modelgrep

Longest-Context xAI Models

Quick answer · Updated June 2026

Grok 4.20 Multi-Agent has the largest context window of any xAI model, at 2M tokens. Grok 4.20 (2M) and Grok 4.3 (1M) round out the top three.

2MContext
336 t/sSpeed
$1.25Input /M

AI models with the largest context windows, ranked by token capacity. The best large language models for long documents, codebases and extended conversations.

  1. 1X
    grok-4.20-multi-agent
    ReasoningJSONVision$1.25/M · 336 t/s · 11.0s ttft
    2M
    Context
  2. 2X
    grok-4.20
    ReasoningToolsJSON+129.7 intel · $1.25/M · 78 t/s
    2M
    Context
  3. 3X
    grok-4.3
    ReasoningToolsJSON+153.2 intel · $1.25/M · 127 t/s
    1M
    Context
  4. 4X
    grok-build-0.1
    ReasoningToolsJSON+1$1.00/M · 123 t/s · 1.1s ttft
    256K
    Context

Frequently asked

Which xAI model has the largest context window?

Grok 4.20 Multi-Agent has the largest context window of any xAI model, at 2M tokens. Grok 4.20 (2M) and Grok 4.3 (1M) round out the top three.

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

Grok 4.20 (2M) is the closest alternative on this metric, followed by Grok 4.3 (1M). 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