Predictable latency tiers
Real-time and batch processing are planned. Rates and availability will be confirmed before launch.
DEVELOPER PLATFORM / REST APIThree model families.
Three model families.
One unified REST contract.
Preview one API for specialist models and structured findings. AI endpoints are not live.
● HTTPS POST /v1/analyze● JSON / Multi-part● Bearer Token Auth
API REQUEST · PYTHON
python
import requests
API_KEY = "vv_live_sample"
ENDPOINT = "https://api.vesselvision.ai/v1/analyze"
payload = {
"model": "prism",
"task": "pediatric-wrist-fracture",
"image_url": "https://storage.hospital.org/scans/wrist_pa_042.png",
"outputs": ["findings", "concepts", "heatmap"]
}
response = requests.post(
ENDPOINT,
headers={"Authorization": f"Bearer {API_KEY}"},
json=payload
)
result = response.json()
print("Findings:", result["findings"])
print("Concept Confidence:", result["concepts"])REST ARCHITECTURE
Designed around clinical review.
Keep model selection, inference uncertainty, and physician verification close to your application code.
- Deterministic capability routing via model & task parameters
- Structured output schema with uncertainty & concept attribution
- Planned audit timestamps and institution-specific data controls
- Data retention terms agreed before integration
Institutional data controls
Discuss deployment, encryption, and data-handling requirements before integration.
Security Notice: Do not submit identifiable patient health information (PHI) or production secrets to preview endpoints.