Safe Medical Language Model
OpenAI Health Bench 65 score. Citation-backed responses, GDPR-ready deployment, <2% hallucination rate.
Metformin is contraindicated in patients with severe renal impairment (eGFR <30 mL/min/1.73m²)[1], acute or chronic metabolic acidosis[2], and in patients undergoing radiologic studies involving iodinated contrast materials[3].
[1] FDA - Metformin Prescribing Information (https://www.fda.gov/...)
[2] American Diabetes Association Guidelines 2025 (https://diabetesjournals.org/...)
[3] FDA - Metformin Safety Information (https://www.accessdata.fda.gov/drugsatfda_docs/label/...)
When disabled, responses are faster but may lack sources. Enable for regulatory compliance.
| Model | Persly V1 |
| OpenAI Health Bench | 65/100 |
| Context Window | 128K tokens |
| Citation Coverage | 100% (optional mode) |
| Hallucination Rate | <2% (with citation mode) |
| Compliance | GDPR-ready, SOC 2 Type II |
| Latency | Citation mode: ~15s / Standard mode: ~5s |
curl https://api.persly.ai/v1/llm/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "What are the contraindications for metformin?",
"citation_mode": true,
"max_tokens": 500,
"temperature": 0.3
}'Medical knowledge accuracy across 100 questions
Every sentence has a verifiable source (citation mode)
False medical facts (citation mode enabled)
Correctly identifies uncertain/out-of-scope questions
| Model | Score |
|---|---|
| Persly V1 | 65 |
| GPT-5 | 50 |
| Gemini 2.5 | 38 |
* OpenAI Health Bench: https://github.com/openai/simple-evals/tree/main/health_bench * Hallucination rate measured on 500 medical Q&A pairs
Power patient-facing chatbots with safe, citation-backed answers
Summarize patient records, research papers, clinical notes
Answer medical questions with verifiable sources
Provide drug interactions, contraindications, dosing info
We're GDPR-ready and SOC 2 Type II compliant. For HIPAA, contact us for BAA (Business Associate Agreement) options.
Citation mode: 100% coverage, <2% hallucination, slower (~15s). Standard mode: Faster (~5s), may lack sources, ~5% hallucination.
Yes, but it's optimized for healthcare. For general use, consider generic LLMs (OpenAI, Anthropic).
100+ languages. Citations include both local and international sources.
Let's discuss how our APIs can power your healthcare product