← All models View on HuggingFace →
Qwen: Qwen3.5-9B
qwen/qwen3.5-9b
VisionTool useJSONReasoningStreaming
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
Pricing
Input
$0.04 / 1M
Output
$0.15 / 1M
Specs
Context
262,144 tokens
Input
text, image, video
Output
text
Released: 2026-03
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Open weights · HuggingFace
8,817,892 downloads/mo
1,500 likes
apache-2.0 image-text-to-text