OpenAI is rolling out ChatGPT for Clinicians, a specialized version of its chatbot designed specifically for clinical workflows. It's free for verified US physicians, nurse practitioners (NPs), physician assistants (PAs), and pharmacists.
The tool offers access to OpenAI's latest models for handling clinical questions. A new Skills feature lets users save common workflows—like referral letters and prior authorizations—as reusable templates. Its clinical search function pulls real-time citations from peer-reviewed literature with proper attribution, while a deep research mode can essentially act as a proxy for conducting medical literature reviews. When users search for clinical questions in ChatGPT, eligible literature reviews can automatically count toward Continuing Medical Education (CME) credits. HIPAA compliance is available as an optional add-on through a Business Associate Agreement (BAA), and conversations won't be used to train the models.
Before launch, OpenAI's physician advisors tested the system across 6,924 conversations in their daily work, with 99.6% of responses rated as safe and accurate. In a citation test of 355 samples, ChatGPT for Clinicians cited standard sources more frequently than human physicians did.
OpenAI also released HealthBench Professional, an open benchmark covering three types of clinical tasks: care consultation, documentation writing, and medical research. In the ChatGPT for Clinicians environment, GPT-5.4 scored a composite 59.0, outperforming the base GPT-5.4 (48.1), Claude Opus 4.7 (47.0), Gemini 3.1 Pro (43.8), written responses from human physicians (43.7), and Grok 4.2 (36.1).