Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | intfloatmultilingual-e5-large-instructRemove × | thenlpergte-baseRemove × | QwenQwen3-Embedding-8BRemove × |
|---|---|---|---|
| What’s different | 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:”… | The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE… | 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… |
| Date | Apr 17, 2025Listed | Nov 22, 2023Listed | Jun 10, 2025Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | See provider quotes | $0.005 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.01 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 0 endpoints → | 1 endpoint → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | |||
| FreshStack · MTEB 1.38.43 ↗MTEB 1.38.43; test/default; dataset 7a20df1a | Not reported | Not reported | 0.43017 ↗Revision 4e423935; test/defaultContributor reported |
Specifications | |||
| Context window | 512 | 512 | 41K |
| Max output | — | 460 | 32K |
| Parameters | — | — | 8B |
| Open weights | Not reported | Supported | Supported |