Qwen3.5-35B-A3B with zero data retention.

• ZDR

  Claude, GPT, Gemini, and other models answer with zero data retention (ZDR). The provider reads the chat to answer it and promises by contract to keep nothing.

In ZDR and Open, Thinkr's proxy can read the chat in transit and writes none of it to disk.

• Qwen3.8 2.4TQwen's largest open-weight model, for hard reasoning and code.See the model
• Qwen3.8 27BQwen's open-weight 27B model with image input and thinking.See the model
• Qwen3.6 35B A3BQwen's open-weight model with 3B active parameters and image input.See the model