February 5th, 2025
API
App
Token

We've released an API Dashboard accessible at https://venice.ai/settings/api. This includes historical usage information and your current VCU balances.
API Keys now are typed: ADMIN and INFERENCE. You can configure this when creating new API keys. All existing API keys are by default ADMIN keys. ADMIN keys will have access to all API endpoints while INFERENCE keys will be limited solely to inference endpoints.
Updated the VCU section of the token dashboard to clean up the layout and add some clarity on titles. We've also added a link to the API dashboard.
Implement Disable Telemetry Collection setting in the App Settings (Top Right Settings > App Settings). Enabling this mode will disable all browser based product usage telemetry Venice collects.
Improve LaTeX rendering support. Example chat here. Fixes this Feature Base request.
Settings drawer on the right now is able to be used while executing inference (vs. the previous overlay). The UI will remember our drawer state when you return to the app. Fixes this Feature Base request. Additionally, advanced settings will remember the state you toggled.
Document uploads to the Chat window will be retried if they experience network issues while processing.
Add an option in the User Settings menu (accessible from the left nav bar) to request the browser make storage persistent. This will requset that browsers do not clear out old history to free up space.
Beta - Published the /api/v1/api_keys/rate_limits endpoint that returns which API tier you're on (explorer, or paid), your balances, and the rate limits currently in effect for each model for your user. Note - this API format is subject to change. View it on Postman.
Beta - Published GET / POST / DELETE endpoints on /api/v1/api_keys for managing API keys. View it on Postman.
Published $VVV circulating supply endpoint and documented it on Postman.
Added an integrations page on the docs to compile third party and community supported tools that connect to Venice.ai