Computer visionSearch and RAG

CLIP (OpenAI)

The 2021 model that first linked images and text: search photos by words and classify them without training. English only; SigLIP 2 or PE are usually chosen today.

The last open version came out in Apr 2022. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
OpenAI, USA
First release
Jan 2021
Latest release
Apr 2022
Sizes
about 0.15B – 0.6B
License
Commercial use allowedMIT
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Retail and marketplaces, Media and production, Security
Deploy on your server Hugging Face GitHub

What it does

  • Image search by text query
  • Automatic tags for a catalog
  • Finding similar images

Where it is used

E-commerceStock photo libraries and mediaContent moderation

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. ViT-L/14@336px
  2. ViT-L/14 и RN50x64
  3. ViT-B/16 и RN50x16
  4. RN101 и RN50x4
  5. CLIP ResNet-50 и ViT-B/32

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can CLIP (OpenAI) be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does CLIP (OpenAI) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does CLIP (OpenAI) support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download CLIP (OpenAI) and what does it cost?

The CLIP (OpenAI) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Computer visionSigLIP (наследник CLIP)Google · USACommercial use allowed

Models that map images and text into a shared space: you can search photos by words and classify images without training. OpenAI's CLIP (2021) is the predecessor.

DetailsComputer visionPerception Encoder (PE)Meta · USACommercial use allowed

Meta's family of encoders for images and video, and with PE-AV also for audio. PE-Core searches by text more accurately than SigLIP 2 (per Meta); small versions are available.

DetailsComputer visionruCLIP (ai-forever)Sber AI and SberDevices (ai-forever) · RussiaCommercial use allowed

A Russian version of CLIP: matches images with Russian captions. Lets you search photos by description and sort images into categories without training.

Details

Source: github.com/openai/CLIP. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.