For prototypes and internal tools
Start with a single API key and selected model access.
- OpenAI-compatible endpoint
- Claude, GPT, and Kimi model IDs
- Streaming responses
- Usage visibility in console
Pricing
Transparent access, without public rate noise
Aergia AI pricing is usage-based. Public pages show the access model and production controls; account-specific rates and limits are handled inside the console or through sales.
For teams shipping user-facing AI
Use higher limits, stronger operational visibility, and team controls.
- Team API key management
- Request logs and usage records
- Model availability monitoring
- Routing designed for stable workloads
For custom capacity and governance
Align access, limits, and operations with your production requirements.
- Custom account setup
- Dedicated operational review
- Capacity planning support
- Security and compliance discussions
How billing works
Model usage stays visible before it becomes surprising.
The pricing page keeps public messaging clean. Actual model rates, account limits, and payment workflows are account-specific.
01
Choose access
Create an account and select the model access level your team needs.
02
Call models
Use one endpoint and explicit model IDs across your application.
03
Review usage
Track usage and operational behavior from the console.