Embedding model

mistral-embed

General-purpose Mistral text embedding model for semantic search, clustering, classification, and retrieval workflows. Token IDs on this page use the shared Mistral Tekken v3 tokenizer vocabulary.

Mistral

Endpoint
Embeddings
Status
Current
Default dimensions
1,024
Max input
8,192 tokens
Tokenizer
mistral_tekken_v3
Tokenizer tokens
131,072 known tokens (130,072 mergeable)
Open model token IDs Open tokenizer reference Mistral docs