qwen4-max is live: provider pricing and near-1M recall verified
Alibaba’s Qwen4 flagship, released on 16 November, combines a 2.4T backbone, native vision and 1M context. APIYI connected on 17 November. A 951,498-token request recalled markers from both the middle and end, and all 15 Default-group release checks passed.
Pricing per 1M tokens: $1.50 input, $4.50 output including thinking, and $0.075 cached input, with eligible top-up bonuses.
Endpoints and groups:
/v1/chat/completions: available in Default and SVIP/v1/responses: available in CodexResponses/v1/messages: available in ClaudeCode
← Back to Live Updates · 📚 Monthly archive