Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | BAAIbge-m3Remove × | intfloatmultilingual-e5-large-instructRemove × | BAAIbge-m3-multi-8kRemove × |
|---|---|---|---|
| What’s different | BGE-M3 is a versatile text embedding model that supports multi-functionality, multi-linguality, and multi-granularity, allowing it to perform dense retrieval, multi-vector retrieval, and sparse retrieval in… | The Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:”… | BGE-M3 is a multilingual text embedding model developed by BAAI, distinguished by its Multi-Linguality (supporting 100+ languages), Multi-Functionality (unified dense, multi-vector, and sparse retrieval),… |
| Date | May 27, 2024Listed | Apr 17, 2025Listed | Sep 3, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.01 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | See provider quotes | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 0 endpoints → |
Specifications | |||
| Context window | 8.2K | 512 | 8.2K |
| Max output | 7.4K | — | — |
| Parameters | — | — | — |
| Open weights | Supported | Not reported | Not reported |