DeepSeek-V4-Pro-Max (Reasoning)

by DeepSeek

DeepSeek-V4-Pro-Max (Reasoning) is a reasoning model from DeepSeek, released on April 23, 2026. It has a 1M-token context window and can generate up to 1M output tokens. API pricing is $1.3 per 1M input tokens and $2.6 per 1M output tokens.

DeepSeek-V4-Pro-Max is the maximum reasoning effort mode of DeepSeek-V4-Pro, a 1.6T-parameter MoE model with 49B activated parameters and a 1M-token context window. It introduces a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) for dramatically improved long-context efficiency, requiring only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2 at 1M-token context. The model also incorporates Manifold-Constrained Hyper-Connections (mHC) for stable signal propagation and is trained with the Muon optimizer for faster convergence. Pre-trained on more than 32T tokens, V4-Pro-Max significantly advances open-source knowledge capabilities, achieves top-tier performance in coding benchmarks, and bridges the gap with leading closed-source models on reasoning and agentic tasks.

Key specs

Compare on the AI leaderboard · All AI models

More models from DeepSeek

• DeepSeek-V4.1-Flash (Reasoning) — DeepSeek
• DeepSeek-V4-Pro-0813 (Reasoning) — DeepSeek
• DeepSeek-V4-Flash-Vision-Exp (Reasoning) — DeepSeek
• DeepSeek-V4-Flash-0423 (Reasoning) — DeepSeek
• DeepSeek-V3.2 (Thinking) (Reasoning) — DeepSeek
• DeepSeek-R1-0528 — DeepSeek