Quickstart

Quickstart

from visynx import Visynx

vf = Visynx(api_key="vf_...")          # or set VISYNX_API_KEY
model = vf.model("shelf-scanner/3")    # your project name and version

result = model.predict("shelf.jpg", confidence=0.4)

for d in result:
    print(d.class_name, round(d.confidence, 2), d.box)

result.save("annotated.jpg")

bottle 0.94 [412.0, 118.5, 501.2, 388.0]
bottle 0.91 [502.6, 121.0, 590.4, 390.7]
can    0.78 [604.1, 210.3, 664.9, 372.2]

visynx pulls in only requests and Pillow. No OpenCV, no numpy, no torch — the models run on Visynx's GPUs, not yours.

Naming a model

Your project and its training version — the same name the app shows you:

model = vf.model(train_name="shelf-scanner", version="3")
model = vf.model("shelf-scanner/3")          # the same thing, as one handle
model = vf.model(train_name="shelf-scanner") # newest version

Or take the model with you

Professional and Enterprise accounts can download the weights and run them themselves. Every plan can keep using hosted predict() instead — downloading is an option, not a step.

pip install "visynx[local]"

vf = Visynx(api_key="vf_...")
model = vf.model(train_name="shelf-scanner", version="3")

model.download(path="./models/shelf-scanner")                # native weights
model.download(path="./models/shelf-scanner", format="onnx") # or a portable export
model.download(path="./models/shelf-scanner", format="edge") # ~4x smaller, for devices

local = vf.load_model("./models/shelf-scanner")   # or visynx.load_model(...)
result = local.predict("image.jpg", confidence=0.25)
result.save("annotated.jpg")

Plan	Hosted predict()	download()	Local predict()
Starter	yes	no	no
Professional	yes	yes	yes
Enterprise	yes	yes	yes

The check is the server's: an account without the feature gets a PlanRequiredError and no bytes, whether the call comes from here or from curl. Downloading someone else's model is refused the same way.

One local call covers every export and every kind of model — detection, instance segmentation, pose, classification, semantic segmentation, in FP32, FP16 or Edge. visynx reads what the file is, feeds it the way it expects, and returns predictions in your image's own pixel coordinates: boxes, outlines, keypoints, or a blended mask — the same Result the hosted call returns.

local.labels                                 # class names, read from the file
local.runtime                                # 'portable' or 'native'
local.device                                 # where it is running

Choosing where it runs

Any format — a checkpoint or any of the exports — takes a device:

vf.load_model("./models/x")                  # "auto": the GPU when there is one
vf.load_model("./models/x", device="cpu")    # keep it off the GPU entirely
vf.load_model("./models/x", device="gpu")    # insist on the GPU

"gpu" is a requirement rather than a preference, so a machine without one gets a VisynxError saying what is missing — never a silent fall back to the CPU at a tenth of the speed. "auto" is the one that falls back, by design.

Portable (.onnx) exports need nothing but visynx[local]. A native checkpoint also needs the runtime it was trained with; python -m visynx setup installs it.

Run on NVIDIA Jetson

On a Jetson (JetPack 6), a Jetson export loads through TensorRT. The engine is built on the device the first time the model loads and cached after that: INT8 when the export ships calibration, FP16 otherwise. TensorRT needs the onnxruntime-gpu build for JetPack 6 in place of the standard onnxruntime.

Pair the device once. This checks the key and saves it, so Visynx() needs no arguments on this device:

python -m visynx pair

import visynx

vf = visynx.Visynx()                                   # the paired key
model = vf.model("shelf-scanner/3")
model.download(path="./models/shelf", format="jetson_fp16")   # or "jetson_int8"

local = visynx.load_model("./models/shelf")
cam = visynx.open_camera("csi://0")         # or "usb://0", or an rtsp:// URL
ok, frame = cam.read()
result = local.predict(frame[..., ::-1])    # OpenCV frames are BGR; predict reads RGB

python -m visynx build-engine ./models/shelf builds the engine ahead of time, so the first frame is not the slow one. Cameras need OpenCV (pip install opencv-python-headless). Downloading a model is a Professional and Enterprise feature; on other plans, hosted predict() works on a Jetson like anywhere else.

