedicated model on RunPod GPU Hourly
Managed Keys OpenAI / Anthropic / Google via Mycelis Per token
BYOK Your own provider key Per token
Shared Pool Shared infra for selected models Per token

1) GPU instance

Best for data sovereignty and predictable performance.

  1. Go to Dashboard → My Models → New Deployment
  2. Select GPU Instance
  3. Pick a base model (or trained model)
  4. Select GPU type and runtime schedule

2) Managed keys

Use OpenAI, Anthropic, or Google without managing external credentials.

  1. Select Managed Key
  2. Choose provider and model
  3. Deploy instantly (no provisioning delay)

3) BYOK

Use your own provider key through Mycelis.

  1. Select BYOK
  2. Choose provider (openai, anthropic, google, or custom URL)
  3. Store your API key securely

Next steps