Plans
| Plan | Monthly Included | Concurrent Sessions | Price |
|---|---|---|---|
| Capy Pro | $20 usage | 5 | $20/month |
| Enterprise | Unlimited | Unlimited | Contact us |
Usage costs
Capy charges based on actual usage, billed in dollars. All models are priced at API cost.What you pay for
Your costs come from two sources: AI Usage (LLM)- Input tokens: text sent to the model (prompts, file contents, context)
- Output tokens: text the model generates (responses, code)
- More capable models cost more per token
- Pricing is based on the provider’s API rates
| Size | CPU | RAM | Cost/Hour |
|---|---|---|---|
| Small | 2 cores | 4 GB | $0.17 |
| Medium | 4 cores | 8 GB | $0.33 |
| Large | 8 cores | 16 GB | $0.66 |
| Ultra | 16 cores | 32 GB | $1.32 |
Typical usage
| Task | Approximate Cost |
|---|---|
| Quick code edit | $0.05–$0.20 |
| Feature implementation | $0.50–$2.00 |
| Large refactor | $2.00–$10.00 |
Enterprise
For teams needing unlimited usage, custom integrations, or dedicated support:- Unlimited usage
- Unlimited concurrent sessions
- Priority support
- Custom integrations
FAQ
What happens when my balance runs out?
What happens when my balance runs out?
Active tasks will pause. You can add more balance or wait for your monthly refresh.
Does unused balance roll over?
Does unused balance roll over?
Yes, any balance you manually add rolls over. Monthly plan usage allowances
refresh each month.
Which models are most cost-effective?
Which models are most cost-effective?
Claude Haiku and Gemini Flash are the most economical. Use them for simpler tasks.