qwen3.8-max

Alibaba · Priced per token

A flagship MoE model with 2.4 trillion parameters, featuring a comprehensive leap in programming and office productivity, capable of autonomous programming to deliver a complete project in just over ten days. It is competent in hundreds of professional tasks such as law, finance, and design, and can deliver production-grade results end-to-end in a single conversation. Native visual understanding runs through the entire process of planning, execution and verification, supporting in-depth semantic analysis of ultra-long documents and long videos. It autonomously plans and iterates in a closed loop during long-horizon tasks, and evolves continuously.

Pricing

Base price

  • Input: $1.7891 per 1M tokens
  • Output: $5.3671 per 1M tokens
  • Cached input: $0.2237 per 1M tokens
  • Cache write: $2.2364 per 1M tokens

List rate at a 1x group multiplier, before any account-specific discount. The effective rate is this figure times the multiplier of the group the account is in.

Pricing by group

GroupMultiplierInputOutput
default1x$1.7891$5.3671

API access

  • openai — POST /v1/chat/completions

Available to groups: default

Other models from Alibaba

All models