Mistral Embed is Mistral AI's general-purpose text embedding model with 1024 dimensions, designed for semantic search and retrieval tasks with a 55.26 score on the MTEB benchmark.
import { embed } from 'ai';
const result = await embed({ model: 'mistral/mistral-embed', value: 'Sunny day at the beach',})Mistral Embed launched alongside La Plateforme as Mistral AI's retrieval-focused embedding endpoint. Mistral Embed produces 1024-dimensional vector representations and scores 55.26 on the Massive Text Embedding Benchmark (MTEB), a standard evaluation suite for embedding model quality.
The embedding space preserves semantic similarity for nearest-neighbor retrieval. Documents with similar meaning cluster closely, while semantically distinct texts land farther apart in the vector space.
Mistral Embed integrates into retrieval-augmented generation (RAG) architectures where a Mistral AI generation model handles question answering and Mistral Embed indexes the knowledge base. Using the same provider ecosystem for both embedding and generation simplifies the stack and keeps provider management consolidated through AI Gateway.