AgentSpot is based on DO credits: one credit per outcome. Not per user who might log in. Not per million tokens the model happened to consume. Tokens still power AgentSpot under the hood — we just don't make them your problem.

AgentSpot is based on DO credits: one credit per outcome. Not per user who might log in. Not per million tokens the model happened to consume. Tokens still power AgentSpot under the hood — we just don't make them your problem.
DO credits | Per user (others) | Per token (others) | |
|---|---|---|---|
| What you are paying for | Work completed | A user with a login | Model consumption |
| Cost of adding your whole team | $0 | Grows with every seat | N/A |
| Cost of a complex task | Same as a short one | Unpredictable | Goes up, unpredictably |
| Cost when a run fails | $0 | You still pay | You still pay |
| What you forecast against | Outcomes you already plan | Headcount you do not control | Token math you cannot predict |
One workflow — 15 tasks
| Event | Cost |
|---|---|
| New agent conversation is started | 1 DO credit |
| A workflow run completes | 1 DO credit |
| An application is loaded | 1 DO credit |
Create, test and iterate on agents, workflows and apps, free on both Free and Fleet.
A workflow that does not complete, an app that does not load: no charge. You pay only when it works.
Unlimited users. No builder seats, no viewer seats, no per-user subscriptions.
Scenario: a 150-person ops team running 250 workflows per week (~1,000 per month)
| AgentSpot | Per-seat tool | Per-token tool | |
|---|---|---|---|
| How you're billed | By workflow run: 250 DO credits per week | By headcount: 150 seats × $20/month | By consumption: ~1,000 workflows × $3–$5 each |
| Monthly cost | $1,650 | $3,000 | $3,000–$5,000 |