Qwen3

Qwen: Qwen3.5 Plus 2026-04-20

qwen/qwen3.5-plus-20260420

Audio inside a video clip

Cannot hear clip audioprobed 2026-10-22

Probed: missed a spoken codeword inside the clip. Any comment it makes on sound is invented.

What it answered

SHAPE: Yellow square
AUDIO: NONE

Descriptionfrom OpenRouter

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

Context length

1,000,000 tok

Max completion

65,536 tok

Knowledge cutoff

—

Expires

—

Added to OpenRouter

4/27/2026

Cache last refreshed

11/12/2026

Primary modality

text+image+video->text

Source

OpenRouter

Input modalities

textimagevideo

Output modalities

text

Pricing

Field	Per token (USD)	Per million
prompt	0.0000003	$0.300
completion	0.0000018	$1.80
input_cache_write	0.000000375	$0.375
overrides	[object Object]	—

Supported parameters(16)

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

OpenRouter page