Updated monthly

Changelog

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

Venice

Changelog

September 2025

Models

4 changes

Text models3

  • Venice Large Pricing

    Venice Large (qwen3-235b 2507 thinking and instruct) input/output pricing dropped to $0.90 / $4.50 from $1.50 / $6.00.

    All users
  • Venice Small Pricing

    Venice Small (qwen3-4b) input/output pricing dropped to $0.05 / $0.15 from $0.15 / $0.60.

    All users
  • Venice Uncensored Pricing

    Venice Uncensored (venice-uncensored) input/output pricing dropped to $0.20 / $0.90 from $0.50 / $2.00.

    All users

Image models1

  • Qwen Image Performance

    Qwen Image now runs in about half the time with a Lightning LoRA applied. CFG and Steps are pinned to 1 and 8 respectively per LoRA authors' recommendations.

    All users

Features

10 changes

Chat3

  • Auto Model Routing

    Improved auto model routing to direct anime-related prompts to anime-optimized models.

  • LaTeX Rendering

    Made additional improvements to LaTeX rendering for mathematical equations.

  • Print Chat Rendering

    Improved rendering when printing text chats.

Image, video and audio2

  • Execution Timer

    Updated execution timer to reflect all images when generating multiple variants.

  • Default Image Editing Model

    Migrated to Qwen Edit as the default model for image editing and in-painting.

Wallet and payments1

  • Wallet Connect Update

    Updated to the latest version of Wallet Connect to improve the wallet linking user experience.

General4

  • Download Post Images

    Added a Download option to post share menus so users can save post images.

  • My Posts Tab

    Added a 'My Posts' tab to the social feed navigation.

  • Social Feed Photo Rendering

    Updated social feed rendering to better support non-square aspect ratio photos.

  • Default API Key Permissions

    Changed default for new API keys to 'inference only' instead of 'admin' keys.

API

5 changes
  • Multiple Image Variants

    Added support for multiple image generations in a single API request via the variants parameter.

  • Get Character Details

    Added an API route to get details on a specific character. API docs have been updated.

  • Model Deprecation Headers

    Added model deprecation headers (x-venice-model-deprecation-warning and x-venice-model-deprecation-date) to API endpoints.

  • Photo URL in Character Data

    Added photoUrl parameter to character data returned from the API.

  • Strict Tool Parameter Validation

    Added an optional strict boolean on tool parameters to enable stricter parameter validation for tool calls.

Fixes

2 changes
  • Pinch to Zoom

    Fixed pinch to zoom functionality when the photo viewer is open.

    Chat
  • Copy Edited Images

    Fixed issue where copy action did not properly include in-painted or edited images.

    Studio

Have an idea for Venice?

Share feature requests and vote on ideas from the community on Learn Venice.

Submit an idea
Building on Venice?Read the API docsBrowse FAQs