ModelWatch

Compare models

Up to 4 models side by side.

Provider
DeepSeek
Listed
Date added to OpenRouter
Oct 17, 2026
Input price
USD per 1M tokens
$0.04
Output price
USD per 1M tokens
$0.50
Workload cost
Chat reply (2K in, 500 out)
$0.0003
Context window
1.05M
Max output
944K
Output speed
tokens per second
164
Time to first token
seconds
1.43s
Intelligence Index
Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations.
32.6
Engineering Index
Artificial Analysis Engineering Index: engineering and technical problem solving.
37.6
Inputs
text, image
Open weights
Yes
Good at
visionlong-contextopen-weightslow-cost
Notes
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...

Best value in each row is highlighted. Share this page's URL to share the comparison.