Skip to content

Codestral Embed

Codestral Embed is Mistral AI's first embedding model specialized for code, outperforming general-purpose and competing code embedding models on real-world retrieval benchmarks.

index.ts
import { embed } from 'ai';


const result = await embed({
  model: 'mistral/codestral-embed',
  value: 'Sunny day at the beach',
})

What To Consider When Choosing a Provider

  • Configuration: Codestral Embed supports variable embedding dimensions, letting you tune the size-versus-quality tradeoff to match your vector store's cost and latency constraints.
  • Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

When to Use Codestral Embed

Best For

  • RAG pipelines for coding agents: Building pipelines that retrieve relevant code snippets
  • Semantic code search: Large repositories where keyword search is insufficient
  • Duplicate code detection: Similarity analysis across codebases using Codestral Embed's 85% average on code retrieval benchmarks
  • Code clustering: For analytics, refactoring identification, or repository organization
  • Large-scale indexing pipelines: Workloads where embedding cost is a primary concern at millions of documents

Consider Alternatives When

  • General text documentation: You need to embed prose rather than source code (consider Mistral AI Embed)
  • Natural language retrieval: Your workload is primarily over descriptions of code rather than code itself
  • Generation alongside embedding: You require both capabilities in a single model call

Conclusion

Codestral Embed fills a gap that general-purpose embedding models leave open. Code has structural patterns, syntax, and semantics that differ from prose, and a model trained on real-world code data retrieves it more accurately. For teams building coding agents, code search, or repository analytics, Codestral Embed is more precise than adapting a text embedding model.

Frequently Asked Questions

  • What makes Codestral Embed different from a general text embedding model?

    Codestral Embed was trained on real-world code data and optimized for code retrieval tasks. These tasks involve matching function signatures, logic patterns, and structural similarities that general text models don't capture well.

  • What is the context window for Codestral Embed?

    0 tokens. For files larger than this, chunk at 3,000 characters with 1,000-character overlap.

  • What embedding dimensions does Codestral Embed support?

    Variable dimensions with ordered relevance: you can keep the first n dimensions for a quality-versus-cost tradeoff. Codestral Embed scores well on retrieval at 256 dimensions with int8 precision in published benchmarks.

  • What is the pricing for Codestral Embed?

    Check the pricing panel on this page for today's numbers. AI Gateway tracks rates across every provider that serves Codestral Embed.

  • Can Codestral Embed be used for duplicate code detection?

    Yes. Semantic similarity via embeddings is an effective approach for identifying duplicate or near-duplicate code patterns that differ syntactically but are logically equivalent.

  • How does Codestral Embed compare to Mistral AI Embed?

    Mistral AI Embed is a general-purpose text embedding model. Codestral Embed was trained specifically for code and outperforms general models on code retrieval benchmarks. Use Codestral Embed when your corpus is source code; use Mistral AI Embed for natural language documents.