Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | tencentHy4-previewRemove × | moondreamMoondream: Moondream 3 PreviewRemove × |
|---|---|---|
| What’s different | Hy4 preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy Team, with 49B parameters activated per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention… | Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over… |
| Date | Aug 27, 2026Listed | Oct 15, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.834 in / $2.501 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ | $0.30 in / $2.50 out/ 1M tokensPrimeIntellect · via OpenRouter · all routes ↗primeintellect/fp8 · quantization=fp8 |
| Provider endpoints | 8 endpoints → | 2 endpoints → |
Specifications | ||
| Context window | 1M | 32K |
| Max output | 64K | 4.1K |
| Parameters | — | — |
| Tool calling | Supported | Not reported |
| Structured output | Supported | Not reported |
| Image input | Not reported | Supported |
| Reasoning | Supported | Supported |
| Prompt caching | Supported | Not reported |
| Open weights | Supported | Supported |