Choose Your Model

The right model for each job.

Fast routing does not need the same brain as a messy support investigation. Pick the model that fits each agent or helper — so quality stays high where it matters and spend stays sane everywhere else.

How it works

Match the model to the work

  1. 01

    Create the agent

    Start with the job — receptionist, support, lead qualifier, or a focused subagent.

  2. 02

    Choose a model

    Pick the provider and model that fit that job's difficulty and latency needs.

  3. 03

    Tune as you learn

    If answers are thin, step up. If costs climb on simple FAQs, step down.

  4. 04

    Mix across helpers

    The main agent and its subagents can use different models for different work.

Capabilities

Why model choice belongs in a no-code builder

You should not need an engineering team to change brains.

Per-agent control

Support can run a stronger model while a simple router stays light and fast.

Per-helper control

A knowledge search helper and a summarizer do not have to share the same model.

Cost that matches usage

Pair model choice with Embage's action-based pricing so short FAQs stay cheap.

Quality where it counts

Use a stronger model for long investigations, refunds, or ambiguous questions.

Swap without rebuilds

Change the model in settings — keep knowledge, datastores, and tools as they are.

Fits the no-code flow

Model choice is a field in the builder, not a deployment pipeline.

In practice

Simple rule of thumb

Start practical, then adjust from real conversations.

Receptionist & routing

Prefer faster, lighter models when the job is greet, classify, and hand off.

Deep support

Prefer stronger models when policy nuance and multi-step troubleshooting matter.

Structured extraction

Post-conversation reviewers often want a model that follows field shapes carefully.

High-volume FAQs

If most chats are short and knowledge-backed, keep the main model lean.

FAQ

Common questions

Do I lock into one model forever?

No. You can change models as your traffic, quality bar, or budget changes — without rebuilding the agent.

Can subagents use different models?

Yes. That is one of the main reasons to split work into helpers — each job gets the brain it deserves.

How does this relate to pricing?

Embage pricing stays close to model usage and completed actions, so choosing a lighter model for simple work shows up in what you spend.

Test Only

Your first friendly agent
is about 10 minutes away.

We’re in a public test — jump in, build a chatbot or voice agent, and forgive a few rough edges. Data may reset.

Test environment · No credit card required