Changes

Model Studio will lower the pricing for Qwen3-Max on the Mainland China Edition, starting from November 13, 2025.

• Half price for batch processing
• Implicit cache: Cached input tokens are billed at 20% of the standard price for input tokens.
• Explicit cache: Tokens that are used to create the cache are billed at 125% of the standard input token price. However, subsequent hits are billed at only 10% of the standard price.

Thank you for your support and trust in Model Studio.