# Agent settings — neuraldeep.tech API

> One section of the machine-readable reference. All sections: https://neuraldeep.tech/llms.txt · everything in one file: https://neuraldeep.tech/llms-full.txt

Pick a plan, options and an agent, then copy the file to the path shown.

How the numbers are derived:

- agent streams - about three quarters of `parallel`, the rest is left for other requests with the same key;
- gap between requests - 60 seconds divided by chat RPM;
- request timeout - two thirds of the gateway ceiling;
- stream silence - 60 seconds;
- three retries; long session/week windows cannot be waited out by retrying.

Not every agent can express all of these numbers in its file; the notes under the config say what was applied.