Find your models

for m in vf.models():
    print(m.slug, m.display_name)
# shelf-scanner/3   Shelf Scanner v3
# defect-seg/1      Defect Seg v1

"shelf-scanner/3" is the model's slug — your project name and its training version, the same name you see in the app. A raw "yolo/<job_id>" also works and skips the lookup.

What you get back

predict() returns a Result: iterate it for detections, or reach for the raw API payload with .json().

result = model.predict("shelf.jpg")

len(result)              # 3
result.detections[0]     # Detection('bottle', 0.94)
result.json()            # the raw API response, untouched

result.plot()            # a PIL image with boxes drawn on
result.save("out.jpg")   # ...written to disk

Each Detection carries class_id, class_name, confidence, and box ([x1, y1, x2, y2] in absolute pixels). Segmentation models add polygons; pose models add keypoints.

Anything image-shaped works

model.predict("shelf.jpg")                  # a path
model.predict("frames/")                    # a directory -> list of Results
model.predict(open("shelf.jpg", "rb"))      # an open file
model.predict(pil_image)                    # a PIL image
model.predict(numpy_array)                  # a numpy array (from OpenCV, say)

Beyond boxes

Two flags the hosted GPUs do for you, with nothing extra to install. Each runs a second model, so each costs extra credits:

# Turn every detected box into a precise instance polygon with SAM 2
result = model.predict("shelf.jpg", segment=True)
result.detections[0].polygons

# Add a monocular depth map, and a relative distance per detection
result = model.predict("shelf.jpg", depth=True)
result.detections[0].depth_median      # 0-1, higher is closer
result.depth_image.save("depth.png")

Semantic-segmentation models return a dense mask instead of boxes:

result = model.predict("road.jpg")
result.semantic["legend"]     # [{'class_id': 1, 'class_name': 'road', ...}]
result.save("mask.jpg")       # the mask, blended over your image

Get an API key

In Visynx, go to Settings → API Keys, create a key, and copy the secret — it is shown once. Keys start with vf_, never expire, and can be locked to specific IPs or CIDR ranges. Keep it out of source control:

vf = Visynx()                      # reads VISYNX_API_KEY

A predict() call spends 1 Vision Credit on the checkpoint or the full-precision graph, and 2 on the optimised runtimes (format="onnx_fp16" or format="edge"); format="auto" is billed for whichever it runs. segment=True and depth=True each add a surcharge for the extra model they run. You are charged only after the inference succeeds — a failed call is free — and a call retried after a 429 is billed once, not twice.

Some endpoints are deliberately not reachable with an API key: batch prediction over a whole dataset, live-camera inference, workflow runs, and the AI-labelling tools (SAM/DINO/box-prompt). Those run from the Visynx app with a signed-in session. Calling them with a key returns PermissionDeniedError.

Errors

Every failure is a typed exception, and it quotes the response's X-Request-ID when the server sent one — include it if you contact support. (Authentication failures are rejected before that header is assigned, so 401s carry none.)

Exception	Means	Do
AuthenticationError	key invalid or revoked	create a new key
PermissionDeniedError	email unverified, or the key's IP allowlist rejected you	verify your email / check the allowlist
InsufficientCreditsError	out of Vision Credits	top up
PlanRequiredError	your plan does not include this (e.g. downloading a model)	upgrade, or use hosted predict()
ModelNotFoundError	no such model, or not yours	check vf.models()
PayloadTooLargeError	image over 50 MB	resize before sending
RateLimitError	rate limited, retries exhausted	back off
MaintenanceError	platform in maintenance	retry later

429s are retried automatically, honouring the server's Retry-After. All of these subclass VisynxError, so one except VisynxError catches everything.

Self-hosting

Point the client at your own deployment:

vf = Visynx(api_key="vf_...", api_url="https://visynx.internal/api")

or set VISYNX_API_URL.