get_by_text() and observe(). The vision-language models
understand a description for locator(query=...). The public catalog lists both
families with live pricing.
- CLI
- Python SDK
- Go SDK
- REST API
The CLI does not have a model-catalog command. Use an SDK or the public
REST operation, then pass the chosen engine or model to
axilio phone.Axilio models
The Axilio line comes in two tiers: Lite is free, and Pro reads harder screens such as small fonts and dense layouts for a per-call price. You do not pass these model IDs to the driver. Pick the tier with an OCR-engine option:- CLI
- Python SDK
- Go SDK
phone find-text and phone wait-for use their default OCR engine and do
not accept an engine override.- Python SDK
- Go SDK
Vision-language models
Describing something in plain English, such aslocator(query="the heart icon"),
runs a vision-language model. So does refining a text locator with nth,
within, has, or filter. Pass a catalog ID to choose one:
- CLI
- Python SDK
- Go SDK
- Python SDK
- Go SDK
model= off and Argus picks a sensible default. An id that isn’t in the
list below is rejected before anything is billed.
Vision-language calls are billed per token:
Prices are pulled live, so they’re never stale. See Usage
to track what you actually spend.
Calling Argus directly
The driver runs Argus for you on the live screen. If you have your own image to analyze, call it directly withclient.argus — the same models,
on any image. See the
Client reference
for the SDK methods (locate, detect, list_models), or the
Vision API reference for the REST
endpoints.
Next steps
Find
Where the engine and model options plug in.
Usage
See what your vision calls cost.