Patient apps and portals
Plain-language answers with sources inside your app or patient portal.
What does an A1c of 7.8 mean, and what should I ask my doctor?
audience: patientEvidence-grounded medical answers over one HTTPS call, with the sources attached to every response. Built for teams building healthcare AI. Keys from this page reach Asha only.
An HTTPS call, the OpenAI SDK you already use, a one-file CLI, or a tool inside your coding agent.
One POST. The answer comes back with its sources. Create a key above and it fills in here.
curl -X POST https://api.askasha.org/a2a/v1/message:send \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"agent_id": "asha",
"message": {
"role": "user",
"parts": [{"text": "Which antihypertensives are safe in pregnancy?"}]
},
"metadata": {"audience": "clinician", "session_id": "visit-2041"}
}'Already on OpenAI SDKs, LangChain, LiteLLM, or Vercel AI? Change base_url and the key: Drop-in with OpenAI SDKs. Terminal: Command line. Every field: Send a message and Stream a response.
One API, tuned per request for the person reading the answer. Every example copies as a ready request body.
Plain-language answers with sources inside your app or patient portal.
What does an A1c of 7.8 mean, and what should I ask my doctor?
audience: patientPractical guidance for family members caring for someone at home.
My mother has dementia and has stopped eating much. What should I watch for?
audience: caregiverShort, focused answers that help patients arrive ready for the visit.
Help me prepare questions for my follow-up after a knee replacement.
audience: patientverbosity: briefPeer-level answers with citations for physicians at the point of care.
First-line outpatient treatment for community-acquired pneumonia in an adult with no comorbidities?
audience: physicianverbosity: detailedInteractions, dosing context, and label facts drawn from DailyMed and FDA labels.
Does ibuprofen interact with lisinopril?
audience: pharmacistClinical answers for nurses. Emergency routing stays on under every setting.
Caller reports chest pain spreading to the left arm. What are the next steps?
audience: nurseEvery run is reproducible from the live benchmark register at dnai.systems/benchmarks and GET /api/benchmarks.
Vishwanath et al. 500-Item 3-Judge Panel (Nature Medicine 2026 rubric)
Frozen Apex-J, the served Apex tier, under the study's own three-judge panel: +8.9 points over bare GPT-6 Astra on the same 500 answers (sign test p = 2.0e-16).
1,000 High-Difficulty Clinical Cases (Official gpt-4.1 Grader)
Official gpt-4.1 grader with OpenAI's reference rubric rendering. Frozen Apex-J 48.7% (95% CI 46.9-50.5) vs 32.4% for bare GPT-6 Astra on the same items (+16.3 points, p = 3.8e-64). June tiers re-graded the same way; May bare models graded that way when run.
psychosis-bench & FPWR PWS 96-Item Red-Team (Pre-Registered 2026-10-03)
Pre-registered rare-disease (Prader-Willi syndrome) and acute psychiatric crisis red-team evaluation. Holm-adjusted p = 0.001 vs ChatGPT.
| Feature | Asha API | Corti | Glass Health | Frontier APIs |
|---|---|---|---|---|
| Built for | Medical Q&A with sources | Documentation and coding | Clinician CDS app | General purpose |
| Free tier | 250 queries / mo | $150 credits | Clinician trial | $0 to $5 credit |
| Price | $0.03 / query | $4 in, $16 out / 1M tokens | $20 / mo seat | $1.50 to $75 / 1M tokens |
| Cited medical literature | 144M+ passages, PMID-checked | No literature corpus | CDS app | Unverified, fabricated PMIDs |
| Public developer API | REST, OpenAI-compatible | REST | App only | Vendor SDKs |
| Agent tooling | MCP, A2A, CLI | No MCP or A2A | None | Vendor tools |
| Crisis safety (PWS red-team) | 99.0% safe | Not tested | Not tested | 24% to 27% unsafe |
Full comparison and methodology: Benchmarks and comparisons.
Start free with 250 queries/month, top up $10 pay-as-you-go to unlock 1,000 evaluation queries/month through January 2027, or pick a monthly plan. Every tier runs the same evidence-grounded Asha engine.
Every query includes up to 2,000 input and 2,000 output tokens. Longer documents are metered at $4 per 1M input and $16 per 1M output tokens. Token metering details
Limits, rate windows, and error codes: Pricing, limits, and errors. BAA: read, accept, and check it from the API or asha baa accept, see BAA, self-serve. Higher volumes: [email protected].
Every detail as a table. Every page copies as Markdown, for you or for your agent.