Guides
Python Bindings
Use VisionSqueezer from Python via native pyo3 wheels.
pip install vision-squeezer ships native wheels (pyo3 + maturin) for Linux, macOS, and Windows. No Rust toolchain required.
Terminal
pip install vision-squeezer
API
optimize_image
import vision_squeezer as vs
report = vs.optimize_image(
"screenshot.png", # str path or bytes
model="claude", # claude | gpt4o | gpt5 | gemini
quality=75,
format="jpeg", # jpeg | webp | avif
smart_crop=False,
auto_quality=None, # e.g. 0.95 to target SSIM
output_path=None, # write to disk if set
)
print(report["tokens_saved"], report["size_reduction_pct"])
Inputs accept both str (file paths) and bytes (raw image data). The returned dict contains bytes, base64, dimensions, byte counts, token counts, and the chosen quality.
estimate_tokens
vs.estimate_tokens(width=2400, height=1670, model="claude")
# -> { "tokens": ... }
optimal_dimensions
vs.optimal_dimensions(width=4096, height=3072, model="gpt4o")
# -> { "width": ..., "height": ... }
Pipeline example
import vision_squeezer as vs
# Estimate before committing
est = vs.estimate_tokens(4096, 3072, model="gpt4o")
if est["tokens"] > 1000:
vs.optimize_image(
"large.png",
model="gpt4o",
auto_quality=0.95,
format="avif",
output_path="large.optimized.avif",
)