Tencent Hy Image3.5 Preview Ships With $0.024 Per-Image API
- Source
- x.com
- Date
Hy Image3.5 preview is live. 🚀 Professional-grade image generation, +30% win rate in human eval vs Hy Image3.0 Both Text to image & Image to image available. Up to 2K. Better Consistency. API: https://t.co/5BvR2SdI6Q Priced for everyone. $0.024 per image on Tencent Cloud API. We only charge for what we generate — your reference images are free. Two weeks free (Only in OnSolo and Miora): Miora https://t.co/UxwBScI64O OnSolo https://t.co/iXnNNg6U9k Try it and tell us where it breaks.
Context
Tencent's Hy team has released a preview of Hy Image3.5, an image model that both generates images from text and edits or transforms input images, at up to 2K resolution. In the launch post, Tencent describes it as professional-grade, with better consistency, and claims a "+30% win rate" against Hy Image3.0 in human . Tencent ran that comparison itself and does not say whether the figure means 30 percentage points or a 30% relative gain, how many judges took part or what prompts were used.
Tencent's pricing is the most concrete part of the launch. The model costs $0.024 per image on the Tencent Cloud API, and Tencent says it charges only for generated output, not for reference images supplied for image-to-image work. That matters for editing, where users upload source images. The post also offers two weeks of free use, but only through the Miora and OnSolo apps. The linked Tencent Cloud console, the two app sites and the demo video could not be read, so the API's terms and the free trial's conditions are not checked beyond the post.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Checking sign-in…
Loading comments…





