Mistral AI
Mistral: Mistral Embed 2312
mistralai/mistral-embed-2312
Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively capture semantic relationships in text.
Input
$0.1
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
8.19K
tokens
Embeddings output · Token reference fields do not establish an output-unit price.
Limits
Context
8,192
tokens
Max output
6,553
80% of the context window
Model facts
Author
Mistral AI
Tokenizer
Mistral
Modality
Text -> Embeddings
Created
Oct 31, 2025
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · TextOutput · Embeddings