Deploy SAM
All Features Cloud & Costs

Pick your clouds.
See what they cost.

Connect Hetzner, Scaleway, GCP, or four other providers. You pay them directly at their prices, and SAM shows how many server hours each person used.

  • Add machine types by region from each connected account, with vCPU, memory, disk, and a monthly price in the provider’s own currency. Nothing joins a pool on its own
  • Project, user, and installation scopes, resolved in that order
  • How agents are placed (Balanced, Pack, Spread, Smallest fit) and what happens when a provider is out of capacity (wait and retry, try other allowed machines, or stop with an error), per pool
  • Nodes are reused when they fit and stay warm for 30 minutes
  • Settings → Usage tracks token spend by model and day against a monthly budget; Admin → Costs and Admin → Usage cover the whole installation
Read the guide
Project compute pool editor marked Ready with 7 machines in the pool. Hetzner, Scaleway and Vultr accounts each have an on switch and list their machines with region and monthly price: cx23 in Falkenstein for €5.49, PLAY2-MICRO in Paris for €7.99, and five Vultr machines in Frankfurt, Chicago and New Jersey from $24.00. Below, Available machines starts with search, account and continent filters, and a maximum price per currencyProject compute pool editor marked Ready with 7 machines in the pool. Hetzner, Scaleway and Vultr accounts each have an on switch and list their machines with region and monthly price: cx23 in Falkenstein for €5.49, PLAY2-MICRO in Paris for €7.99, and five Vultr machines in Frankfurt, Chicago and New Jersey from $24.00. Below, Available machines starts with search, account and continent filters, and a maximum price per currency

Choose exact machine types and regions

Available machines lists one row per account, machine type and region, such as cx33 at Hetzner in Nuremberg or PRO2-S at Scaleway in Paris, with vCPU, memory, disk, and a monthly price in the provider’s own currency. Add the ones SAM may rent: nothing joins a pool on its own. Search, filter by account, continent, size or price, sort any column, and switch a whole account off without losing its machines. You also choose how agents are placed on servers (Balanced, Pack, Spread, or Smallest fit) and what SAM does when a provider is out of capacity: wait and retry, try other allowed machines, or stop with an error.

The Available machines table: search, account and continent filters, minimum vCPU and memory, a maximum price for dollars and one for euros, and Hide unavailable. Rows list each machine with its account, vCPU, memory, disk, region and monthly price, with Remove on machines in the pool (cx23 in Falkenstein, PLAY2-MICRO in Paris, Vultr machines in Chicago and Frankfurt) and Add on the rest (cpx31 in Helsinki, cx33 in Nuremberg, PRO2-S in Amsterdam and Paris)The Available machines table: search, account and continent filters, minimum vCPU and memory, a maximum price for dollars and one for euros, and Hide unavailable. Rows list each machine with its account, vCPU, memory, disk, region and monthly price, with Remove on machines in the pool (cx23 in Falkenstein, PLAY2-MICRO in Paris, Vultr machines in Chicago and Frankfurt) and Add on the rest (cpx31 in Helsinki, cx33 in Nuremberg, PRO2-S in Amsterdam and Paris) One row per machine and region, in each provider’s own currency

See why a node was chosen

Resource requirements resolve from task, trigger, skill, and agent profile down to project and platform defaults. The chat’s infrastructure panel shows the resolved requirement alongside the placement decision — which node won, and why.

Chat session details showing the requested vCPU, memory, and disk, the observed and configured hardware, the current compute pool with its strategy, and a saved placement decision explaining why a warm Hetzner node was reusedChat session details showing the requested vCPU, memory, and disk, the observed and configured hardware, the current compute pool with its strategy, and a saved placement decision explaining why a warm Hetzner node was reused Every placement decision is explained, not just made

One fleet, every provider

The Nodes page lists every machine across every connected provider side by side, with health, CPU/memory/disk usage, and price. Follow-up work reuses a warm node instead of waiting on a fresh boot.

Nodes page listing Hetzner, Scaleway, and Vultr machines side by side with status, health, observed and configured hardware, offering price, CPU, memory, and disk usage, and the workspaces on eachNodes page listing Hetzner, Scaleway, and Vultr machines side by side with status, health, observed and configured hardware, offering price, CPU, memory, and disk usage, and the workspaces on each One fleet view across every connected cloud provider

Token and compute usage, per user

Settings → Usage shows your AI usage by model and by day, against a monthly budget, for traffic routed through the SAM AI proxy. It also tracks your compute usage in node-hours against your quota. Admins get the installation-wide view — LLM spend by model, day, and user with a projection, plus per-user node usage — in Admin → Costs and Admin → Usage.

Settings → Usage page showing total cost, requests, and input and output tokens, a per-model breakdown, a daily cost trend, and budget controls with daily token limits and a monthly cost capSettings → Usage page showing total cost, requests, and input and output tokens, a per-model breakdown, a daily cost trend, and budget controls with daily token limits and a monthly cost cap Token usage by model and by day, against a monthly budget
Previous Comments Next Schedules & Triggers

Ready to try SAM?

SAM is open source. To deploy it, you need a Cloudflare Workers Paid plan, a domain on Cloudflare, and a GitHub account.

Deploy SAM Read the Docs