modelgrep

Lowest-Latency Rekaai Models

Quick answer · Updated June 2026

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.

1.2sLatency
14 t/sSpeed
$0.100Input /M
16KContext

AI models ranked by time-to-first-token (p50). The most responsive large language models for real-time and interactive use cases.

  1. 1R
    reka-edge
    ToolsJSONVision$0.100/M · 14 t/s · 16K ctx
    1.2s
    Latency
  2. 2R
    reka-flash-3
    Reasoning$0.100/M · 35 t/s · 66K ctx
    1.3s
    Latency

Frequently asked

Which Rekaai model has the lowest latency?

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.

What's a good alternative to Reka Edge?

Reka Flash 3 (1.3s) is the closest alternative on this metric. See the full ranking above for the tradeoffs.

How many Rekaai models are there?

modelgrep tracks 2 Rekaai models with live benchmarks, speed, latency and per-provider pricing. 2 of them qualify for this ranking.

More Rekaai rankings

All rankings