AI models
Which model answers your calls and chats, what premium models change, and how model choice shows up on your bill and in your call quality.
Models are managed for you
SIMCOAI selects and operates the AI models behind your front desk. You choose a tier rather than wiring up a provider account.
If a model provider has a problem, SIMCOAI is designed to fall back rather than fail the call outright. Provider incidents that affect service appear on the status page.
Standard and premium
| Standard | Premium | |
|---|---|---|
| Typical use | Everyday reception, FAQs, straightforward capture | Nuanced conversations, longer context, harder judgement calls |
| Speed | Generally faster to first reply | Can be slower - visible in first reply latency |
| Cost | Included in your plan allowance | Consumes more AI usage; may need the premium add-on |
| When to switch | Default | When transcripts show the AI missing nuance a person would catch |
How model use is billed
Model usage is metered as AI usage against your plan. Premium models consume more of it for the same conversation.
Careful. Switching everything to premium is rarely the right first move. Check whether the problem is actually missing knowledge - see knowledge and documents - because a better model cannot invent facts you never supplied.
See usage and limits for how AI usage is counted, and add-ons for premium model access.
A sensible way to decide
- Start on standardIt handles the majority of front-desk conversation.
- Read a day of transcriptsLook for specific failures, not general impressions.
- Separate the two failure typesMissing knowledge is a knowledge fix. Missed nuance is a model question.
- Change one thingThen compare the next day of calls against the same measures.
Expected result
A decision based on your own transcripts rather than on which tier sounds better.