🔶 DeepSeek V4 Pro 0813:智能、性能与价格分析
英文标题:🔶 DeepSeek V4 Pro 0813: Intelligence, Performance and Price Analysis
DeepSeek V4 Pro 0813(Reasoning,Max Effort)在同等规模的开放权重模型中表现出领先的智能水平,且价格具备一定竞争力。该模型在 Artificial Analysis Intelligence Index 中得分 53,显著高于可比模型 27 分的中位数,但生成 1.3 亿 token,输出相对偏冗长。其输入价格为每百万 token 0.43 美元、输出价格为每百万 token 0.87 美元,评测总成本为 135.03 美元;生成速度为每秒 78 token,高于每秒 65 token 的平均水平。对开发者而言,该模型提供 100 万 token 上下文窗口,适合需要长上下文、较强推理能力及较高吞吐量的文本任务。
52.4 KB
中文
DeepSeek V4 Pro 0813(Reasoning,Max Effort)在智能水平方面位居领先模型之列;与其他同等规模的开放权重模型相比,其价格也较为合理。它的速度同样高于平均水平,但输出略显冗长。该模型支持文本输入与文本输出,并提供 100 万 token 的上下文窗口。
DeepSeek V4 Pro 0813(Reasoning,Max Effort)在 Artificial Analysis Intelligence Index 中获得 53 分,在可比模型中明显高于平均水平(中位数:27 分)。在评估 Intelligence Index 时,该模型生成了 1.3 亿 token;相较于 1 亿 token 的中位数,其输出量略显冗长。
DeepSeek V4 Pro 0813(Reasoning,Max Effort)的定价为:每百万输入 token 0.43 美元(略贵,中位数:0.33 美元),每百万输出 token 0.87 美元(价格适中,中位数:1.20 美元)。总体而言,在 Intelligence Index 上评估 DeepSeek V4 Pro 0813(Reasoning,Max Effort)的成本为 135.03 美元。
DeepSeek V4 Pro 0813(Reasoning,Max Effort)的生成速度为每秒 78 token,高于每秒 65 token 的平均水平。
English / 原文
DeepSeek V4 Pro 0813 (Reasoning, Max Effort) is amongst the leading models in intelligence and reasonably priced when comparing to other open weight models of similar size. It's also faster than average, however somewhat verbose. The model supports text input, outputs text, and has a 1M tokens context window.
DeepSeek V4 Pro 0813 (Reasoning, Max Effort) scores 53 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 27). When evaluating the Intelligence Index, it generated 130M tokens, which is somewhat verbose in comparison to the median of 100M.
Pricing for DeepSeek V4 Pro 0813 (Reasoning, Max Effort) is $0.43 per 1M input tokens (somewhat expensive, median: $0.33) and $0.87 per 1M output tokens (moderately priced, median: $1.20). In total, it cost $135.03 to evaluate DeepSeek V4 Pro 0813 (Reasoning, Max Effort) on the Intelligence Index.
At 78 tokens per second, DeepSeek V4 Pro 0813 (Reasoning, Max Effort) is faster than average (65).