Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of VoyageAI by MongoDB: voyage-4, Google: Gemini Embedding 2 Preview
2 modelsvoyageaiVoyageAI by MongoDB: voyage-4Remove ×googleGoogle: Gemini Embedding 2 PreviewRemove ×
What’s differentvoyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple…Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation…
DateJul 27, 2026ListedApr 17, 2026Listed
Listed rate$0.06 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗$0.20 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints1 endpoint →1 endpoint →
Context window32K8.2K
Max output28.8K7.4K
Parameters——
Image inputNot reportedSupported
Audio inputNot reportedSupported
Video inputNot reportedSupported

Add another model

Search all models →