Embedding Model Comparison

Side-by-side pricing, dimensions, and quality scores for popular embedding models.

ModelProviderPrice / 1M TokensDimensionsMax TokensMTEB Score
text-embedding-005GoogleFree*7682,04863
text-embedding-3-smallOpenAI$0.021,5368,19162
voyage-3-liteVoyage$0.0251232,00062
jina-embeddings-v3Jina$0.021,0248,19266
voyage-3Voyage$0.061,02432,00067
embed-v4Cohere$0.101,02451264
mistral-embedMistral$0.101,0248,19261
text-embedding-3-largeOpenAI$0.133,0728,19165
* Google text-embedding-005 has a generous free tier. Check current limits at cloud.google.com.

Cost vs. Quality Tradeoff

The cheapest model isn't always the best choice. Consider your use case: for high-volume RAG pipelines where marginal quality differences compound, a higher-quality model like Voyage-3 or OpenAI text-embedding-3-large may deliver better end-user results despite higher costs. For simple classification or clustering tasks, budget models work well.

Key considerations