Updated monthly
Changelog
New models, features, and API changes shipped to Venice each month.

Changelog
November 2025
Models
17 changesText models8
Anonymized Tags
Added anonymized tags to text models.
All usersDolphin Mistral 3.2
The new Dolphin Mistral 3.2 model is now available in beta.
BetaGemma Multimodal Flag
Added a multi-modal flag to the Gemma model.
All usersGLM 4.6, developed by Zhipu AI, is now available for Pro users. It excels in analysis and structured problem solving but is currently live without reasoning.
Pro usersPrivate Tags
Added private tags to LLM and image models for better filtering.
All usersGLM 4.6 was set as the default for all users, reverted due to high output token volume, and later reapplied.
All users
Image models4
Nano Banana
Nano Banana is now live as a pay-per-use image model with increased prompt and token limits.
All usersNano Banana Pro is now live as a pay-per-use image model, excelling at distilling complex prompts into clear imagery and infographics.
All usersSeedream v4
Seedream is now available as a pay-per-use image model.
All usersNanoBanana V1
Disabled the original NanoBanana (V1) model.
All users
Video models2
Veo 3
By popular demand, the Veo 3 video generation model has been brought back.
All usersWan 2.5 Default
Wan 2.5 is now the default video model.
All users
Deprecated3
- Qwen3-235b
- Wan 2.5 Safety Check
- Flux Models
Features
27 changesChat12
Action Menu
Released a new action menu to all users; fixed a bug with the Video button on img2video models.
Markdown Tables
Added support for GitHub-flavored markdown, including tables, for richer formatting in chat.
Memoria
Memoria is now in beta, providing advanced memory retention for longer conversations and more coherent character interactions.
BetaModel Switcher
Released a new, simple model switcher that rearranges user tags and triggers settings/actions on hover.
Progress Circle
Added a progress circle to display context usage and a circular progress indicator with a tooltip for character count.
Temporary Chats
Temporary chats are now live for all users, with selection persisting across sessions and state reflected in the chat input.
Image, video and audio9
Credit Confirmation Dialog
Added a dialog for credit confirmation before video regeneration.
DOCX Parsing
Added support for text parsing from native Word (DOCX) files.
HEIF Image Support
You can now upload and use HEIF images in the Image Editor and Upscaler.
Negative Prompt Support
Added negative prompt support to the video settings modal for models that support it.
Video Preview
Added support for video in the photo preview on the chat interface.
XLSX Parsing
Added support for XLSX document text parsing using markdown-tables.
Library and media1
New Library
The all-new Library is now available, offering a redesigned space to manage and view your generated content.
General3
Character Share Links
A share link has been added to the character menu, making it easy to share custom characters with others.
Mini App Auto-Connect
Implemented auto-connect functionality within the mini app on Base.
Web Scraping
You can now include a URL in your prompt and Venice will automatically scrape the page to use as context for your request.
Mobile app2
ASR on Mobile
Automatic Speech Recognition (ASR) is now available for mobile beta users.
BetaAndroid APK Update
Updated the Android APK download URL to point to version 1.3.0.
API
3 changesreasoning_content Support
Added support for reasoning_content instead of <thinking> tags for reasoning models.
Mini App Tags
Added mini app tags to the CMS at the request of Coinbase.
Search-Based Pricing
Enabled usage-based pricing for web search for all users.
Fixes
21 changesStop/Cancel Behavior
Improved stop/cancel behavior for multi-modal requests.
ChatBold Text Display
Tweaked character escaping to correctly display bold text in edited messages.
ChatCharacter Action Menu
Fixed the Character Action Menu button to only open on the intended hover event.
ChatCreate Account Link
Fixed an issue where the 'Create Account' link in the video notice was broken.
ChatHTML Rendering
Prevented HTML and meta tags from being rendered in chat messages; treats HTML as plain text in user message markdown.
ChatMessage Alignment
Fixed message/avatar alignment in multi-modal.
Chat
Have an idea for Venice?
Share feature requests and vote on ideas from the community on Learn Venice.