Architecture

All resources

When dedicated infrastructure beats an API

The crossover is not a matter of taste. It is a calculation, and most teams can do it from data they already have.

· 7 min read

Start from utilisation, not from price

The instinct is to compare a per-token rate against an hourly instance rate. That comparison is meaningless without a third number: how much of that instance you will actually keep busy.

Dedicated capacity is cheap per request only when it is well utilised. A workload running at 15% utilisation on reserved hardware is usually more expensive than the same workload on a metered API, no matter how good the headline rate looks.

The four numbers that decide it

You can get a defensible answer from four figures, all of which are already in your logs.

  • Sustained request rate: the median, not the peak.
  • Peak-to-median ratio: how spiky the demand curve really is.
  • Token shape: average input and output length per request.
  • Quality floor: the smallest model that still clears your bar.

Peak shape matters more than volume

Two workloads with identical monthly volume can land on opposite sides of the line. A steady background batch job utilises reserved capacity beautifully. A workload that sits idle for twenty hours and then triples for four does not.

This is why the useful mitigation is rarely 'buy more capacity'. It is to keep an external API in place as an overflow path, size dedicated capacity to the sustained band, and let the spike spill over. The economics come from the base load; the resilience comes from the overflow.

The workloads that should not move

It is worth being explicit about the negative case. Low-volume workloads, highly variable ones, anything that genuinely needs the newest frontier model the week it ships, and anything where the quality bar cannot be met by a model you can run yourself. These belong on an external API, and moving them is value destruction dressed up as cost saving.

A migration that moves the right 60% of your spend and deliberately leaves the rest alone is a better outcome than one that moves everything.

The short version

Work out sustained rate, peak ratio, token shape and quality floor per workload. The crossover falls out of those four numbers, and it will not be the same answer for every workload you run.

Read next

The anatomy of a per-token bill

Where the money actually goes when you run AI at volume, and why the invoice grows faster than the value it produces.

Next step

Curious whether this applies to your workload?

Tell us how many people are in the firm and what kind of client work they handle. We will tell you what it would cost to give all of them a private workspace, before anyone talks about a contract.

Talk to Runvo

Tell us the size of the firm and what your client contracts require.