Qwen: Qwen3.6 27B

qwen/qwen3.6-27b

VisionTool useJSONReasoningStreaming

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

Pricing

Input

$0.29 / 1M

Output

$3.20 / 1M

Specs

Context

262,144 tokens

Input

text, image, video

Output

text

Released: 2026-04

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Open weights · HuggingFace

5,064,096 downloads/mo

1,552 likes

apache-2.0 image-text-to-text

View on HuggingFace →

Use this model →