Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Details

FieldValue
idaccounts/fireworks/models/deepseek-v4-flash-vision-exp
familydeepseek-flash
modalitytext+image->text
context_length1000000
max_output_tokens384000
release_date2026-08-21
is_open_weightsyes
supports_tool_callyes
supports_reasoningyes
supports_structured_outputyes
supports_attachmentyes
input_modalitiestext, image
output_modalitiestext
DeepSeek V4 Flash Vision Exp