Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | perplexityPerplexity: Embed V1 4BRemove × | intfloatmultilingual-e5-large-instructRemove × |
|---|---|---|
| What’s different | pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter… | 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:”… |
| Date | Mar 16, 2026Listed | Apr 17, 2025Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.03 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → |
Specifications | ||
| Context window | 32K | 512 |
| Max output | 28.8K | — |
| Parameters | 4B | — |