$0.13 per 1M tokens.
There is no free API; the cheapest paid price is $0.13 per 1M input tokens.
#39 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Polish v1 · Pair Classification · Polish, Text Embedding 3 Large scores 82.9 vs 82.9 — about the same.
Through the OpenAI API.
Released 2024-01-25. It is the current version in its line.
No, Text Embedding 3 Large is a closed model available through an API. The closest open-weights option here is STS Multilingual Mpnet Base v2.
Text Embedding 3 Large is a closed embeddings & retrieval model from OpenAI, released Jan 2024.
Bge Multilingual Gemma2 (cheaper), Qwen 3 Embedding 8B (better), STS Multilingual Mpnet Base v2 (open weights).
CheaperBge Multilingual Gemma2unstatedOpen+8%-14%$0.11
BetterQwen 3 Embedding 8BunstatedOpen+6%-92%$0.01GOpenSTS Multilingual Mpnet Base v2unstated+10%——Max input: 8K tokens → 0K tokensiCheaperMultilingual E5 Large InstructunstatedOpen+5%-92%$0.01Max input: 8K tokens → 1K tokensiCheaperE5 Mistral 7B InstructunstatedOpen+5%-83%$0.022
Jina Embeddings v5 Text SmallunstatedOpen+5%-62%$0.05