Side by side

See the difference.

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

Scroll to compare models →

Comparison of embeddinggemma-2, Google: Gemini Embedding 2 (batch), Qwen3-Embedding-8B
3 modelsgoogleembeddinggemma-2Remove ×googleGoogle: Gemini Embedding 2 (batch)Remove ×QwenQwen3-Embedding-8BRemove ×
What’s differentEmbeddingGemma 2 is a 740M parameter multimodal embedding model from Google DeepMind that maps text (incl. code), images, video and audio, alone or interleaved, into a single 768-dimensional vector space,…Gemini Embedding 2 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 (RAG). It…The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3…
DateOct 8, 2026ListedMay 20, 2026ListedJun 10, 2025Listed
Listed rateSee provider quotes$0.10 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗$0.01 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints0 endpoints →1 endpoint →1 endpoint →
FreshStack · MTEB 1.38.43 ↗MTEB 1.38.43; test/default; dataset 7a20df1aNot reportedNot reported0.43017 ↗Revision 4e423935; test/defaultContributor reported
Context window8.2K8.2K41K
Max output—7.4K32K
Parameters——8B
Image inputNot reportedSupportedNot reported
Audio inputNot reportedSupportedNot reported
Video inputNot reportedSupportedNot reported
Open weightsNot reportedNot reportedSupported

Add another model

Search all models →