LatentKit

What is LatentKit?

LatentKit is a route-based AI gateway for teams that want one integration surface and centrally managed provider selection.

LatentKit sits between your application and AI providers. Your code sends standard task payloads; your workspace configures which providers and models each API key uses through published routes.

What LatentKit does

You want to…LatentKit gives youWhere
Swap providers or models without redeployingRoute-based routingRoutes & policies
Survive a provider outageOrdered failover plus health checksRoutes & policies
Send different kinds of work to different modelsPurposesPurposes
Trade speed against quality per requestResponse profilesRoutes & policies
Use your own provider keysBYOK connectionsProviders
Handle images, audio, embeddings, videoCapability routingREST API
Reproduce a resultSeeded deterministic routingDeterminism
Run work asynchronouslyQueue endpointQueue
See spend per app, route, and modelUsage analyticsConsole → Usage

Route-based by design

Application requests do not choose a provider or model. Instead:

  1. You create an API key in the console.
  2. The key is assigned a published route (policy).
  3. Your app sends chat, embedding, or image payloads to /v1/*.
  4. LatentKit resolves the route and executes against eligible providers.

This keeps application code stable while your team tunes cost, latency, and fallback in the console.

BYOK and Platform Access

Routes can use bring-your-own-key (BYOK) provider connections or Platform Access managed credentials billed through LatentKit credits. The integration shape is identical — only billing and credential ownership differ.

First mental model

Think of LatentKit as three layers:

LayerManaged inWhat it does
Application codeYour appSends task payloads like messages, input, or prompt
API keyConsoleAuthenticates the app and points to a published route
RouteConsoleChooses eligible provider/model attempts, failover, and response depth

If the route changes, your application code usually does not.

A route usually holds several models. When some jobs want a particular one — extracting data versus drafting prose, say — a purpose lets your application ask for it by a name you chose, still without naming the model itself. Change which model that name means, and your application does not change.

Who this is for

  • Product teams shipping AI features without hard-coding provider SDKs per model
  • Platform teams that need centralized routing, usage tracking, and key management
  • Developers using AI coding tools who want a secure backend integration pattern

Next steps

On this page