Parameters
Undisclosed
Context Length
128K
Modality
Text
Architecture
Undisclosed
License
Proprietary
Release Date
1 Jun 2025
Knowledge Cutoff
Jun 2025
API Pricing (per 1M)
Input: $1.25 · Output: $2.50
Rank
#62
| Benchmark | Score | Rank |
|---|---|---|
General Text | auto 1430 | 75 |
Web Development | 1240 | 84 |
Intelligence Index | 0.11 | 167 |
Overall Rank
#62
Coding Rank
#122
Grok 4.1 Fast is a high-throughput reasoning model from xAI engineered for low-latency agentic workflows and real-time data grounding. It supports multihop web search, tool execution, and dual thinking modes across a 2M token context window.
Architecture specifications are undisclosed for proprietary models.
Attention
Attention Structure
Multi-Head Attention
Attention Heads
Undisclosed
Key-Value Heads
Undisclosed
Attention Head Dimension
Undisclosed
Position Embedding
Absolute Position Embedding
RoPE Theta
Undisclosed
Sliding Window Attention
Undisclosed
Sliding Window Size
Undisclosed
Sliding Window Ratio
Undisclosed
Linear Attention
Undisclosed
Linear Attention Ratio
Undisclosed
Normalization
Undisclosed
Activation Function
Undisclosed
Dimensions
Hidden Dimension Size
Undisclosed
Number of Layers
Undisclosed
FFN Intermediate Size (Dense)
Undisclosed
Multi-Token Prediction Heads
Undisclosed
Tokenizer
Vocabulary Size
Undisclosed
xAI's frontier intelligence models trained with reinforcement learning at unprecedented scale using the 200,000 GPU Colossus cluster. Grok 4 series demonstrates state-of-the-art performance in reasoning, coding, and multimodal understanding with native tool use capabilities. Features real-time search integration across X and the web, advanced reasoning through scaled RL training, and industry-leading performance on academic benchmarks. Designed for both immediate responses and extended thinking modes with vision capabilities.
Assistant
Online