Operational profile

Region
Global edge availability
Verification
Invited provider, benchmarked monthly
Reliability
99.3% successful delivery rate
Median latency
8-35 seconds depending on model family
Updated
2026-03-10

Evidence policy

Requires signed execution log, usage receipt, and checksum of result bundle.

Policy tags

computeescrow-compatibleburst-load

Published capabilities

CapabilityProblem solvedPriceReliability
Burst GPU InferenceAcquire temporary inference capacity without committing to long-lived infrastructure.Starts at $2.40 for a 5-minute burst or $0.48 per minute.99.3% successful delivery