Project AURIONAI Use-Cases Research & Innovation
OpenAI
embeddingfamily

CLIP

Image and text encoders trained together on 400 million image-caption pairs, used for zero-shot image classification and image-text search.

OpenAIOpenAIUSA
Diagram of CLIP contrastive pretraining and zero-shot classification, from the CLIP repository.
Levelfamily
Classembedding
Parametersnot in the notes
Contextnot in the notes
Released26 Feb 2021
Opennessunknown
Runs onnot in the notes
Statusactive

Lineage

OpenAICLIP ViT-L/14 336px belongs to this familyembedding22 Apr 2022
OpenAICLIP ViT-B/32 belongs to this familyembedding
OpenAICLIP ViT-L/14 belongs to this familyembedding427.62M
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Contrastive image-text encoders (CLIP and SigLIP lines)exemplar

Identity

Developer
OpenAI
Family
not in the notes
Released
26 Feb 2021 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text, image
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2103.00020 https://arxiv.org/abs/2103.00020
  2. github.com/openai/CLIP https://github.com/openai/CLIP
  3. github.com/GoogleCloudPlatform/vertex-ai-samples/tree/ma... https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/model_garden
  4. huggingface.co/api/models?pipeline_tag=zero-shot-image-class... https://huggingface.co/api/models?pipeline_tag=zero-shot-image-classification&sort=downloads&limit=50
  5. huggingface.co/openai/clip-vit-base-patch32 https://huggingface.co/openai/clip-vit-base-patch32
  6. huggingface.co/openai/clip-vit-large-patch14 https://huggingface.co/openai/clip-vit-large-patch14

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "CLIP", https://aurion.semai.id/models/openai-clip/, records of October 2026.