V4-Flash vs. V4-Pro: DeepSeek promised better and cheaper. It’s true,  but not how I expected.

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.

DeepSeek, the Chinese AI lab that’s been undercutting OpenAI and Anthropic on price since it arrived, recently refreshed V4-Flash, moving The 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 .