CHAT

DeepSeek-V4-Pro API

All You Need to Know About DeepSeek-V4-Pro API

Overview

Model Provider:DeepSeek

Model Type:LLM

State:Ready

Key Specs

Quantization:FP8

Parameters:1.6T

Context:1M

Pricing:$1.74 input / $3.48 output / $0.01 cache

Try Model API

Quick Start

Reserve Dedicated Endpoint

Introduction

DeepSeek-V4 including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.

DeepSeek-V4 series incorporate several key upgrades in architecture and optimization:

1. Hybrid Attention Architecture: We design a hybrid attention mechanism combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to dramatically improve long-context efficiency. In the 1M-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2.

2. Manifold-Constrained Hyper-Connections (mHC): We incorporate mHC to strengthen conventional residual connections, enhancing stability of signal propagation across layers while preserving model expressivity.

3. Muon Optimizer: We employ the Muon optimizer for faster convergence and greater training stability.