Grok 4.1
Hallucination Halved, 2M Context
xAI's November 2025 update to Grok 4 — most notably, it cut the hallucination rate roughly in half (from ~9% to 4.22%). The Fast variant ships with a 2 million-token context window, making it one of the longest-context production models available.
Intelligence
Medium
Speed
Medium
127 tok/s output
Cost
Low
$0.20 in / $0.50 out
Context
2M
Up to 2,000,000 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on
Artificial Analysis. Cost buckets are fixed dollar
thresholds keyed off output-token price ($/M out).
Intelligence
- Top 1%≤ 1%
- Top 5%≤ 5%
- Top 10%≤ 10%
- Good≤ 25%
- Medium≤ 50%
- Below avg> 50%
Speed
- Top 1%≥ 345 tok/s
- Top 5%≥ 237 tok/s
- Top 10%≥ 196 tok/s
- Good≥ 146 tok/s
- Medium≥ 90 tok/s
- Slow< 90 tok/s
Cost
- Freeopen weights · self-host
- Low< $1 / M out
- Moderate$1–5 / M out
- High≥ $5 / M out
Why it matters
Demonstrated that aggressive RLHF + factuality-focused training can halve hallucination at the frontier without sacrificing capability. Grok 4.20 Beta 2 (March 2026) continued this trend.
Core Capabilities
Long Documents
Handles entire codebases, books, and multi-doc RAG.
Multimodal
Combines text, vision, and audio in one model.
Generative
Produces images, video, audio, or other media.
Reasoning
Solves complex math, logic, and planning tasks.
Context Window
2M tokens
≈ entire codebase
4k Chat 聊天
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M
2M
Availability
API
Available
Product / App
Available
Open Source
Not released
Enterprise
Contact sales
Pricing Model
Pay per token
Input and output billed separately.
Pay-per-token Capability / Performance
Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).
Lower 20% Upper 80% This model
Context / memory
Context window size · log-scaled
6.0
9.0
10.0
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this
Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.
What it feels like
- Mid-cycle refresh of Grok 4.
- AA Intelligence Index of 73 at release — leading frontier slot, ahead of o3 (70), Gemini 2.5 Pro (70), Claude 4 Opus (64)
- GPQA Diamond all-time high of 88%; Humanity's Last Exam 24%; AIME 2024 94%; MMLU-Pro 87%
- Leads Coding Index (LiveCodeBench + SciCode) and Math Index (AIME24 + MATH-500)
Best use cases
- Math, science, and reasoning research where Grok 4 leads on raw benchmark numbers
- Real-time information lookup inside the X (Twitter) product with full timeline access
- Tool-using agents that benefit from extended reasoning + verifiable-rewards training
Tools to try
Not ideal for
- Customer-facing products where political-bias risk is a brand concern
- Workflows requiring system-prompt-free behaviour — RL tuning shows different defaults depending on scaffold
Model Evolution
grok is xAI's language model family.