DeepSeek V4 Flash Vision Exp

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

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

From the lab

Related articleDeepSeek-V4-Flash-Vision-Exp Release: Multimodal API Now Live
RELEASE DATEAug 21, 2026
WEIGHTSClosed weights
CONTEXT WINDOW1M
MAX OUTPUT384K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.