DeepSeek V4 Pro (Reasoning)

FrontierOpen weightsTextReasoning

DeepSeek V4 family model by DeepSeek.

About the DeepSeek V4 family

DeepSeek's 2026 generation in Flash (fast/cheap) and Pro tiers with reasoning-effort control — continuing its playbook of frontier performance at disruptive prices with open technical detail.

All DeepSeek V4 models

How this one is configured

This configuration runs in reasoning mode (thinks step-by-step before answering).

Also runs at: high · max effort

Effort controls how long the model thinks before answering — higher effort usually means better answers on hard problems, at the cost of speed and money. Same model underneath, so they share this page.

Who makes it

DeepSeekChinaHangzhou lab famous for frontier-level open models at rock-bottom cost.