AI Model Radar
中文 EN

DINOv3

Meta
Model overview

DINOv3

Meta's current public DINOv3 open-weight self-supervised vision representation model.

embeddingsegmentationobject trackingvisual segmentationevaluationlocal inference
CompareCompanyRankingsPublic signals
Representative version

DINOv3

CompanyMeta
ReleaseNot disclosed
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
ContextNot disclosed
Input modalitiesimage
Output modalitiesvector
Tool use / function callingNot disclosed
Structured output / reasoningNot disclosed
Vision / audio / videoConfirmed: Vision; Not shown: Audio, Video
Open weights / LicenseWeights available / license pending verification
meta-dinov3-current · License source pending verification
Vendor APINot disclosed
API source pending verification
OpenRouterNot separately listed on OpenRouter
PricingNo reliable public source
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use casesvisual segmentation / research evaluation / local inference / retrieval embeddings
Claim evidenceRelease / model specs / weightsDINOv3 | Meta AIDINOv3
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versionDINOv3
meta-dinov3-current
PricingNo reliable public source
ContextNot disclosed
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Evidence gaps

Public display boundary

Parameter scale not disclosedRelease date not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed