Track your agents' spend at the rates you actually pay

Agent Observability shows the token and query cost of every trace from the AI agents you've connected to Monte Carlo. Those costs can now use your own negotiated per-model rates instead of list price.

A new Rate overrides section in Settings → Agent Observability lets you set your own rate for any model your agents use. Overrides sit on top of the default cost book:

• Models without an override keep the default rate.
• Deleting an override puts that model back on the default rate.
• The model field suggests models from the cost book, and you can also type any model name.
• Overrides apply to the whole account.

Every cost view for your agents uses the new rates on its next load, including past traces. Your agents' spend in Monte Carlo now matches what you're billed by your model provider.

Currently available for Snowflake Cortex agents.