Compare

Flow AI vs the alternatives

There are three ways to route inference. They all give you an endpoint — the difference is what they optimize for. Flow optimizes for the cheapest model that completes the task, billed at true cost.

Direct API

Call one provider's model yourself. Full control, but you pay list price, pick the model by hand, and have no failover when it's down or slow.

Token routers

OpenRouter-style: send a chosen model across its hosts and pay a markup on tokens. Cheaper sourcing, but it never knows whether your agent's task actually finished.

Flow AI

Managed, completion-aware routing: the cheapest model that completes the task, billed at true pass-through cost + 2.5% — plus a community capacity network you can earn from.

Side by side

Flow AIToken routersDirect API
Pricing modelPass-through cost + 2.5%Markup on token pricesList price (no routing)
Routes byWhether the task completesToken price / availabilityN/A — you pick
RoutingCheapest model that completes, per requestPick a model, route across its hostsYou pick + call one model
Quality cascade (escalate only if needed)YesNoNo
Prompt-cache-aware billingYes — billed at the cache rateVariesYes (per provider)
Failover across providersYes — automaticYesNo
Community capacity & earn (Hive)Yes — share spare capacity, earn creditsNoNo
Drop-in for OpenAI / Anthropic / CodexAll threeOpenAI-styleNative only

“Token routers” covers OpenRouter-style services that route a chosen model by token price and availability.

The core difference

Completion > cheap tokens

A model that narrates a plan instead of calling the tool is worse than useless — and a token-router will happily send your agent there because it's cheap per token. Flow measures whether the work actually got done and routes to the cheapest model that finishes the job, escalating only when it has to. You get the savings of a router with the reliability of picking the right model.


Switch in one line.

Change one base URL — keep your harness, lose the markup.