There is no per-unit API price: price not verified.
#83 of 89 in Multimodal.
On MIEB lite · Document Understanding · English, Clip Vit Base Patch32 scores 12.4 vs 13.6 — lower.
Released 2021-02-26. It is the current version in its line.
Yes, the weights are open.
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Clip Vit Base Patch32 is an open-weights embeddings & retrieval model from OpenAI, released Feb 2021.
Jina Embeddings v5 Omni Nano (better), Argus Colqwen3.5 9B v0 (open weights).
BetterJina Embeddings v5 Omni NanounstatedOpen×6—$0.02Memory (4-bit): 0.1 GB → 0.6 GBDOpenArgus Colqwen3.5 9B v0unstated×7.2——Memory (4-bit): 0.1 GB → 5.3 GB
BetterEmbeddingGemma 2unstatedOpen×5.4—$0.02Memory (4-bit): 0.1 GB → 0.2 GB
Nemotron Colembed VL 8B v2Open×7.2——Memory (4-bit): 0.1 GB → 5.2 GBDArgus Colqwen3.5 4B v0unstatedOpen×7.2——Memory (4-bit): 0.1 GB → 2.8 GBvVultronRetrieverPrime Qwen3.5 8BOpen×7.1——Memory (4-bit): 0.1 GB → 5 GBvVultronRetrieverCore Qwen3.5 4.5BOpen×7.1——Memory (4-bit): 0.1 GB → 2.7 GB