Tutorial · 4 min

How to use Run History & Cost Logs

Every AI run, reproducible and costed

A full log of each run: the prompt, the model chain that answered, tokens consumed and the cost, so any output can be traced and repeated.

Before you start

  • A signed-in SciExpert account

Steps

  1. 1

    Open Run History & Cost Logs

    From the workspace sidebar choose Run History & Cost Logs. On a phone, open the All menu and tap Run History & Cost Logs.

  2. 2

    Set up your inputs

    A full log of each run: the prompt, the model chain that answered, tokens consumed and the cost, so any output can be traced and repeated. Start with the smallest realistic input so you can check the output before scaling up.

  3. 3

    Run it

    Run the tool and check the first output: prompt, provider and fallback chain recorded.

  4. 4

    Review what came back

    Work through the results: token counts and cost per run; reproducible run details for your methods section; filter by service, date or project.

  5. 5

    Save or export

    Save the configuration as a preset if you will repeat it, and export the output when you need it outside SciExpert. Your inputs persist across refreshes and sign-ins.

Tips

  • Start with a small input, verify the output, then scale up.
  • Save a preset once the configuration works so you can reuse it across papers.

Troubleshooting

Nothing happens when I run it

Check that every required field is filled and that your plan includes this service — locked services show a padlock in the sidebar.

The output is not what I expected

Reduce the input to a single item, confirm the result is correct, then add the rest back gradually.

More tutorials

Browse all 79 tutorials →