Qwen3.8-Max API pricing variable pricing

API model id

qwen3.8-max

Input / 1M

$2.00

Output / 1M

$6.00

Cached input / 1M

—

Context window

—

Notes

Alibaba Cloud Model Studio (Qwen first-party API), USD per 1M tokens, Singapore region (International deployment scope) list price, single tier 0<tokens<=1M. Cached-input prices are on the separate Context Cache page (not stored). 50% batch discount where supported.

Source

https://www.alibabacloud.com/help/en/model-studio/model-pricing

Provider type

First-party (HQ: China)

Regions

Singapore, US (Virginia), Germany (Frankfurt), Japan (Tokyo), China (Hong Kong), China (Beijing)

EU data residency

unknown — Model Studio regions decide the access point and data storage location; the service deployment scope decides where inference runs. Germany (Frankfurt) supports Global and EU scopes, but on the pricing page only some older models (e.g. qwen-plus, qwen3.5-flash, qwen3-vl-plus) have an EU-scope price; the Qwen3.8/3.7 models listed here are only offered with Global (or International) scope, so inference can run outside the EU. Prices differ by region (stored: Singapore/International list prices).

Last verified

2026-10-23

Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.