Codestral Embed
Codestral Embed is Mistral's first embedding model specialized for code, outperforming general-purpose and competing code embedding models on real-world retrieval benchmarks.
import { embed } from 'ai';
const result = await embed({ model: 'mistral/codestral-embed', value: 'Sunny day at the beach',})About Codestral Embed
Released May 28, 2025, Codestral Embed is Mistral's first embedding model purpose-built for code. Codestral Embed achieves an 85% average score on code retrieval benchmarks, outperforming Voyage Code 3, Cohere Embed v4.0, and OpenAI's large embedding model on evaluations derived from real-world code data.
Codestral Embed supports variable dimensions with ordered relevance. You can truncate to the first n dimensions and still get ranked embeddings. Mistral's benchmarks show retrieval performance even at 256 dimensions with int8 precision, enabling index size reduction without proportional quality loss.
The context window is 0 tokens. For repositories with large files, Mistral recommends chunking at 3,000 characters with 1,000-character overlap. This balances retrieval recall against chunk boundary artifacts.