Side by side

See the difference.

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

Scroll to compare models →

Comparison of embeddinggemma-2, Hi3D 3D Part Splitter, LiquidAI: LFM2.5-Embedding-350M (free)
3 modelsgoogleembeddinggemma-2Remove ×hitem3dHi3D 3D Part SplitterRemove ×liquidLiquidAI: LFM2.5-Embedding-350M (free)Remove ×
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,…Split a 3D model into parts with Hi3D.LFM2.5-Embedding-350M is a text embedding model from Liquid AI. It produces 1,024-dimensional embeddings for retrieval and semantic search. Successful OpenRouter requests and embeddings may be retained and…
DateOct 8, 2026ListedJul 31, 2026ListedAug 18, 2026Listed
Listed rateSee provider quotes$0.40/ generationfal · all routes ↗$0.00 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints0 endpoints →1 endpoint →1 endpoint →
Context window8.2K—512
Max output——460
Parameters———
Open weightsNot reportedNot reportedSupported

Add another model

Search all models →