Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | tencentTencent: Hy-MT2-1.8BRemove × | moondreamMoondream: Moondream 3.1Remove × | nvidiaNVIDIA Nemotron 3.5 Super VisionRemove × |
|---|---|---|---|
| What’s different | Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based,… | Native object detection and pointing return structured coordinates; runs locally on Apple Silicon or NVIDIA GPUs. | Ask NVIDIA Nemotron 3.5 Super questions about an image: describe scenes, read text and charts, and reason over what it sees. |
| Date | Aug 20, 2026Listed | Oct 15, 2026Listed | Oct 15, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.044 in / $0.177 out/ 1M tokensTencent · via OpenRouter · all routes ↗tencent/fp8 · quantization=fp8 | $0.30 in / $2.50 out/ 1M tokensPrimeIntellect · via OpenRouter · all routes ↗primeintellect/fp8 · quantization=fp8 | See provider quotes |
| Provider endpoints | 2 endpoints → | 2 endpoints → | 0 endpoints → |
Specifications | |||
| Context window | 8.2K | 32K | — |
| Max output | 4.1K | 4.1K | — |
| Parameters | 1.8B | 9B | — |
| Image input | Not reported | Supported | Not reported |
| Reasoning | Not reported | Supported | Not reported |
| Open weights | Supported | Supported | Not reported |