Model

DeepSeek V4.1 Flash 1017

DeepSeek · cn · Artificial Analysis 45.1

October 2026 refresh of DeepSeek V4.1 Flash with the same multimodal, tool-oriented design and stronger benchmark results.

Input imagetext Output text

Provider listings

Text

Language and vision-language generation.

In €Out €
image text text
0.30/M cached 0.03/M
1.20/M
image text text
0.44/M cached 0.110/M
1.31/M
image text text
0.60/M cached 0.12/M
1.80/M