Pricing & credit model
qRaptor uses a credit-based pricing model. Credits are consumed when you run agents, generate and deploy apps, send messages, use voice, and make LLM calls.
How credits work
- Each plan includes a monthly credit allocation (see Plans & entitlements).
- Your allocation resets on the 1st of each calendar month. Unused monthly credits do not roll over.
- When you upgrade, your remaining credits are preserved and the new plan’s allocation is added on top.
- If you run out, you can purchase additional credits. Purchased credits do not expire.
What consumes credits
Running agents
| Action | Credits |
|---|---|
| AI Agent run (production) | 1.0 per run |
| AI Agent run (preview / test) | 0.25 per run |
| Task Agent run (production) | 0.5 per run |
| Task Agent run (preview / test) | 0.1 per run |
These per-run fees are charged in addition to the LLM token cost of the run (see LLM usage below).
Generating apps
| Action | Credits |
|---|---|
| Generate a new app | 5.0 |
| Change request | 3.0 |
| Fix | 2.0 |
| App preview | 0.25 per preview |
Deployments
| Action | Credits |
|---|---|
| Deploy an app to production | 50 (one-time) |
| Deploy a Multi-Agent System | 50 (one-time) + 100 / month |
| Deploy an agent as an API | Free |
Messaging & voice
| Action | Credits |
|---|---|
| 0.001 per message | |
| SMS | 0.01 per message |
| 0.02 per message | |
| Voice — speech to text | 0.5 per minute |
| Voice — text to speech | 0.25 per minute |
| Voice — realtime | 2.0 per minute |
| Telephony phone number (rental) | 100 per number / month |
A telephony number is charged a flat monthly rental whether or not it takes any calls, and it keeps billing while it is unattached. The conversation itself is charged at the voice rates above — there is no separate per-minute telephony fee. See Billing & suspension.
Storage
| Resource | Credits |
|---|---|
| Content Store storage | 1.0 per 100 MB / month |
LLM usage
LLM calls are billed per token, priced by model. Both input tokens (prompt + context) and output tokens (response) are metered, and more capable models cost more per token. LLM usage is charged on top of the per-run and per-generation fees above.
To keep LLM costs down, use smaller models for simple classification or routing, keep prompts and context concise, and use Condition nodes to skip LLM calls when they aren’t needed.
Top-ups
If you exhaust your monthly allocation, you can buy additional credits from the billing dashboard. Top-up pricing depends on your plan — contact us for details. Purchased credits are added to your balance and do not expire.
Monitoring usage
Track your credit consumption from:
- Per-run view — Each agent execution shows its credit cost in the run detail.
- Project dashboard — Aggregated usage across all agents in the project.
- Workspace billing — Total consumption across all projects with a breakdown by project.