Proxy API: 15% of savings on provider bill. Models API: $0.40 per 1M tokens removed (Helene 1.1), $0.90 per 1M tokens removed (Adeline 1). Free tier available with Condense Lite (approximately 20% compression).
Key features
H100, H200, and B300 GPU availability
Interruptible (preemptible) GPU capacity
50% deposit payment model
Flexible launch sizes (1, 2, 4, or 8 GPUs)
Availability confirmation before payment
United States and European Union regions
Public Pricing API
No platform fee layered on top
Minimum 2,000 GPU-hours per request
Proxy API for seamless integration requiring only one base URL and header change
Maintains 98.6% cache hit rate
Preserves instructions, questions, answers, code and error messages
Direct billing from provider with no stored API keys
SOC 2 Type II and ISO 27001 compliance in progress
Zero data retention with GDPR export and erasure support
What makes it different
Radically lower prices than major cloud providers
Request-based model with capacity confirmation
Competition and distributed supply model
No promotional pricing, available capacity
Removes 37.3% of bills on average sessions and 66-72% on sessions over 800k tokens
Pay only 15% of savings on Proxy API with no fee if no savings occur
Built around cache architecture rather than against it
Public benchmark allowing comparison with alternatives before purchase
Operates transparently with audit logs and ability to inspect rewritten requests
Compute Cheap
condense