Estimate Time
estimate_timeRead-onlyIdempotent
Estimate how long one model call or a whole job takes—on a usual day and a slow day—from your own timed runs, using logged run history when time matters more than cost.
Instructions
Estimate how long one call and a whole job take, as a usual time and a slow day, from the user's own timed runs of that model called that way (kept by log_run). Use when the question is time, not money, and some runs have been logged; it says so when none have. Not for cost (estimate_cost) or for a job you have a promptfoo sample of (forecast_job gives time and cost together).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model": "<model>",
"input_tokens": "<input_tokens>",
"output_tokens": "<output_tokens>"
},
"name": "estimate_time"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| way | No | How the model is called | api |
| calls | No | How many calls the job makes | |
| model | Yes | A model name, as the catalogue or Ollama names it | |
| thinking | No | Thinking turned on | |
| concurrency | No | Calls running at once | |
| input_tokens | Yes | Prompt tokens per call | |
| output_tokens | Yes | Answer tokens per call, including hidden thinking |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||