Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

Details

FieldValue
idqwen3-7-flash
familyqwen
modalitytext+image+video->text
context_length1000000
max_input_tokens991000
max_output_tokens65536
release_date2026-07-15
is_open_weightsno
supports_tool_callyes
supports_reasoningyes
supports_structured_outputyes
supports_attachmentyes
input_modalitiestext, image, video
output_modalitiestext

Providers

Qwen3.7 Flash