ModelWatch
← Catalog

DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

visionlong-contextopen-weightslow-cost
Input price
$0.04 / 1M tokens
Output price
$0.50 / 1M tokens
Context window
1.05M tokens
Max output
944K tokens
Output speed
164 tokens/s
Time to first token
1.43s
Inputs
text, image
Open weights
Yes
OpenRouter id
deepseek/deepseek-v4.1-flash-1017
Listed
Oct 17, 2026

Benchmarks

Intelligence Index
32.6
Engineering Index
37.6

Speed and benchmarks for “DeepSeek V4.1 Flash 1017 (Max)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others