Router

Route requests using your rules.

Create a Router by defining paths that decide where each request should go.

  • Add multiple routes with a Default Inferencer.
  • Define routing rules using Conditions and Condition Groups.
  • Use Classifiers to route requests based on meaning.
ApplicationRequestResponseRouterFirst matching route winsRoute 1Route 2DefaultModel 1Failovernested inferencerModel 2

General
Routes
Common
Tags
More
*Name
Coding vs General Router
*Default Inferencer Type
Please select oneMODEL▼

MODEL
LOAD_BALANCER
FAILOVER
RACE
ROUTER
GATEWAY
*Default Inferencer
Please select oneGeneral Chat Model▼

General Chat Model
Code Expert Model
Description
Please enter descriptionCoding questions go to the code model.
Router applied
Apply

Define your Router

Choose the Default Inferencer that should handle requests when none of your routing rules apply.

  • Use any inferencer as the default, from a Model to a Failover.
  • The default can provide a simple destination or another execution flow for unmatched requests.

Add your Routes

Each route pairs a Condition with the inferencer that should answer when it matches.

  • Routes are checked in their Order, and the first matching route decides where the request goes.
  • A Condition can evaluate words, length, tags, or the result of a Classifier that classifies the request based on its content.
  • The Not option reverses a condition, so one rule can handle both directions.
General
Routes
Common
Tags
More
*Routes
*If CCG Type
Please select oneCondition▼

Condition
ConditionGroup
*If CCG 1
Please select oneIs Coding Question▼

Is Coding Question
Is Long Text
*Then Inferencer Type
Please select oneMODEL▼
*Then Inferencer
Please select oneCode Expert Model▼

Code Expert Model
General Chat Model
*Order
Order1
Router applied
Apply

General
Routes
Common
Tags
More
Validator
Please select oneJSON Response Validator▼

JSON Response Validator
YAML Config Validator
Budget
Please select oneMonthly Cost Cap▼

Monthly Cost Cap
Daily Spend Guard
Memory
Please select oneSupport Chat Memory▼

Support Chat Memory
Wiper
Please select oneThirty Day Cleanup▼

Thirty Day Cleanup
Log Group
Please select oneProduction Logs▼

Production Logs
Applied
Apply

Expand what your Router can do

You can extend the Router with functionality for validation, cost management, conversation context, data cleanup, and debugging. Your application keeps calling the same endpoint, while each addition handles its specific responsibility on every request.

  • A Validator makes sure every answer arrives in the format you expect, such as clean JSON.
  • A Budget caps what the Router can spend per run, chat, day, week, or month.
  • A Memory lets conversations remember earlier context, while a Wiper clears stored data according to your policy.
  • A Log Group keeps a record of requests for debugging and review.

Select the functionality you need, and click Apply.


What a Router changes for your application

Send different requests to different inferencers through one endpoint, using the routing logic you define.

Route using your own conditions

Define any Condition you need and send matching requests to the inferencer you choose.

Route intelligently by content

Use a Classifier to understand the content of a request and route it based on its classification.

Always have a fallback

When no Condition matches, the Default Inferencer handles the request. Any inferencer can be the destination, including a Model, Load Balancer, Failover, Race, or another Router.

A Router can also stand inside any other inferencer, including a Load Balancer, Failover, Race, or Gateway.



Ready to build your AI execution flow?

Configure your first inferencer with help from our team.