Qwen3.5-9B is a native multi-modal large language model launched by Tongyi Qianwen team, with 9B parameters. As a lightweight Dense model of the Qwen3.5 series, it uses an efficient hybrid architecture that combines gated delta network and gated attention. It natively supports 256K context length and can be expanded to approximately 1 million tokens. The model achieves unified basic visual language capabilities through early fusion training...
Provider: Qwen
Context window: 256K
Pricing: $0.03 input / $0.11 output per 1M tokens
Capabilities: serverless, json_mode, function_calling, structured_output
