DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis
DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis
DeepSeek V4 Flash 0731 (Reasoning, Max Effort) Intelligence, Performance & Price Analysis DeepSeek V4 Flash 0731（推理版，最大努力模式）智能、性能与价格分析
Comparison Summary DeepSeek V4 Flash 0731 (Reasoning, Max Effort) is amongst the leading models in intelligence and well priced when comparing to other open weight models of similar size. The model supports text input, outputs text, and has a 1M tokens context window. DeepSeek V4 Flash 0731（推理版，最大努力模式）在智能方面处于领先地位，与同等规模的其他开源权重模型相比，价格极具竞争力。该模型支持文本输入和输出，并拥有 100 万 token 的上下文窗口。
DeepSeek V4 Flash 0731 (Reasoning, Max Effort) scores 50 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 25). When evaluating the Intelligence Index, it generated 210M tokens, which is very verbose in comparison to the median of 100M. DeepSeek V4 Flash 0731（推理版，最大努力模式）在 Artificial Analysis 智能指数中得分为 50 分，远高于同类模型的平均水平（中位数：25）。在智能指数评估过程中，它生成了 2.1 亿个 token，与 1 亿的中位数相比，表现得非常详尽。
Pricing for DeepSeek V4 Flash 0731 (Reasoning, Max Effort) is $0.14 per 1M input tokens (competitively priced, median: $0.43) and $0.28 per 1M output tokens (competitively priced, median: $1.20). In total, it cost $72.02 to evaluate DeepSeek V4 Flash 0731 (Reasoning, Max Effort) on the Intelligence Index. DeepSeek V4 Flash 0731（推理版，最大努力模式）的定价为每 100 万输入 token 0.14 美元（价格极具竞争力，中位数：0.43 美元），每 100 万输出 token 0.28 美元（价格极具竞争力，中位数：1.20 美元）。评估该模型在智能指数上的总成本为 72.02 美元。
Technical Specifications 技术规格
- Reasoning: Yes (This page shows the reasoning version of this model. A non-reasoning variant may also exist.) 推理能力： 是（本页面展示的是该模型的推理版本，可能还存在非推理版本。）
- Input/Output Modality: Supports text. 输入/输出模态： 支持文本。
- Context Window: 1M (~1500 A4 pages of size 12 Arial font). 上下文窗口： 100 万（约 1500 页 12 号 Arial 字体的 A4 纸）。
- Total Parameters: 284B. 总参数量： 2840 亿。
- Active Parameters: 13B (Number of parameters active per token during inference). 激活参数量： 130 亿（推理过程中每个 token 激活的参数数量）。
- License: MIT. 许可证： MIT。
Intelligence Evaluation Relevance 智能评估相关性
While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases. 虽然模型智能通常可以跨用例转化，但特定的评估指标可能对某些特定用例更为重要。
AA-Omniscience Index AA-Omniscience 指数
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. AA-Omniscience 指数（越高越好）用于衡量知识可靠性和幻觉水平。它奖励正确答案，惩罚幻觉，且对拒绝回答不予惩罚。得分范围为 -100 到 100，其中 0 表示正确与错误答案数量相等，负分表示错误多于正确。