Changelog

Share your feature requests here.

This is where you can share feature requests and suggest improvements for Venice.ai. Whether it’s a small enhancement or a major new capability, we’re interested in hearing what matters most to you.

Join the conversation on our discord.

ad intellectum infinitum

Deep Research Assistant

A rival to OpenAI’s Deep Research Assistant Provide a built in AI agent that acts like a dedicated research assistant. You give it a prompt (a question or topic), and it: Searches the Web: It intelligently browses the internet, finding relevant information. Iterates: It doesn't just stop at the first search. It analyzes the results and asks itself, "Do I need more information?" This creates a loop of searching and refining. Generates a Report: Once it has gathered enough information, it compiles a complete report for you.

An Anonymous User 3 months ago

13
💡

Feature Requests

In Progress

Temporary chats

A temporary chat option would be very useful for chat organization. For instance, if I have a dumb question like “how to pronounce gnu”, I don’t need that saved in my chat history. Yes, I can delete the chat myself, but a temporary chat option would save time/clicks in the UI. Additionally, in my opinion, the best way to go about this would be to have the option to make chats temporary by default. Similarly to how Kagi’s Assitant chats expire after 24 hours, along with the ability to set the default behaviour to permanent if needed (permanent being how Venice works currently). So how I envision this working in an ideal world, is that there is some global app setting that sets the default behaviour of chats, with the three options being: permanent, expire after 24 hours, expire after app close. Then, there would be an option to save specific chats to my chat history (probably through the ellipsis menu). Thank you for considering this.

An Anonymous User 3 months ago

12
💡

Feature Requests

In Progress

VCU Consumption Limits for API Keys

Introduce configurable limits on VCU consumption per API key to enable controlled usage. This is essential for VCU rentals, resale, subscription models, and quota management while preventing overuse and abuse. Proposed Features: Users should be able to set custom VCU limits per API key, with the following options: Total Limit (Refillable/Renewable) A fixed maximum VCU allocation per key, manually or automatically refillable. Use Case: Renting out VCU with refill options. Daily Limit A hard cap on VCU usage per day to prevent overconsumption. Use Case: Subscription plans where users get X VCU per day. Time-Based Allocation (Rolling or Fixed Window) A set VCU limit over a defined period (weekly, monthly, etc.). Fixed Window: Resets at the start of each cycle (e.g., “10,000 VCU/month”). Rolling Window: Applies a limit over any continuous period (e.g., “10,000 VCU over 30 days”). Use Case: Monthly subscription tiers with more flexible usage patterns. One-Time Use & Expiration A single-use VCU allocation that expires when depleted. Use Case: Selling one-time VCU packages. Per-Request Limit A cap on the VCU usage per individual API call to prevent single-call overuse. Use Case: Protects against excessive batch-processing requests. Rate Limiting (VCU per Time Interval) Restrict usage to a maximum VCU per minute/hour to prevent sudden spikes. Use Case: Prevents a user from burning an entire daily quota in minutes. Grace Period / Temporary Overages An optional soft limit where users can slightly exceed their quota before getting fully blocked. Use Case: Prevents disruptions for legit users who slightly overconsume. Why This Matters: Enables VCU rentals and resale with precise quota control. Prevents accidental or malicious overuse. Supports subscription-style access models. Provides budget control and cost predictability. Ensures a clean and scalable way to manage VCU distribution. Implementation Considerations: Limits should be configurable via the dashboard and API. Admins should have usage tracking & alerts when quotas are close to being hit. This feature would enhance VCU-based services and expand monetization options, benefiting both Venice and its users.

An Anonymous User 3 months ago

9

API

Enable Direct PDF and Text File Uploads via Venice API

Currently, users must convert PDF files to text or read text files and manually include the content in the prompt when using the Venice API. This process is time-consuming, prone to errors, and inefficient, especially with large files. Proposed Solution: Introduce a feature allowing users to upload PDF or text files directly through the Venice API, similar to the functionality available in Venice Chat. This would eliminate the need for manual conversion or extraction, streamlining the workflow.

DMR 3 months ago

API

Multi-character Chat

The ability to create, effectively, a chat room with a human, and 2 custom characters where the AI’s will read and respond to all messages in turn. An important feature in such a mode would have to be a post order (or batting order for the Americans out there) so that the AI’s don’t end up bouncing off one another endlessly before the human can post. For example: Human posts Character 1 posts Character 2 posts -repeat- in this example, character 1 would not be able to post again until after the human as posted.

An Anonymous User 3 months ago

5
💡

Feature Requests

VCU market

Integrate VCU market functionality into the API dashboard stakers can reserve a certain amount of their VCU capacity for resale if a buyer needs more VCU than any one staker has available, the system generates a virtual key that represents aggregate capacity from multiple stakers etc xref: https://veniceai.featurebase.app/p/vcu-consumption-limits-for-api-keys

An Anonymous User 3 months ago

4
💡

Feature Requests

Add a search provider for browsers

All browsers implement a standard called “OpenSearch”, which lets websites advertise that they support a search provider. Each browser implements the UX for this slightly differently, but all support it in some way or another. By adding a file to venice.ai, and adding a tag to the site, it’s possible for users to add Venice as a search provider to their browser. You can advertise multiple search options, such as “Venice: Llama 3.1 405B”, “Venice: Deepseek R1 671B”, “Venice: Default Web Model”. The UX from thereon out would be that you can set Venice as your default search provider, and searches would be sent to Venice instead of, say, Google or DDG. Here’s MDN’s reference material: https://developer.mozilla.org/en-US/docs/Web/XML/Guides/OpenSearch#reference_material Here’s what it looks like on IMDb when you right-click the search bar on Firefox, if you don’t already have IMDb as a search provider. Here’s what a search looks like.

Justin Martin 3 months ago

💡

Feature Requests

FLUX Uncensored

Please bring back the older FLUX uncensored image generator, alongside the custom one. It is great for generating NSFW images, but when it comes to males, it falls short massively compared to the previous one. Pony realism isn't great, either. It's very clear you're just generating from a small set of training data, so anything custom is almost impossible. The older FLUX was one of the best things you introduced, and now it's gone. I've been paying for Venice for a while, I'd love to see it reintroduced.

An Anonymous User 3 months ago

7
💡

Feature Requests