Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | thenlpergte-baseRemove × | intfloatmultilingual-e5-large-instructRemove × | nvidiaNemotron-3-DiarizationRemove × |
|---|---|---|---|
| What’s different | 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 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:”… | Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call… |
| Date | Nov 22, 2023Listed | Apr 17, 2025Listed | Sep 25, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.005 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | See provider quotes | $0.00001/ secondDeepInfra · all routes ↗Input audio second |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 1 endpoint → |
Specifications | |||
| Context window | 512 | 512 | — |
| Max output | 460 | — | — |
| Parameters | — | — | — |
| Open weights | Supported | Not reported | Not reported |