Microsoft: Multilingual E5 Large
Multilingual E5 embedding model for semantic search and clustering in about 100 languages. Inputs are limited to 512 tokens, so long documents need to be split into chunks first.
- Maker
- Microsoft
- Model ID
intfloat/multilingual-e5-large- Context length
- 512 tokens
- Input
- text
- Output
- embeddings
Providers
- Berget AI: Data centers: Sweden; Sovereign EU; Zero data retention
Facts as Markdown · Quickstart
More models by Microsoft
- Microsoft: Multilingual E5 Large Instruct Microsoft · 512 tokens · embeddings
More Embedding models
- BAAI: BGE M3 BAAI · 8,192 tokens · embeddings
- BAAI: BGE Multilingual Gemma2 BAAI · 8,192 tokens · embeddings
- Qwen: Qwen3 Embedding 8B Qwen · 32,768 tokens · embeddings