Qwen3.5-Plus

Released

Qwen3.5-Plus is an AI model released by Qwen on Monday, Feb 16 2026, the same day as Qwen3.5. It is a 397B parameterThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. model with a 1M token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider..

API pricing

International (Singapore)
Up to 256K input tokens
InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$0.40
OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$2.40
Over 256K and up to 1M
InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$0.50
OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$3.00
  • Output prices include reasoning tokens.
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Verified October 19, 2026Read from alibabacloud.com. Click the check to open the source.

Available from

Alibaba02-15$0.26$1.561M
Alibaba20260420$0.30$1.801M
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Checked November 6, 2026Third-party rates from openrouter.ai, not the lab’s own list price.

Compare Qwen3.5-Plus with

Qwen3.5-Plus

About

Qwen3.5-Plus was the hosted counterpart of Qwen3.5-397B-A17B, providing the vision-language model through Alibaba Cloud's managed API. The underlying model had 397 billion total parameters with about 17 billion active per token.

Alibaba documented a one-million-token context by default, built-in tools and adaptive tool use for the service. Those hosted features and service terms were separate from the settings and license for running the downloadable checkpoint.

Frequently asked questions

Qwen3.5-Plus was released by Qwen on Monday, Feb 16 2026.

All Qwen releases

24 tracked