A
APPLE / apple/DepthPro2-L

Depth Pro 2 L

Apple family released on November 20 that estimates per-pixel metric depth from photos and video. It combines attention across frames with a decoder per image to preserve edges and temporal consistency. Each size has its own weights; the focal estimator is a separate component.

01 / SUMMARY

The essential

ORIENTATIONMonocular metric depth · 334M

Primary use stated or inferred cautiously from official documentation.

CONTEXTFrames at input resolution

Maximum input capacity when published by the source.

EXITDepth in meters per pixel

Documented maximum generation limit.

ACCESSHugging Face · downloadable checkpoint

Verified availability channels.

MODEL TYPEVision and geometry

Primary functional family and verified specialties.

LICENSEApple AMLR · non-commercial research

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDapple/DepthPro2-L
Model typeVision and geometry
Access modelOpen weights
LicenseApple AMLR · non-commercial research
DeploymentSelf-hosted
Release20 NOV 2026
Knowledge cutoffNot published
EntranceImage · Video
ExitDepth maps
Context windowFrames at input resolution
maximum outputDepth in meters per pixel
ReasoningNot published
Published tools
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningNot published
Verified platformsHugging Face
BEST SUITED FOR

Research into visual geometry, video and scene reconstruction.

WORTH MONITORING

Apple AMLR limits the weights to non-commercial scientific research and academic development; it is not Apache 2.0. Infinite values for sky or distant regions are not formatting errors. The focal estimator adds 23.5M parameters to each size.

03 / CAPABILITIES

What it can do

01

Orientation

Research into visual geometry, video and scene reconstruction.

02

Context

Frames at input resolution · Depth in meters per pixel

03

Tools and integration

Not published

04

Access

Hugging Face · downloadable checkpoint

Input modalities
ImageVideo
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNo published official API rateStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputSelf-hosted infrastructure costMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

No verified official API tariff. Self-hosting requires memory, compute and maintenance; downloadable weights do not make inference free.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

Apple performance measurements on one NVIDIA B200, BF16 and uncompiled PyTorch: a 32-frame 1080p clip processed in one call, including the focal estimator. FPS and reserved memory apply to that protocol, not single-frame latency or any GPU.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

apple/DepthPro2-L

Version added to Inferama's verified catalog.

07 / SOURCES

Traceability