Model
Picking the language model that powers your agent, and the trade-off between latency, quality and cost.
The language model reads the system prompt and the conversation so far, decides what to say, and decides which tool to call.
What the picker shows
The Model drawer holds the Reply model picker. It lists the models available to your workspace, with models suited to live calls first and Show all models for the rest. Each entry shows:
- the model name;
- the tier: Fast, Balanced, Power or Speed;
- the residency, Australia or Global;
- the latency;
- the per-minute model rate.
You select one model. That choice lands in a draft and changes nothing on live calls until you publish.
The tiers and how residency works are on Available models.
The tiers
| Tier | What it is for |
|---|---|
| Fast | The everyday default. Quick to respond, dependable on tool calls, low cost. |
| Balanced | More reasoning headroom at a higher rate, still quick enough for a call. |
| Power | The most capable models for the hardest calls, highest rate, usually slowest. |
| Speed | The lightest, lowest-latency models for simple, high-volume calls. |
New agents start on the default model, a Fast-tier model that runs in Australia. In our testing its model family is the most reliable at tool-calling, and it is fast enough that the caller does not hear a gap. Start here, and move up only when the agent is genuinely getting calls wrong.
When to change the model
Change the model when you have evidence, not a hunch:
- The agent picks the wrong tool or fumbles an unusual call: try a stronger tier.
- Replies are correct but the caller is left waiting: try a faster model.
- Cost is the concern and calls are simple and repetitive: a Speed-tier model may be enough.
Use the test panel and evals to compare the old model against the new one. A model is reliable only if it behaves correctly on every call, not most of them.
What a minute costs
The per-minute rate shown in the picker is the model component rate, not necessarily the rate charged to your workspace. A usage-based rate can also include speech recognition and speech synthesis. Vertical AI public plans use their plan rate after the included allowance, except that a premium model whose rate is above A$0.40 a minute bills at its own rate. Negotiated rates can differ. Check Plan and usage and Billing before estimating the cost of a model change.