Reka Edge has the lowest latency of any Rekaai model, responding in about 1.2s to first token. Reka Flash 3 (1.3s) is next.
AI models ranked by time-to-first-token (p50). The most responsive large language models for real-time and interactive use cases.
Reka Edge has the lowest latency of any Rekaai model, responding in about 1.2s to first token. Reka Flash 3 (1.3s) is next.
Reka Flash 3 (1.3s) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
modelgrep tracks 2 Rekaai models with live benchmarks, speed, latency and per-provider pricing. 2 of them qualify for this ranking.