Updated daily at 05:00 UTC
Embedding
CLIP
OpenAI's open-weights contrastive image-text models that embed images and text in a shared space.
By OpenAI.
Versions
4 versions
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| CLIP ViT-L/14@336pxCLIP · Open weights | OpenAI | Embedding | Apr 2022 | — | — | — |
| CLIP ViT-L/14 and RN50x64CLIP · Legacy · Open weights | OpenAI | Embedding | Jan 2022 | — | — | — |
| CLIP ViT-B/16 and RN50x16CLIP · Legacy · Open weights | OpenAI | Embedding | Jul 2021 | — | — | — |
| CLIP (RN50, ViT-B/32 and RN101, RN50x4)CLIP · Legacy · Open weights | OpenAI | Embedding | Jan 2021 | — | — | — |
