← All models

DeepSeek V4 Flash Vision Exp

deepseek-flash

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

Family
deepseek-flash
Providers
16
Context
1,000,000
Output
384,000
Knowledge
-
Weights
Open
Input
textimage
Output
text
Release date
2026-08-21
Updated
2026-09-01

Providers

Source: models.dev