Last week, we complete the migration of our backend infrastructure to our next generation platform. This transition reduces latency and cost and enables support for new types of inference (including video). We look forward to the next round of feature work this new infrastructure will support.

App

• Added support for bulk chat deletion. Select the three dots to the right of the chats header to find the option.

  

• Swapped out browser confirmation windows with native confirmation windows to allow them to be displayed on mobile crypto wallet browsers (like Coinbase Wallet).

• Updated our Wallet Connect packages to fix a bug that was causing a notice to pop up prompting to change wallet networks.

• Added additional delay to the character search to avoid re-rendering while search results are in flight.

• Updated navigation on character pages making them easier to navigate on mobile.

• Added support to allow for the “None” image style to be added to favorites.

• Fixed a bug that was causing scroll issues in the left nav bar.

API

• Venice's new upscale enhance mode is now available through the existing upscale API.

  • API docs are available here.

  • Postman example cane be found here.

  • API pricing for upscale has been updated here.

• Added an OpenAI compatible image generation endpoint. This endpoint supports fewer configuration parameters than our full image endpoint but will work with OpenAI compatible image generation libraries without modification. Docs are updated.

• Added support for json_object type under response_format for LLM API requests. Docs are updated.

• Changed default image model to venice-sd35 to match app default.

• Return more helpful errors when LLM API requests fail to execute on the runners. This should make debugging complex json_schemas easier to understand.