modelstop.top

Compare Models

Run side-by-side checks for pricing, context window, and latency.

DeepSeek: DeepSeek V3

deepseek

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Context window
163,840 tokens
Input cost
$0.32 / 1M
Output cost
$0.89 / 1M
Latency (p50)