grok-4.3

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

• Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
• Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.
• Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
• Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

About this model

Grok 4.3 is the latest model from xAI, with advanced reasoning, productivity, and multi-agent capabilities, enabling it to achieve state-of-the-art performance across challenging academic and industry benchmarks.

Responsible AI considerations

Safety techniques

Because models developed by xAI push the frontier of AI capabilities, xAI seeks to mitigate their risks through both evaluating model behaviors and implementing safeguards. Details about the evaluation and mitigation for top RAI risks are included in the xAI Grok 4.3 model card.

Safety evaluations

Microsoft's safety and responsible AI evaluations found Grok-4.3 to be less safe than other models evaluated and offered through Azure Direct. In particular, the review found that the model brings (i) higher risks of producing potentially harmful content (e.g., content including hate and unfairness, sexual, violent, and glorification of self-harm) and (ii) higher risks of successful jailbreak attacks.

Grok-4.3 benchmarks and system evaluations are detailed in the xAI Grok 4.3 model card.

We have also made safety benchmarks available for this model in the model card benchmark tab and the tradeoff chart, which illustrates the significantly higher jailbreak success rates on Grok-4.3 compared to other models.

Known limitations and considerations

We require that customers 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, but note that integration of these required safeguards will probably not mitigate all the risks. Given Microsoft's safety and responsible AI evaluation found Grok-4.3 to be less safe than other models offered through Azure Direct (see "Safety evaluations" section above), there may be categories of harm this model can produce that are not covered by Azure AI Content Safety evaluation and mitigations. Therefore, customers should conduct their own evaluations according to their intended use cases and implement appropriate mitigations before deploying Grok-4.3 in production systems.

Acceptable use policy

Review the xAI model card for additional information on system evaluations, expected behavior, and safety systems. Customers are required to 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. See the "Out of scope use cases" section for scenarios where we do not recommend deploying Grok-4.3.

Key model capabilities

Grok 4.3 provides a broad set of capabilities centered on reasoning, long-context understanding, and agentic execution. It features always-on reasoning that enables the model to handle complex, multi-step tasks with improved accuracy and instruction following. The model supports a large context window, allowing it to process extensive documents, conversations, or datasets in a single interaction. It also includes native function calling and tool integration, enabling workflows that combine reasoning with actions such as web search, code execution, and data retrieval. In addition, Grok 4.3 supports multimodal inputs—including text, images, and video—and can produce structured outputs, making it well suited for building reliable, production-grade systems that require automation, data analysis, and end-to-end task orchestration.