We are excited to release Codestral Embed, our first embedding model specialized for code. It performs especially well for retrieval use cases on real-world code data. Codestral Embed significantly outperforms leading code embedders in the market today: Voyage Code 3, Cohere Embed v4.0 and OpenAI’s large embedding model. Codestral Embed can output embeddings with different dimensions and precisions, and the figure below illustrates the trade-offs between retrieval quality and storage costs. Codestral Embed with dimension 256 and int8 precision still performs better than any model from our competitors. The dimensions of our embeddings are ordered by relevance. For any integer target dimension n, you can choose to keep the first n dimensions for a smooth trade-off between quality and cost.
Notes: Unlikely to use >1e25 FLOP (lightweight embedding model). Meanwhile, >1e23 FLOP is likely given compute used for code LLMs generally.
Training Code AccessibilityCodestral Embed is available on our API under the name `codestral-embed-2505` at a price of $0.15 per million tokens. It is also available on our batch API at a 50% discount. For on-prem deployments, please contact us to connect with our applied AI team.