Log in
← All models

Grok 4.20

Frontier

The 2M-token member of the Grok line — built for very large agent contexts.

xAI
Maker
83/100
Overall
61
Value score
$1.63
Blended /1M
2M
Context
Proprietary
Weights
Pricing: $1.25 in · $2.50 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality8.6/10 · 75% community
Agentic Ability8.0/10 · 72% community
Speed7.6/10 · 71% community
Value for $8.5/10 · 75% community
Reliability8.5/10 · 75% community

Grok 4.20 extends the Grok line to a 2M-token context — the largest among the mainstream frontier models — at the same competitive price. Useful when an agent needs to hold an unusually large amount of code or documents in a single run.

Strengths
  • 2M-token context
  • Frontier quality at mid-tier price
  • Strong agentic mode
Trade-offs
  • Big context costs add up fast
  • Smaller ecosystem than GPT/Claude

Agents that run Grok 4.20 well

Agents that genuinely need 2M tokens of context.

Best model for ClineBest model for AiderBest model for CursorBest model for OpenCodeBest model for OpenClaw

Grok 4.20 FAQ

Is Grok 4.20 good for AI agents?
Agents that genuinely need 2M tokens of context. On our editorial scoring it rates 8.0/10 for agentic ability and 8.6/10 for output quality. 2M-token context.
How much does Grok 4.20 cost?
Via OpenRouter, Grok 4.20 is priced at $1.25 in · $2.50 out / 1M tokens — a blended rate of about $1.63 per 1M tokens for typical input-heavy agent use.
What is Grok 4.20's context window?
Grok 4.20 has a 2M-token context window — large enough to hold sizeable codebases or document sets in a single run. xAI is the maker.
Can I self-host Grok 4.20?
No — Grok 4.20 is a proprietary, hosted-only model from xAI. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.
What are the downsides of Grok 4.20?
The main trade-offs: big context costs add up fast; smaller ecosystem than gpt/claude. It's strongest for agents that genuinely need 2m tokens of context.

Grok 4.20 compared

Grok 4.20 vs Opus 4.8Grok 4.20 vs GPT-5.5Grok 4.20 vs Gemini 3.1 ProGrok 4.20 vs GLM 5.2Grok 4.20 vs Qwen3.7 MaxGrok 4.20 vs DeepSeek V4 ProGrok 4.20 vs Kimi K2.6Grok 4.20 vs Grok 4.3

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →