AI models
The SIMCOAI models by name - which one answers, what each is for, and how the choice shows up in your call quality and on your bill.
The SIMCOAI models
Every SIMCOAI model is a configuration SIMCOAI builds and runs on top of a frontier base model: its own instructions, its own context routing, its own response deadlines, token budgets and guardrails. What you choose between is the configured assistant, not the engine - which is why the engine underneath can be replaced with a better one without your choice or your call behaviour changing.
| Model | What it is for | Speed |
|---|---|---|
| SIMCOAI Cura 1 | Routine opening hours, order updates and message taking at high volume. | Fast |
| SIMCOAI Sermo 1 | Live calls, short chats and first responses where somebody is waiting. | Fastest |
| SIMCOAI Mens 1 | Everyday chat and dashboard work needing a fuller answer. | Balanced |
| SIMCOAI Vis 1.1 | Our most capable current model for complex policies, refunds, setup advice and multi-step work. Uses premium allowance. | More deliberate |
| SIMCOAI Hermes 1 — Mini | Experimental direct voice conversation with the smaller model. Choose in a phone profile; currently limited to developer accounts. | Being validated |
| SIMCOAI Athena 1 — Full | Experimental direct voice conversation with the Full model. Choose in a phone profile; currently limited to developer accounts. | Being validated |
Models are managed for you
Choose Cura 1, Sermo 1, Mens 1 or Vis 1.1 in Dashboard → AI Models. SIMCOAI operates each configuration for you. Hermes 1 Mini and Athena 1 Full are experimental choices in per-number phone profiles. Developer accounts can save a choice for subsequent calls on that phone profile. Other accounts continue with current Call Studio calling. They use a fixed native voice rather than the Call Studio voice. There are no customer-owned API keys and no custom endpoints.
How the choice is made
In AI Models, choose a preferred model and whether to use it for every request or let SIMCOAI decide. Automatic choice uses Sermo for routine live calls and can use Vis for complex work within your premium allowance. A fixed choice applies to calls too, so Mens or Vis can take longer to answer.
| Profile | Model | Notes |
|---|---|---|
| Economy | SIMCOAI Cura 1 | Routine requests |
| Fast | SIMCOAI Sermo 1 | Default for live calls |
| Balanced | SIMCOAI Mens 1 | Everyday work |
| Premium | SIMCOAI Vis 1.1 | Included in Growth and Pro with limited usage; more with the add-on |
- Always use selected model
- Every request uses the model you selected, subject to plan limits.
- Let SIMCOAI decide
- Routine requests stay quick. Complex work uses Vis when premium use is allowed. If a limit blocks Vis, automatic routing uses Mens so the request can still be answered.
How model use is billed
SIMCOAI Vis 1.1 uses two premium usage units per answer. Growth includes 50 units a month, Pro includes 250, and the Premium AI Models add-on adds 1,000. Standard AI usage is metered separately.
See usage and limits for how AI usage is counted, and add-ons for premium model access.
A sensible way to decide
- Start where the defaults put youLet SIMCOAI decide: Sermo handles live calls, Mens handles everyday chat, and Vis handles harder work when allowance is available.
- 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 model sounds better.