Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | intfloatmultilingual-e5-large-instructRemove × | moondreamMoondream: Moondream 3.1Remove × |
|---|---|---|
| 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:”… | Native object detection and pointing return structured coordinates; runs locally on Apple Silicon or NVIDIA GPUs. |
| Date | Apr 17, 2025Listed | Oct 15, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $0.30 in / $2.50 out/ 1M tokensPrimeIntellect · via OpenRouter · all routes ↗primeintellect/fp8 · quantization=fp8 |
| Provider endpoints | 0 endpoints → | 2 endpoints → |
Specifications | ||
| Context window | 512 | 32K |
| Max output | — | 4.1K |
| Parameters | — | 9B |
| Image input | Not reported | Supported |
| Reasoning | Not reported | Supported |
| Open weights | Not reported | Supported |