This website is not yet fully optimised for mobile viewing. Some features may not display or function as intended.
US
xAI

Grok 3 Beta (Think)

xAI

Overview

No description provided. Want to help? Contribute on GitHub or click here!

Quick Links

Key Metrics
Max Input
128K
Tokens
Max Output
8K
Tokens
Input Price
-
Per 1M Tokens
Output Price
-
Per 1M Tokens
Throughput
-
tok/s
Latency
-
ms
Model Information
Release Details

Announced

17 Feb 2025

Released

-

Knowledge Cutoff

Nov 2024

License

Proprietary

Model Architecture

Parameters

-

Training Data

-

Context Window

Input Context Length

128,000 tokens

Output Context Length

8,000 tokens

Key Features
Web Access
Yes

Real-time access to current web information

Multimodal
No

Ability to process multiple data types (text, images, etc.)

Reasoning
Yes

Advanced logical and deductive reasoning capabilities

Fine-Tunable
Yes

Can be customized for specific use cases

Model Release & Updates
17 Feb 2025
Model Announced
Model first introduced to the public
Benchmarks & Performance Comparison
GPQA
75.40%
LisanBench
-
AidanBench
-
Aider-Polyglot
-
LiveBench
-
AIME 2024
52.20%
ARC-AGI-1
-
ARC-AGI-2
-
AIME 2025
-
Humanity's Last Exam
-