modelgrep

Fastest xAI Models

Quick answer · Updated June 2026

The fastest xAI model is Grok 4.20 Multi-Agent at 325 output tokens per second. Grok 4.3 (155 t/s) and Grok Build 0.1 (120 t/s) round out the top three.

325 t/sSpeed
$1.25Input /M
2MContext

AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.

  1. 1X
    grok-4.20-multi-agent
    ReasoningJSONVision$1.25/M · 11.5s ttft · 2M ctx
    325 t/s
    Speed
  2. 2X
    grok-4.3
    ReasoningToolsJSON+153.2 intel · $1.25/M · 670ms ttft
    155 t/s
    Speed
  3. 3X
    grok-build-0.1
    ReasoningToolsJSON+1$1.00/M · 769ms ttft · 256K ctx
    120 t/s
    Speed
  4. 4X
    grok-4.20
    ReasoningToolsJSON+129.7 intel · $1.25/M · 691ms ttft
    76 t/s
    Speed

Frequently asked

What is the fastest xAI model?

The fastest xAI model is Grok 4.20 Multi-Agent at 325 output tokens per second. Grok 4.3 (155 t/s) and Grok Build 0.1 (120 t/s) round out the top three.

What's a good alternative to Grok 4.20 Multi-Agent?

Grok 4.3 (155 t/s) is the closest alternative on this metric, followed by Grok Build 0.1 (120 t/s). See the full ranking above for the tradeoffs.

How many xAI models are there?

modelgrep tracks 4 xAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Grok 4.3. 4 of them qualify for this ranking.

More xAI rankings

All rankings