Overview
We adjusted credit consumption for the Lite and BYOM (Bring Your Own Model) options in Pipefy AI. Running an automation with Lite now costs half of what it did, and BYOM runs cost a third less.
The change is already live for the entire base, no configuration needed.
What's new?
- Pipefy AI Lite: consumption drops from 2 credits to 1 credit per run.
- Bring Your Own Model (BYOM): consumption drops from 1.5 credits to 1 credit per run.
- Standard and Pro stay at 2 credits per run (Pro is in its promotional period until 10/08, then moves to 3 credits).
How does this help?
- Lite's cost now matches its use case: picking the lightest model for simple tasks now makes financial sense too, not just technical.
- BYOM reflects the real cost of running your own model: if you already pay for your model's tokens, you no longer absorb a disproportionate credit cost on top of that.
- No action required: the update is already live across the entire base, no need to reconfigure existing agents or automations.
Use cases
1. Ticket triage agent running on Pipefy AI Lite
A support team uses a Lite agent to classify and route recurring requests, like password resets and access requests. With lower consumption, the agent can run across the full incoming volume instead of just part of it, keeping heavier models reserved for cases that need deeper analysis.
2. Procurement agent running on BYOM
A company already running its own model to extract data from invoices and purchase request forms now pays 1 credit per run instead of 1.5. The agent still reads attachments and fills in card fields automatically, but at a lower total operating cost per card processed.
3. HR onboarding agent using Lite
An admission process uses a Lite agent to validate documents submitted in the form and fill in fields like ID number, address and personal data. With the lower credit cost, the HR team runs the agent on every card in the process without closely tracking monthly consumption to stay within budget.
4. Finance reconciliation agent using BYOM
A finance team uses its own model to reconcile entries between accounts payable and receivable pipes. With BYOM's lower credit cost, the automation now runs on every card each month instead of a sample, removing the need to manually check the rest.
Most relevant for
- Account admins
- Teams using Pipefy AI Lite
- Customers with Bring Your Own Model (BYOM) configured
- Pipe Admins building AI agents
Documentation
For the full step by step, check the Help Center article.
Plans and availability
- Pipefy AI Lite: 1 credit per run (previously 2).
- BYOM: 1 credit per run (previously 1.5).
- Standard and Pro: stay at 2 credits per run. Pro is in its promotional period until 10/08/2026, after which it moves to 3 credits.
- Already live for the entire base, no configuration needed.
