---
title: "Discussion on \"Choosing Embedding Models and Dimensions: Why 1536 Isn't Always Better Than 384\" | Hashnode"
description: "Discussion on \"Choosing Embedding Models and Dimensions: Why 1536 Isn't Always Better Than 384\". Learn how to choose embedding models and dimensions for production RAG systems. Compare OpenAI, Voyage AI, and Google's free options for embedding"
url: "https://hashnode.com/posts/choosing-embedding-models-dimensions-production-tradeoffs/698b7959ce66e4a1190732b1"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Choosing Embedding Models and Dimensions: Why 1536 Isn't Always Better Than 384](https://blog.pragmaticbyharsh.com/choosing-embedding-models-dimensions-production-tradeoffs?utm_source=hashnode&utm_medium=feed)

Learn how to choose embedding models and dimensions for production RAG systems. Compare OpenAI, Voyage AI, and Google's free options for embedding

Feb 10 · 11 min read · blog.pragmaticbyharsh.com  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#embedding](https://hashnode.com/tag/embedding)
-   [#rag](https://hashnode.com/tag/rag)
-   [#vector-database](https://hashnode.com/tag/vector-database)
-   [#llm](https://hashnode.com/tag/llm)

## Written by

[Harshavardhanan](https://hashnode.com/@harshavardhan)

@harshavardhan

  
[View profile](https://hashnode.com/@harshavardhan)

Architect In Role. Developer by Heart

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
