Cost was the wedge. Routing is the product. What's shipping, what changed, and what Frugal Cloud will add.
A model's leaderboard position tells you how it does on the leaderboard's distribution, not yours. Fifty queries from your own logs beat it every time.
The moment an MCP server leaves stdio for HTTP, it becomes a network service with everything that implies. The hardening playbook I actually run.
Six fields, one JSONL file, first deploy. The instrumentation playbook that answers every question you'll be asked about your agent in month three.
Inference got an order of magnitude cheaper and everyone noticed. The per-call price of search, scrape, and browse barely moved, and almost nobody did.
One captured run, walked rung by rung: 0 hits in 529ms, a fall-through, 3 hits at $0, and exactly what lands in the ledger afterward.
Autocomplete, overnight reports, and research tasks live in different corners of the same triangle. Products that pick one corner for everything overpay in all three.
Your tool chain will break in exactly five ways. Here's what each one looks like in the logs, and what a chain that survives it does differently.
Pipeline, fan-out/fan-in, escalation ladder, verify loop. Each pattern has a signature failure: a place the bill or the latency hides until production.
Every middleman reselling API calls adds margin and a second data controller. The case for bring-your-own-key as trust architecture, tradeoffs included.
Everyone budgets for tokens. Then a teardown shows search at 54% of task cost. The math behind why research agents multiply search spend.
Paid providers should be the fallback, not the default. The case for making your agent's first call free, with the failure modes stated honestly.
Most teams discover their switching cost the day a price hike or outage forces the move. Ask these six questions while the answer is still cheap.
An empty result set arrives as a 200 and gets treated like a 500. The provider didn't fail — it answered. What you do next should depend on whether that answer cost money.
Thirty real queries with expected answers will save you more money than any discount negotiation. You can't swap models, cut costs, or route traffic without a way to score the output.
One transport is a subprocess and a pipe. The other is a service you now operate. Which MCP transport you pick is really a question about who connects, from where.
Your invoice knows what you spent by provider and month. It has no idea what one agent run cost. Stamp the cost on the response envelope and the question answers itself.
A backup provider you've never exercised is a config value, not a plan. The rules I use to order rungs, avoid paying twice, and break flapping providers out of the chain.
Escalation isn't a cost hack, it's an architecture: the cheap model handles the bulk, the expensive one earns its rung. The same ladder logic that works for tool calls.
An agent chains tool calls in sequence, and sequences are where tail latency compounds. How to set a budget, split it per call, and spend it on fallback rungs.
The demo is the easy 20%. This is the other 80% — seven checks that decide whether your AI feature survives contact with real users and a real invoice.
The term gets used for two different things. Here's what a router actually contains — policy, health, fallback, accounting — and the honest cases where you should skip one.
No replatforming, no procurement cycle. Seven changes you can ship by Friday that attack the parts of an agent bill nobody is looking at.
Forget the spec tour. This is what MCP looks like from the inside of a server that runs every day: the parts that stuck and the parts that didn't.
Your agent is a distributed system with a single point of failure per dependency. The playbook for staying up when a provider doesn't.
Model selection for agents isn't a leaderboard question. It's five workload questions, and most teams skip straight to the logo.
Five providers, one capability, a price range from free to half a cent. An analysis of what you're actually paying for when your agent searches the web.
Agents pick providers by what got wired in, not by price. Here's how a routing layer walks every tool call down a ladder — free first, paid as fallback.