Compare DeepSeek V4 Flash 0731 and DeepSeek V4 Pro 0423 on key metrics including price, context length, throughput, and other model features.
DeepSeek V4 Flash 0731 is the official release of DeepSeek V4 Flash, superseding the preview version, with substantially enhanced agentic capabilities. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total, and this re-post-trained revision is suited for coding, reasoning, and agent workflows. The model natively supports a 1M-token context window and flexible reasoning effort: low for simple tasks, high for daily agent workflows, and max for complex ones.
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B active parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, delivering strong results across knowledge, mathematics, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it adds a hybrid attention system for efficient long-context processing and supports multiple reasoning modes to balance speed and depth based on the task. It is well suited for demanding workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both performance and efficiency are essential.