DeployCost
Build a stack

Stack recommendation

Cheapest stack for a AI chatbot / RAG app

App + vector DB + storage + inference (hosted LLM API or self-hosted GPU).

MVPTractionScaling

Cheapest

Recommended
$42/mo
incl. $18/mo egress
  • App compute (PaaS or VPS)
    small · Hetzner (On-demand)
    $4/mo
  • Managed database
    db_small · Neon (On-demand)
    $19/mo
  • Object storage
    obj_free_egress · Wasabi (On-demand)
    $0/mo
  • LLM API
    llm_cheap · Google Cloud (On-demand)
    $1/mo

Assumptions (MVP)

  • paas|vps: hours=730
  • managed_db: hours=730, engine=vector
  • object_storage: storageGb=20, egressGb=50
  • llm_api: mTokensIn=5, mTokensOut=2

Editable usage sliders are coming to /build; today these are sane defaults. Costs are effective monthly estimates, not quotes.