Apps & Tools
Relace Compact
Fast context compaction to reduce input token costs for long-context 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 LLM designed for token-level classification that prunes long agent traces at 50k+ tokens per second. It allows coding agents to maintain performance in long-context windows while cutting input token spend by up to 50% by compacting history during cache-miss events.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.