What changed
On October 26, 2026, OpenAI announced that CodeRabbit is using GPT-6.1 Sol as the primary model in its security agent to improve code review processes. This integration allows the tool to extend security analysis beyond individual code changes and assess risks across complex codebases.
What this means in practice
During pull-request reviews, GPT-6.1 Sol helps analyze changes as developers work, identifying potential security issues that span shared libraries, dependencies, and safeguards. CodeRabbit's system supports broader investigations across repositories, including dependencies and component interactions. It also extends this analysis to linked repositories, such as shared authentication libraries, to understand how weaknesses could impact the wider system.
CodeRabbit Secure connects investigation to remediation. For user-selected findings, it can attempt exploit verification in an isolated sandbox without testing production systems. For supported issues, it can draft a pull request with a proposed fix for a person to review and approve.
These findings feed into the pull-request workflows developers already use to review and improve their code.
Limitations and availability
The supplied announcement does not specify the exact parameter counts or hardware requirements for GPT-6.1 Sol. It also does not mention the availability of the model through an API or download. CodeRabbit reports using GPT-6.1 Sol to flag security-related issues across thousands of repositories and organizations, but the exact scope of its deployment remains unspecified.
