Venice.ai Change Log - March 25-30th, 2025

March 28th, 2025

Launched Multiple Document Support for File Upload - 162 votes on Featurebase.
Launched Jump to Latest Message - 52 votes on Featurebase.
Released an overhauled chat interface that improved performance and made the UI more responsive.
Added image carousel view for multi-image generation.
Made Image Styles searchable.
Resolved an issue with the API settings page and the API keys endpoint in the API timing out for users with large inference logs.
Fixed a bug where Pro users could see errors about inference request requiring Pro status under certain situations.
Updated In-Painting to use Mistral as the vision model for the mask generation pipeline. This should improve performance of in-painting requests.
Added a “Vision” tag to the model selector list.
Adjusted the VCU chart to default to 90 days.
Fixed bug preventing Markdown files from being uploaded to the Text inference endpoint.
Fixed Venice Voice pronunciation of content with slashes between characters (IE HTTP/2 and HTTP/3).
Adjusted user rate limits to use a Fixed Window vs. a Sliding Window. This will ensure that limits in the app fully reset at midnight UTC.

Added support for custom rate limit tiering. Please contact [email protected] if you’re looking for higher limits.
Fixed a bug that was preventing include_venice_system_prompt in the Model Feature Suffix from properly being recognized.
Included include_venice_system_prompt in the venice_paramters in LLM response.
Removed authentication from the /models endpoint to make it simpler to get model IDs.

Updated Venice’s system prompts to attempt to address issues with Chinese characters appearing in responses from Deepseek, Qwen and Mistral responses.