Free embeddings dimension reference — vector size, cost, and benchmarks for OpenAI, Cohere, Voyage, and open models.
Embeddings dimension reference
Higher dimensions can improve recall, but they also increase storage, RAM, and vector index cost. Match the model to search quality and scale needs.
Was Embeddings Dimension Reference useful?
Your vote helps us prioritize improvements.
The QuickToolz Embeddings Dimension Reference lists every popular embedding model with its vector dimensionality, max input tokens, price per million tokens, MTEB benchmark score, and recommended use case. Filter by provider, cost, or dimension — perfect for choosing the right model for RAG, search, or clustering.
Everything you need, nothing you don’t. Built for speed and simplicity.
OpenAI, Cohere, Voyage, Jina, Mistral, NVIDIA, BGE, E5, Nomic.
Filter and sort by dimension, cost, score, and context.
Latest MTEB averages for retrieval, clustering, classification.
Everything you need, nothing you don’t. Built for speed and simplicity.
OpenAI, Cohere, Voyage, Jina, BGE, E5, and more.
Got questions? We’ve got answers. Common questions about Embeddings Dimension Reference.
By dimension, cost, MTEB score, max tokens.
Pick the right model for your latency/cost/quality budget.