qwen3.8-max-preview

by Qwen

Launch offer: Credits are consumed at just 10% of the standard rate, effectively 10× your usage. Limited time only. Qwen3.8-Max-Preview is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen3.7-Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows.

API Pricing

Input	$0.17 / 1M tokens
Output	$0.51 / 1M tokens
Cache read	$0.02 / 1M tokens

Specifications

Context window	991,000 tokens
Modalities	text
Features	tools, function_calling, structured_outputs, web, long_context, thinking

More from Qwen

• happyhorse-1.1-i2v
• happyhorse-1.1-r2v
• happyhorse-1.1-t2v
• qwen3.7-plus
• qwen3.7-max
• happyhorse-1.0-i2v
• happyhorse-1.0-r2v
• happyhorse-1.0-t2v

Use qwen3.8-max-preview via the AIHubMix unified API — one interface for every major LLM.