Apps & Tools
Relace Compact
A high-speed compaction model that cuts AI token costs by over 50% for coding agents.
Playable
Relace Compact media is blocked
Allow external media to connect to the provider and play this content.
Description
Relace Compact is a specialized model designed for token-level classification that prunes agent traces at over 50,000 tokens per second. It identifies and removes stale information like irrelevant bash outputs and repeated file reads on cache-miss, shifting input costs from quadratic to linear growth while remaining imperceptible to users.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.