Tencent: Hy Image 3.5 Preview
- by tencent
- tencent/hy-image-v3.5-preview
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...
What the numbers mean
- Context window100,000 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 75,000 words, or 150 pages.
- Max output90,000 tokens
- The longest single reply it can write: about 68,000 words.
- Input priceFree
- What you pay for everything the model reads. A 1,000-word prompt costs nothing.
- Output priceFree
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs nothing.
- Modalitiestext, image in, image out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.