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 × | tencentTencent: Hy Image 3.5 PreviewRemove × |
|---|---|---|
| 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:”… | Hy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing through one endpoint, taking up to 20 reference images... |
| Date | Apr 17, 2025Listed | Oct 5, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $1.60/ 1M output tokens Tencent Cloud · via OpenRouter · Conditional · Output only |
| Provider endpoints | 0 endpoints → | 1 endpoint → |
Specifications | ||
| Context window | 512 | 100K |
| Max output | — | 90K |
| Parameters | — | — |
| Image input | Not reported | Supported |