Grok 4
Version: 1
Grok 4 is the latest reasoning model from xAI with advanced reasoning and tool-use capabilities, enabling it to achieve new state-of-the-art performance across challenging academic and industry benchmarks. Because models developed by xAI push the frontier of AI capabilities, xAI is committed to mitigating their risks through both evaluating model behaviors and implementing safeguards.
Model developer: xAI
Supported languages: English
Model Release Date: July 9, 2025
Intended Use
Model Alignment
Microsoft's safety and responsible AI evaluations found Grok-4 to be less aligned than other models evaluated and offered through Azure Direct resulting in (i) higher risks that the model will produce potentially harmful content and (ii) lower scores on safety and jailbreak benchmarks.Model Card & Content Safety
Review the xAI model card for additional information on system evaluations, expected behavior, and safety systems. Grok-4 may be capable of producing explicit content, and may do so with a higher propensity than other models. Customers should use both system safety messages and Azure AI Content Safety (AACS) service to manage model behavior and comply with the Microsoft Enterprise AI Services Code of Conduct . Additionally, there may be categories of harm this model can produce that are not covered by Azure AI Content Safety. Accordingly, customers should conduct their own evaluations before deploying Grok-4 in production systems. We have also made safety benchmarks available for this model in the model card benchmark tab and the tradeoff chart.Grok 4 Benchmark Performance Overview
Grok 4 benchmarks and system evaluations are comprehensively included in the xAI Grok 4 model card .Model Specifications
Context Length256000
LicenseCustom
Training DataDecember 2024
Last UpdatedSeptember 2025
Input TypeText,Image
Output TypeText
PublisherxAI
Languages1 Language