{"slug": "v4-flash-vs-v4-pro-deepseek-promised-better-and-cheaper-its-true-but-not-how-i", "title": "V4-Flash vs. V4-Pro: DeepSeek promised better and cheaper. It’s true,  but not how I expected.", "summary": "DeepSeek, the Chinese AI lab, released an updated V4-Flash model that delivers better performance at a lower price than its V4-Pro, according to a The New Stack analysis. The V4-Flash costs $0.28 per million input tokens and $0.42 per million output tokens, compared to V4-Pro's $0.56 and $1.68, respectively, while achieving comparable or superior scores on benchmarks like MMLU-Pro and AIME 2025.", "body_md": "DeepSeek, the Chinese AI lab that’s been undercutting OpenAI and Anthropic on price since it arrived, recently refreshed V4-Flash, moving\n\nThe post [V4-Flash vs. V4-Pro: DeepSeek promised better and cheaper. It’s true, but not how I expected.](https://thenewstack.io/deepseek-flash-pro-benchmark/) appeared first on [The New Stack](https://thenewstack.io).", "url": "https://wpnews.pro/news/v4-flash-vs-v4-pro-deepseek-promised-better-and-cheaper-its-true-but-not-how-i", "canonical_source": "https://thenewstack.io/deepseek-flash-pro-benchmark/", "published_at": "2026-08-10 12:00:00+00:00", "updated_at": "2026-08-10 12:06:31.042294+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products"], "entities": ["DeepSeek", "OpenAI", "Anthropic", "The New Stack", "V4-Flash", "V4-Pro"], "alternates": {"html": "https://wpnews.pro/news/v4-flash-vs-v4-pro-deepseek-promised-better-and-cheaper-its-true-but-not-how-i", "markdown": "https://wpnews.pro/news/v4-flash-vs-v4-pro-deepseek-promised-better-and-cheaper-its-true-but-not-how-i.md", "text": "https://wpnews.pro/news/v4-flash-vs-v4-pro-deepseek-promised-better-and-cheaper-its-true-but-not-how-i.txt", "jsonld": "https://wpnews.pro/news/v4-flash-vs-v4-pro-deepseek-promised-better-and-cheaper-its-true-but-not-how-i.jsonld"}}