DeepSeek V4 Pro

DeepSeek · deepseek/deepseek-v4-pro

← Back to leaderboard

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

open weightstexttext->text

Context

Max context: 1048576
Max output: 384000

Pricing

Input / 1M: 0.43
Output / 1M: 0.87
Blend / 1M: 0.65

Quality

Quality index: 90.8

Provider

Provider: DeepSeek
Moderated: no