Cost Forecast & Model Router
Know what a request will cost before you send it, and stop paying top-model prices for simple steps. The cost forecast shows an estimate in the composer as you type. The model router sends simple steps of a run, such as reading files or writing a commit message, to a cheaper model, and keeps the hard parts on the model you picked.
Turn it on
- Open Settings › Tools › Game changers.
- Turn on Cost Forecast.
- Turn on Model Router if you also want cheaper models for simple steps. It is off by default.
| Setting | Default | Effect |
|---|---|---|
ingot.agent.costForecast.enabled | off | show the estimate in the composer |
ingot.agent.costForecast.warnAbove | 1.00 | estimated cost in USD that shows a warning before sending |
ingot.agent.router.enabled | off | send simple steps to a cheaper model |
Cost forecast
As you type, a chip next to the model in the composer shows the estimate for the request:
≈ $0.18 · 42k tokens
The estimate is the expected tokens (your prompt, attached files, rules, chat history and a typical reply) multiplied by the price of the selected model. Hover the chip to see the breakdown. Local models show $0.00. With your own API key, the estimate uses the provider's list price.
Over the threshold
When the estimate is above ingot.agent.costForecast.warnAbove, the chip turns amber and Send asks first:
This request is estimated at $2.40 (310k tokens), above your $1.00 limit.
| Choice | Result |
|---|---|
| Send anyway | the request is sent as is |
| Use a cheaper model | pick another model; the estimate updates |
| Cancel | back to the composer, nothing is sent |
The forecast is an estimate. The real cost of a run depends on how many steps the agent takes and is shown in Models & limits usage as usual.
Model router
With the router on, every step of a run is sorted before it is sent:
| Step | Model |
|---|---|
| reading and searching files, summarising tool output, short edits, commit messages | a cheaper model |
| planning, multi-file edits, debugging, anything the agent marks as hard | the model you picked |
- Pick your model in the composer as usual.
- Send the request.
- Steps that went to a cheaper model get a note on their tool card, with the model that ran them:
- Click the note and choose Rerun on my model if a routed step wasn't good enough.
The router only uses models you already have access to, through Ingot or your own keys, and it never picks a Chinese-origin model, even if one is enabled in your model list.
The model you accept becomes a habit
Ingot keeps track of which model you keep for each kind of task, and which routed steps you rerun on your own model. Once a pattern is clear, the router follows it: for example, it stops routing test fixes if you always rerun them. These preferences are saved with your habits in .ingot/habits.json (git-ignored, never leaves your machine):
Silver notes
| Note | When |
|---|---|
| Routed to cheaper model | a simple step ran on a cheaper model |
| Saved to Habits | your model choice for a kind of task was learned |