1. Find the spend
Usage & Limits on every plan. Insights on Enterprise.
2. Lower it per agent
Skills, model, context, unused work, then BYOK.
1. Find the spend
In any chat, select the credit count next to the name. You will see Chat & Reasoning, Tool Calls, Compute, Orchestration Fee, and any other types that chat was charged for.
Where to see what a chat cost · Organization Insights
2. Lower it per agent
Work the expensive agents first.Add a skill
Most agents have no skills. Without a playbook, the agent guesses your process every chat — extra tool calls, extra retries, extra tokens.- Open the agent’s Skills section.
- Select + Skill.
- After a chat that went well, tell it: “Turn this into a skill” or “Update your instructions so you always do it this way.”
Check the model
Open Agent Preferences.
Auto is Gumloop’s model router, not a provider model. It already aims for the cheapest tier that should still do the job, and it can move up mid-run. Pinning a cheaper model on an Auto agent is not always a win: easy messages may already be cheap, and hard ones may get worse.
If you pin a model, pick the smallest one that still does the work.
Choose the Right AI Model · Auto
Cut what it reads
Chat & Reasoning is usually most of the bill. Longer chats and extra tools both add tokens.
Context Window is in AI Advanced Settings: Advanced in Agent Preferences, Model tab.
Connectors · Context usage meter · Short vs. long context windows
Stop unused work
Leave evaluations and reflections on if they are useful.
Stop a Scheduled Trigger · Evaluations · Reflections
Ask the agent
In chat, ask which tools it is retrying, which steps it could skip, and to save the fix in a skill or its instructions. On a schedule, Reflections reviews recent chats for patterns such as inefficient tool usage and proposes skill or instruction changes. ReflectionsUse your own key
Optional. Bring-your-own-key (BYOK) sets Chat & Reasoning to 0 credits — you pay the provider instead.
Use your own LLM key
FAQ
I switched to a cheaper model and spend did not drop.
I switched to a cheaper model and spend did not drop.
If the agent is on Auto, Gumloop already routes easy messages to cheaper models. Check the chat’s models list and credit breakdown to see what actually ran. Pin a specific model only when you want every run to use that model.
Why is one chat so expensive?
Why is one chat so expensive?
Open the credit count in the chat header. Long threads, many connected tools, retries, paid enrichment tools, and frontier models all raise Chat & Reasoning and Tool Calls. A new chat for a new topic is often the fastest cut.
Who can see org-wide spend?
Who can see org-wide spend?
Your own logs: Settings > Profile > Usage & Limits. All members: Settings > Organization > Usage & Limits (admin or manager). Insights dashboards: Enterprise, plus Admin, Manager, or Analytics.
Related
Credits
How a chat is billed, and the built-in cost tips
Organization Insights
Leaderboards, Explorer, and the analytics agent
Agent Skills
Playbooks that load only when needed
Choose the Right AI Model
Recommended, Smartest, and Auto