Changelog

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.

App

• 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.

API

• Added support for custom rate limit tiering. Please contact support@venice.ai 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.

Models

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

Website

• Launched a Venice Brand page: https://venice.ai/brand

Venice Voice Text to Speech TTS API Generally Available

• Add support for Venice Voice Text to Speech (TTS) for all users in the API. Docs are updated and Postman example can be found here.

• Added voices for TTS models to the models endpoint. Docs are updated.

Models

• Updated Venice system prompts to address censorship issues that were exhibiting themselves in Qwen and Mistral models.

• Updated Qwen VL 72B to the latest version announced today.

• Released DeepSeek Coder V2 Lite as a Code model for all users.

App

• Add a notice when temperature is greater than 1 that high temperature may create gibberish responses.

• Upgraded the app to Next.js version 15 which improves performance and reliability of the app platform.

• Reverted the changes to Enhance Prompt that resulted in prompts that were far too short.

Models

• Re-activated the Deepseek Coder V2 Lite beta.

API

• Overhauled the API pricing page design.

• Increase length of supported prompts on flux-uncensored models via the API.

• Launch API marketing page.

• Add support for Venice Voice for beta users in the API. Docs are updated. Postman example can be found here.

Bug Fixes

• Fixed issues in Venice Voice that could lead to sentences being read out of order.

• Fixed a bug where copying a WebP image and pasting it for in-painting would not paste the image.

• Fix issues with certain states showing Safe Venice overlays on image prompts.

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.

Securely Backup Chat History

Pro users can how securely backup chat history and migrate to other devices, or recover from a loss of data in their local browser. Here's how they work:

1. On your local device, when you create a new backup, Venice encrypts your data with a password that only you control.

2. That backup is then broken into chunks and uploaded to Venice's infrastructure.

3. You can then download and restore that backup, either overwriting your existing history, or merging it, on any logged in device.

A few important notes:

• Venice does not have any record of the password you create, so if you loose it, your backup is unrecoverable. We suggest you use a password manager to store them.

• You are limited to a max of 5 concurrent backups.

• Backups expire after 90 days.

Backups can be accessed via the menu in the left hand side menu:

From there, you can create a new backup, or restore an existing one:

App

• Maintain EXIF data on upscaled images.

• EXIF data on image generation now includes the model name.

• Updated default values for Dolphin 72B and adjusted additional inference settings based on recommendations from Cognitive Computations.

• Changing the conversation type selector will now change the image settings, but changing the image settings won’t automatically change the conversation type selector.

Mobile Wallets

• Mobile wallets (Coinbase Wallet, Metamask, etc...) will be redirected to the sign-in when visiting the Venice home page. This should reduce friction of logging in from those devices.

API

• Added model specific defaults for temperature and top_p - Updated the /models endpoint to list those defaults in the constraints field.

• Add support for the following parameters in the chat/completions endpoint:

  • repetition_penalty

  • max_temp

  • min_temp

  • top_k

  • min_p

  • stop_token_ids

Bug Fixes

• Fixed a bug where you could not click the scroll bar next to the chat input.

Venice is Burning

Venice is burning. 1/3 of our VVV token supply was burned, and we’ve rebranded.

Characters

• Fix an issue where character images crated with the character generator that were blurred were not showing the Safe Venice description on top.

• When editing a character, if you change the model and the context exceeds the model's new context, you'll now see an error presented on the context screen. Additionally, if you send a message that exceeds the context of the model server side, you'll get a character specific error directing you to change the character context.

• Improved context processing when conversations are nearing the maximum context of the mode.

API

• Support null value in Chat Completions stop parameter. Docs are updated.

• Overhauled significant portion of swagger documentation for Chat Completions API to make parameters and responses more clear in the docs.

App

• Updated the Image Settings “steps” tooltip to be more clear.

• Updated the UI so Reasoning models that never close the </thinking> tag will open the thinking content when the rendering is complete.

• Adjusted rate limits for users to debit only for successful requests.

• Venice Sticker factory prices have been reduced to $9.99.

• Implemented streaming of Venice Voice responses from our Venice Voice servers back to the client to reduce time to first speech.

• Add “Reasoning” feature to model dropdown for Reasoning models.

• Rewrote the app loading screen to remove flashes and other glitches during initial load. Introduce a smooth fade during this transition.

• Update the context length descriptions on our models to be more clear on available context within app.

• Added a warning when clicking links generated from LLMs.Added a warning when clicking links generated from LLMs.

Bug Fixes

• Fixed an issue with the sign out function occasionally requiring multiple calls.

• Fixed a bug where copying a WebP image using the contextual menu wouldn’t put the image on the clipboard.

• Fixed a bug with Safe Venice overlays appearing on non-adult images in some circumstances.

• Fixed a bug where under certain circumstances the user session token would not be refreshed before it expired. This would result in a screen suggesting the user’s clock was out of date.

• Fixed a UI quirk with API Key expiration dates where Safari would show a default date on the expiration selector despite the field being empty.

Characters with Pro Models accessible to all users

Characters that use Venice Pro models are now accessible for non-pro members to interact with. Anonymous and Free users will get a limited number of chats with these characters before being prompted to upgrade to Venice Pro. We look forward to your feedback on Venice Characters.

Venice Voice Downloads

Venice users can now download audio generate from Venice Voice. Once the audio has completely generated, a download icon will appear to the right of the speaker. Clicking this will allow you to save the audio recording as a .wav file.

App

• Refactored the Venice Voice UI so that the button in the message rows only controls reading for that particular message. For users who wish to have the whole conversation read, that can one enabled in the Text settings.

• Venice Voice pronunciation and processing was improved to provide better pronunciation and to strip out characters that are not processable.

• Fixed a bug where a user who was speaking to a character, then went to an image conversation and returned to the character would get an image generation in the first message with that character.

API

• Vision models will now support the submission of multiple image_url parts. For compatibility purposes, the schema supports submitting multiple image_url messages, however, only the last image_url message will be passed to and processed by the model. Docs have been updated.

• The model list endpoint now exposes an optimizedForCode capability on text models. Docs have been updated.

• The model list endpoint now exposes a supportsVision capability on text models. Docs have been updated.

• API Key expiration dates are now returned on the Rate Limit endpoint. Docs have been updated.

• The model list endpoint now exposes all image constraints that are part of the schema validation for image generation. Docs have been updated.

• Postman Authorization helpers have been configured for Venice’s collections. This should help provide instructions for new users on how to generate their API Keys.

• Fixed a bug in the image generation API that was causing content types of binary images to be returned as image/undefined. Added a test case to avoid regression.

• Fixed a bug that was preventing models that had the supportsResponseSchema capability, but not supportsToolCalling from properly processing response_format schema inputs.

• Fixed a bug where Brotli compression was not successfully being passed back to the API caller. The postman example has been updated and a test case has been added.

• The Postman test suite has been completely overhauled and optimized and integrated as part of Venice’s broader CI pipeline.