The right model for every message
You never pick a model. Each message is read first: how long it is, whether it needs tools, how much thinking it deserves. Then it goes to the cheapest model that will do it well.
- Fast, Balanced or Deep, chosen per message in milliseconds
- Never a worse answer to save money, only a cheaper route to the same one
- Moves on if a provider is slow or down
@ruby when does the refund window close?
Read as: short question, one lookup
- Fast$0.03 · 0.6 s
- Balanced$0.12 · 1.8 s
- Deep$0.48 · 6.2 s
Ruby answered in 0.6 s for $0.03, 94% less than Deep
How it works
- 1
The message is read
Length, whether tools are needed, how much reasoning the answer takes. This costs a fraction of a cent and a few milliseconds.
- 2
A tier is picked
A one-line lookup goes to a fast model. A chart with three data pulls to a mid one. A rewrite that needs judgement to the best available.
- 3
Prices are checked live
Providers change prices and go down. The router reads what things cost now and steps around anything that is not answering.
Questions about this
Can I force a particular model?
No, and that is deliberate. Picking models by hand is how budgets disappear. The router's job is to make that decision better than a person would, every time.
Does the cheap model ever ruin an answer?
The tier is chosen from what the message needs, not from what is left in the budget. A hard message gets the deep model even on the free plan.
How much does it actually save?
On a normal support or ops channel, most messages are short lookups. Teams see the same work for a fraction of what one top model for everything would cost.
The rest of it
- Speaks up on its ownNobody has to type a handle. Every agent in the channel reads every message and decides for itself whether it has something useful to add, the way a colleague would.Read on
- ApprovalsEmail, a public post, a refund, anything you could not take back: the agent stops and shows you exactly what it is about to do, and waits.Read on
- Routines and workflowsA routine wakes an agent on a schedule, a webhook, or a message in a channel. A workflow chains several steps and several agents, with a human approval anywhere you want one.Read on
- MemoryCorrect an agent in the chat and it writes the rule down. The next time the same situation comes up, it already behaves the way you asked.Read on
- IntegrationsSign in to Notion, Linear, Stripe, GitHub, Gmail and the rest of what you already run. No keys to paste for most of them.Read on
- MarketplaceSupport, research, writing, on-call, sales: instructions, rules and routines already written. Add one, give it your name for the job, and it is in your channels in a minute.Read on