Client

Python’s high-level Client authenticates Platform requests, opens phone sessions, and exposes the Argus vision service.

from axilio.platform import Client

client = Client()

The constructor reads AXILIO_API_KEY. See Configuration for every client option.

`client.session()`

Use the context manager so the dedicated phone is released on every exit path:

with client.session("android", phone_id="ph_123") as driver:
    driver.get_by_text("Continue").tap()

Parameter	Type	Default	Description
`phone_type`	`"android"`	`"android"`	Device kind. Android is the supported customer platform.
`phone_id`	`str`	`None`	Dedicated phone to allocate. Pass this for customer-facing sessions.
`workflow_id`	`str`	`None`	Associate a direct allocation with a workflow.
`open_timeout`	`float`	`10.0`	Seconds to wait while opening the DCP connection.
`default_ocr_engine`	`str`	`None`	Session-wide OCR default; omission resolves to `free`.
`default_model`	`str`	`None`	Session-wide semantic-vision model; omission lets the service choose.

The yielded driver closes its connection and deallocates the phone when the block exits. An OCR engine or model set on a locator overrides the session default.

Call Argus on your own image

The phone driver already uses Argus for screen understanding. Use the direct clients below when the input is an image you provide. The CLI does not expose a direct own-image Argus command.

Locate a described target

Python SDK
Go SDK
REST API

result = client.argus.locate(
    image=image_b64,
    query="the blue Continue button",
)
if result.found:
    print(result.bbox, result.confidence, result.cost_microdollars)

visionClient := argusclient.NewClient(
    argusoption.WithAPIKey(os.Getenv("AXILIO_API_KEY")),
)
result, err := visionClient.Vision.Locate(ctx, &argusapi.LocateRequest{
    Image: imageB64,
    Query: "the blue Continue button",
})
if err != nil {
    log.Fatal(err)
}
if result.Found {
    fmt.Println(result.Bbox, result.Confidence, result.CostMicrodollars)
}

Import argusapi, argusclient, and argusoption from the github.com/axilioai/platform-go/argus module tree.

REST API References:

Run locate: POST /api/v1/vision/locate

Examples use Bash. To run them in PowerShell, see Run the curl examples on Windows.

jq -n \
  --arg image "$IMAGE_B64" \
  --arg query "the blue Continue button" \
  '{image: $image, query: $query}' |
  curl --silent --show-error --fail-with-body \
    --request POST \
    --url https://argus.axilio.ai/api/v1/vision/locate \
    --header "X-Axilio-Api-Key: $AXILIO_API_KEY" \
    --header "Content-Type: application/json" \
    --data-binary @-

The Python method also accepts optional model and precomputed OCR texts. The Go request exposes the corresponding Model and Texts fields.

Detect text and icons

Python SDK
Go SDK
REST API

result = client.argus.detect(
    image=image_b64,
    inference_type="combined",
    ocr_engine="free",
)

result, err := visionClient.Vision.Detect(ctx, &argusapi.InferenceRequest{
    Image:         imageB64,
    InferenceType: argusapi.InferenceTypeCombined.Ptr(),
    OcrEngine:     argusapi.String("free"),
})
if err != nil {
    log.Fatal(err)
}
fmt.Println(result.GetType())

REST API References:

Run inference: POST /api/v1/vision/detect

Examples use Bash. To run them in PowerShell, see Run the curl examples on Windows.

jq -n --arg image "$IMAGE_B64" \
  '{image: $image, inference_type: "combined", ocr_engine: "free"}' |
  curl --silent --show-error --fail-with-body \
    --request POST \
    --url https://argus.axilio.ai/api/v1/vision/detect \
    --header "X-Axilio-Api-Key: $AXILIO_API_KEY" \
    --header "Content-Type: application/json" \
    --data-binary @-

Detection also accepts confidence_threshold and nms_iou_threshold.

List supported models

Python SDK
Go SDK
REST API

models = client.argus.list_models()
for model in models.data:
    print(model.id, model.pricing)

models, err := visionClient.Vision.ListModels(ctx)
if err != nil {
    log.Fatal(err)
}
for _, model := range models.Data {
    fmt.Println(model.ID, model.Pricing)
}

REST API References:

List models: GET /api/v1/vision/models

Examples use Bash. To run them in PowerShell, see Run the curl examples on Windows.

curl --silent --show-error --fail-with-body \
  --url https://argus.axilio.ai/api/v1/vision/models

Driver reference

See every live phone action.

Models

Understand model selection and pricing.

Drivers

Mobile driver

Models

`client.session()`

Call Argus on your own image

Locate a described target

Detect text and icons

List supported models

See also

Driver reference

Models

​client.session()

​Call Argus on your own image

​Locate a described target

​Detect text and icons

​List supported models

​See also

Driver reference

Models

`client.session()`

Call Argus on your own image

Locate a described target

Detect text and icons

List supported models

See also