Developer API
OpenAI-Compatible Clinical Reasoning API
One API for all healthcare needs. Powered by advanced medical chain-of-thought reasoning, trained on peer-reviewed literature, and designed for evidence-based clinical decisions.
Stop using generic AI. EvidenceMD understands medicine.
AI Reasoning Benchmarks
How EvidenceMD compares to leading AI models on specialized reasoning tasks
See the Difference: Real Clinical Reasoning
EvidenceMD delivers structured, evidence-based responses with citations from peer-reviewed sources.
| Feature | EvidenceMD | OpenAI | Claude | Gemini |
|---|---|---|---|---|
| Citations & Sources | ||||
| Peer-Reviewed Information | ||||
| Clinical Reasoning | ||||
| Biomedical Reasoning |
"What's the treatment plan for aortic thoracic aneurysm 5.9cm in dialysis patient?"
Executive Summary: Treatment Plan for 5.9 cm Thoracic Aortic Aneurysm in Dialysis Patient
The treatment plan requires a critical balance between the imminent risk of aortic rupture/dissection and the significantly elevated perioperative mortality associated with renal failure.
Immediate Recommendation:
A 5.9 cm TAA exceeds the standard intervention threshold of 5.5 cm established by the 2022 ACC/AHA Guidelines [1]. The management strategy must prioritize Thoracic Endovascular Aortic Repair (TEVAR) over open surgery if anatomically feasible.
1. Indication for Intervention:
2. Procedural Approach:
Sources (8 peer-reviewed citations):
[1] ACC/AHA Guidelines 2022 - ahajournals.org
[3] SVS Guidelines - jvascsurg.org
[6] Ann Thorac Surg - annalsthoracicsurgery.org
[10] PMC Study - pmc.ncbi.nlm.nih.gov
[19] JTCVS - jtcvs.org
[26] JAMA Cardiology - jamanetwork.com
Real API response with inline citations and peer-reviewed sources
One API for All Healthcare Needs
Built for developers building the future of healthcare
Patient education, symptom checkers, telehealth platforms
Drug discovery, clinical trials, medical writing
Clinical documentation, SOAP notes, EHR integration
Diet, nutrition, fitness, preventive health apps
API Documentation
OpenAI-compatible API. Drop-in replacement with medical superpowers.
1Get your API Key
Sign in with Google to get your API key from the dashboard.
2Make your first request
curl https://evidencemd.ai/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"model": "evidencemd-fast",
"messages": [
{"role": "user", "content": "What is metformin?"}
],
"stream": true
}'3Receive evidence-based response
Response includes inline citations [1], [2] with source URLs and a References section — all embedded in the content. Every response includes an x-request-id header for tracing.
Three models available:
evidencemd-fast— Quick answers, 1 creditevidencemd-pro— Deep analysis, 2 creditsevidencemd-deep— 97% GPQA Diamond, 4 creditsEvidence-Based Clinical Reasoning
How EvidenceMD transforms clinical decision-making with AI-powered evidence synthesis
Chain-of-Thought Reasoning
Our model follows clinical reasoning patterns - from differential diagnosis to treatment planning, mimicking how physicians think through complex cases.
Real-Time Evidence Synthesis
Automatically retrieves and synthesizes evidence from peer-reviewed journals, clinical guidelines, and medical databases for every query.
Specialty-Aware Responses
Trained across 30+ medical specialties with understanding of specialty-specific guidelines, terminology, and treatment protocols.
Verifiable Citations
Every clinical claim is backed by inline citations from trusted sources - no hallucinations, no made-up references.
Enterprise Solutions
Need custom SLAs, dedicated instances, or volume pricing? Contact us for enterprise solutions.
Ready to Build with Medical AI?
Join developers building the future of healthcare.