Infrastructure-grade pricing.
Transparent relay costs with global low-latency routing. Scale your AI integrations confidently without opaque surcharges or arbitrary rate limits.
Model Pricing
USD / Million TokensInternal server error.
| Model | Input | Output | Cache Read | Cache Write | Official I/O | Savings |
|---|
The backend public catalog could not be loaded. Try again later.
Average price = average price at 1.0x multiplier. Actual unit price fluctuates between 0.8x and 1.5x depending on network load. Savings = discount relative to Anthropic / OpenAI official API pricing at 1.0x baseline.
Nodex AI targets stable availability for API relay endpoints. In the event of a verified SLA breach, affected accounts may be eligible for usage credit reimbursement as defined in our SLA Policy documentation.
Relay Infrastructure & Billing
Global Billing Flexibility
Nodex AI supports universal payment rails to ensure uninterrupted relay access globally.
Low-latency Access
The platform continuously optimizes request paths and node health to reduce API latency.