OpenAI logo

CLIP

CLIPv1Current
byOpenAIOpenAI(ai lab)
Released January 5, 2021
Context--
CategoryVision Model

About CLIP

CLIP is OpenAI’s Contrastive Language-Image Pretraining model family, trained to connect images and natural-language text so it can perform zero-shot image classification and image-text retrieval.

Capabilities

visiontextzero shot classificationimage text retrieval

Input Modalities

imagetext

Output Modalities

embeddingssimilarity-scores

Technical Details

API Identifier
openai/clip
Category
Vision Model

Tags

vision-languageopenaizero-shotimage-classificationmultimodalretrieval

Benchmarks

Performance scores for CLIP across standard benchmarks.

ImageNet zero-shot top-1official-openai-clip-paper · Jan 2021
76.2

Pricing and access

Open-source research model/checkpoints; no hosted API price is specified in the GitHub repository.

OpenAI logo
OpenAIai lab

Creating safe AGI that benefits all of humanity

249 Tools58 MCP Servers14 ModelsFounded 2015San Francisco, CA
View full profile

Tools by OpenAI

Other AI tools from the same organization.

AI Models by OpenAI

AI models from the same organization.

ModelContext WindowPrice (In / Out per M)
GPT-6.1 SolCurrent1.1M$2.00 / $10.00
GPT-6 SolCurrent1.1M$2.00 / $10.00
GPT-6 LunaCurrent1.1M$0.10 / $0.50
GPT-5.6 LunaCurrent1.1M$0.20 / $1.20
GPT-5.6 TerraCurrent1.1M$2.00 / $12.00
GPT-5.6 SolCurrent1.1M$4.00 / $20.00

MCP Servers by OpenAI

Connect this tool to AI assistants via the Model Context Protocol.

Related News

Latest coverage and updates.