Pricing
Pay Only For What You Use
No subscriptions. No minimums. Real-time USDC micropayments with instant receipts.
Inference
Multi-model AI chat completions
from $0.50
per 1M tokens
- ✓ GPT-4o, Claude 3.5, Gemini 2
- ✓ Streaming support
- ✓ Zero cold starts
Sandboxes
Secure code execution environments
$0.02
per hour
- ✓ Isolated sandbox execution
- ✓ Python, Node, Bash
- ✓ Secure runtime
GPU Instances
On-demand GPU compute
Coming soon
per GPU-hour
- ✓ A10, A100, H100
- ✓ Instant provisioning
- ✓ CUDA & PyTorch