Category
Where the code runs, and what it costs to keep it there.
The category split into three different jobs, and each tool bills for a different thing. Which one is cheapest depends entirely on the shape of your team and your traffic.
These protocols are not competing for the same job. Authorization, checkout, and settlement are three different layers, and knowing which one you are shopping for settles most of the argument.
Four different products wear the same label. Which one you need depends on whether you want URLs, passages, or clean text, and the bill is decided by how many pages you fetch, not how many searches you run.
Voice finally works because the pipeline collapsed. What each platform actually charges per minute once the model passthrough is counted, and the three things that decide whether your agent feels broken.
Custom silicon against GPU platforms, and the question that settles it: what is your user doing while the tokens stream? Speed is worth paying for in exactly two of the four common workloads.
Five gateways took most of the production traffic this year. Routing, cost, and governance compared, plus the honest ops bill behind the cheap option.
Picking a Gemma 4 size for the hardware you already own, getting it running under Ollama, and wiring native function calling into a small agent loop.