Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | nvidiaNemotron-3-Embed-1B-BF16Remove × | googleembeddinggemma-2Remove × | voyageaiVoyageAI by MongoDB: voyage-code-4Remove × |
|---|---|---|---|
| What’s different | Nemotron-3-Embed-1B-BF16 is a compact multilingual text embedding model from NVIDIA, pruned and distilled from Ministral-3 to ~1B parameters, that maps text into 2048-dimensional dense vectors for retrieval… | EmbeddingGemma 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,… | voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048, 1024, 512, and 256... |
| Date | Jul 15, 2026Listed | Oct 8, 2026Listed | Aug 13, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | See provider quotes | See provider quotes | $0.12 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 0 endpoints → | 0 endpoints → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | |||
| FreshStack · MTEB 2.14.3 ↗MTEB 2.14.3; test/default; dataset 7a20df1a | 0.4173 ↗Revision f8801746; test/defaultContributor reported | Not reported | Not reported |
Specifications | |||
| Context window | 32.8K | 8.2K | 32K |
| Max output | — | — | 28.8K |
| Parameters | 1B | — | — |