Non-enterprise plans now run on Synthflow LLM
Accounts that are not on an enterprise plan run on Synthflow LLM, our model built for voice agents and tuned for real-time phone conversations, with lower latency and more natural turn-taking than a general-purpose model. Third-party models, including the GPT family, are no longer available on these plans.
Synthflow LLM is the only option in the AI Model selector under General settings. Existing agents are migrated automatically, so no action is required in the dashboard.
API requests that set llm to a GPT value are still accepted and the response looks normal, but the agent stays on Synthflow LLM. Nothing in the response signals that the value was ignored, so update that field in your own automations.
Enterprise accounts are unaffected by this change.