Qwen vision-language model for visual reasoning, documents, and agent tasks

Details

FieldValue
idqwen3-6-flash
familyqwen3.6
modalitytext+image+video->text
context_length1000000
max_output_tokens65536
release_date2026-04-27
is_open_weightsno
supports_tool_callyes
supports_reasoningyes
supports_structured_outputyes
supports_attachmentyes
input_modalitiestext, image, video
output_modalitiestext

Providers