Models

• Mistral 24B is now the default Venice model for all users, bringing multi-modal capabilities to every one. Llama 70B has been updated to a Pro model.

• Launched a preview of our new image inference infrastructure to our beta testers.

App

• Image styles within the image settings are now searchable.

• Added Conversation Forking to allow splitting conversations in new directions per this Featurebase request.

• Added a “Jump to Bottom” mechanism per the Featurebase request.

• Updated the app background to prevent a white flicker when loading the app.

• Support pressing Enter to save the name when re-naming a conversation.

• Update token dashboard to show 2 digits of prevision for staked VVV.

• Updated authentication logic to programmatically reload authentication tokens if they time out due to the window being backgrounded.

• Prevent the sidebar from automatically opening when the window is small.

• Fixed a bug with text settings not properly saving.

• Update image variant generation to more gracefully handle error cases.

• Launched a new backend service to support the growth of Venice — migrated authentication, image generation and upscale to that service. This new service should be more performant and provide Venice a better platform to scale our user continued user growth on.

API

• Added the nextEpochBegins key to the api_keys/rate_limits endpoint. Docs have been updated. Solves this Featurebase request.

• Added response_format support to Qwen VL in the API.

• Fixed a bug where messages to Mistral including a reasoning_content null parameter would throw an error.