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.
For Teams & Enterprises.
Instead of trying to guess how many LLM tokens you will need to purchase, AgentSpot runs on a predictable, outcome-driven consumption model: Data to Outcome (DO) credits. It's simple: 1 credit is consumed per 24-hour period for each new agent conversation started, workflow execution completed, or application load. Additional app loads not counted within 12-hour period.
| 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
| Build | Run | ||||
|---|---|---|---|---|---|
| Use Case | Type | AgentSpot | (tokens) | AgentSpot | (tokens) |
| Accelerate Sales Pipeline | App | FREE | 45M Input, 2M Output~$70 | 1 DO Credit | 4.5M Input, 30k Output~$3.70 per play |
| Summarize Daily Tasks | Workflow | FREE | 18M Input, 400k Output~$20 | 1 DO Credit | 3.5M Input, 25k Output~$2.90 per run |
| Daily Meeting Prep | Agent | FREE | 60M Input, .5M Output~$70 | 1 DO Credit | 7M Input, 40k Output~$5.60 per brief |
* Estimated at Claude API list pricing (Opus 5.5, Oct 2026), assuming 90% prompt caching. Excludes testing, hosting and engineering time; actual costs vary with data volume and design.
Quick answers about how AgentSpot plans work and how DO Credits are used. Select a question to see the answer.
Usage in AgentSpot is measured in Data to Outcomes (DO) Credits. Your credit balance resets every week.
| Activity | Credit use |
|---|---|
| A user starts a new conversation with an agent | 1 credit |
| A workflow runs on a user’s behalf | 1 credit per run |
| A user loads an agentic app | 1 credit (reloads within 12 hours are free) |
Long-running sessions: A single conversation, workflow or app session can stay active for up to 24 hours on one credit. If it stays active longer, one additional credit is used for each additional 24 hours (or part of a 24-hour period).
Example: A user opens an agent conversation Monday at 9am and keeps working in it until Tuesday at 11am. That uses 2 credits.
You can track your credit usage in real time in AgentSpot.