Skip to main content

OpenAI Text and Image Models

Similar to how Venice supports private video models from Google and OpenAi, it should also support private text and image models in both the UI and API and anonymize the call. Leave it to the user / developer to pick the model that makes the most sense for the use-case. To be honest, the private models are leaps and bounds ahead of Qwen3 and the other OSS models, making it hard to justify using Venice given the alternatives are so much better quality.

1 comment

Log in to comment and vote

Comments1

  • Copper Eraser

    •

    Nov 8

    “Private” for third-party hosted models is a bit of a misnomer. For Venice-hosted models, “private” means “we commit not to keeping your prompts”. For third-party it means “we have a ZDR agreement with them, and they commit not to keeping your prompts”. This is weaker (and probably deserves a “ZDR” pill rather than private.

    That said, whether Venice can provide a ZDR/private version of OpenAI models would be a question of whether OpenAI will grant ZDR status to Venice, not just whether Venice wants it.