Juraj Bednar

I vibed a frontend for @AskVenice using OpenCode and GPT-5.4 — open source, purely static HTML. Supports chat, image generation and video. Nothing is sent to my server, it communicates directly with the Venice API. You can run it locally on localhost (needs to be served through

Mar 11

@ErikVoorhees Very cool. Another way to do it: https://t.co/ouVw3NUlAX

Jan 14

Is tool calling for e2ee- models coming to @AskVenice ? Would be cool if I could wire @opencode to Venice with end to end encrypted model with attestation. Already using e2ee models with https://t.co/lE1wXY56Yp It works and is very cool!

Mar 27

Using Claude Code through @AskVenice (and use it with different models, including Opus 4.5, Gemini 3 Pro, Grok 4.1 Fast and also more open models).

Jan 4

Has @AskVenice through API been super unreliable for you lately? Connections dropped, timeouts without next token, etc. Mainly for Sonnet 4.6 and gpt-5.4.

Apr 8

@sabrinaesaquino So how did you make lip sync work? Trying the same stack on @AskVenice, but it's not very good with wan2.7

May 1

Hey @AskVenice any plans of supporting E2EE with tool calling like the other providers, so we can use it with opencode for example? Other providers support it: https://t.co/Ok9lXaOe8w

Jul 10

Reformatter / Translator AI-powered tool for reformatting OCRed books and translating them using Venice AI API (you can alternatively use different API that is OpenAI compatible, even local models). This tool processes OCRed text to fix formatting issues and recognition

Jul 24, 2025

What's your best setup of @nanobrowser_ai with either @AskVenice or local ollama? Are you using vision or only tool calling model? Which give the best results? Do you use different for Planning and Navigation? So far I did not have very good results. Most models through

Jul 21, 2025

Well, I've got a good candidate for a new LLM model 👀 for @AskVenice https://t.co/xh2uWaHQjK Meanwhile pulling to my laptop :)

Aug 5, 2025