New Model: Mistral Small 3.1 24B

Venice launched Mistral Small 3.1 24B for Pro users. With 128k token context limit, this is one of the fastest and largest context models Venice offers. It is a web enabled and multi-modal model that supports vision and function calling and it is available in both the Venice app and the API.

This model was publicly released ~ 1 day ago and we’re thrilled to make it available to the Venice Community.

App

• Adjusted “Enhance Image” mode to return shorter prompt suggestions.

• Migrated Venice Voice to use HTML Audio Player — resolves issues with Audio not playing on iOS devices when the silence switch is enabled.

• Fixed an issue with the “custom settings” indicator perpetually showing on Image Settings

• Re-organized image settings to better group relevant settings together.

API

• Increased the Requests per Day (RPD) rate limits on Paid Tier image generation to 14,400 for Flux derivatives and 28,800 for all other models. API docs have been updated.

Characters

• Fixed a number of UI display issues on mobile for the character info and initial character display pages.

• Fixed issues with persistent filters on the Public Character page causing previous filters to remain active.