Skip to main content

Models

ResponseCX is provider-agnostic: every agent carries a model field, and the platform routes the request to the matching provider. Leave it unset and the provider’s default applies.

Providers and defaults

Setting the model on an agent

Any model identifier the provider accepts is passed through, so a newer model is available the day the provider ships it β€” no platform release needed.
Match the model to the step, not the agent fleet. A common shape: a fast, cheap model (llama-3.1-8b-instant or gemini-2.0-flash) for intent classification, and a stronger model for the customer-facing reply. The classification step runs on every message; the strong model only on the ones that need it.

What the model does not decide

Model choice affects fluency, latency, and cost. It does not decide what the agent is allowed to do β€” that is Settings, Rules, and, for consequential actions, the decision gate.
Upgrading a model is a behaviour change. A stronger model follows your policies differently β€” often better, occasionally in a new wrong way. Run your evaluations against the new model before switching production traffic.
  • Agents β€” where model lives
  • Settings β€” the constraints that bound any model
  • Voice β€” realtime voice models are configured separately, per voice agent