DeepSeek V4 Flash Vision

language modelDeepSeek

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Key facts

Made byDeepSeek
Typelanguage model
ReleasedAugust 21, 2026
Reads at once1,048,576 tokens
Price (API, per million tokens)$0.22 in · $0.65 out
Input → outputtext, image → text

Questions about DeepSeek V4 Flash Vision

Who makes DeepSeek V4 Flash Vision?

DeepSeek V4 Flash Vision is made by DeepSeek.

When was DeepSeek V4 Flash Vision released?

We first saw DeepSeek V4 Flash Vision listed on August 21, 2026.

How much does DeepSeek V4 Flash Vision cost?

Through OpenRouter it costs $0.22 per million input tokens and $0.65 per million output tokens. Prices change, so check the provider before you build on it.

How much text can DeepSeek V4 Flash Vision read at once?

Up to 1,048,576 tokens, roughly 786.4K words.

More from DeepSeek

Other language models

Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with DeepSeek.