$0.025 per 1M tokens.
There is no free API; it costs $0.025 per 1M tokens.
#33 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB English v2 · Pair Classification · English, Text Embedding 005 scores 87.6 vs 87.6 — about the same.
Released 2024-11-18. It is the current version in its line.
No, Text Embedding 005 is a closed model available through an API. The closest open-weights option here is QZhou Embedding.
Text Embedding 005 is a closed embeddings & retrieval model from Google, released Nov 2024.
E5 Mistral 7B Instruct (cheaper), Voyage Large 2 Instruct (better), QZhou Embedding (open weights).