{
    "author": null,
    "date_published": null,
    "dek": null,
    "direction": "ltr",
    "domain": "www.seangoedecke.com",
    "excerpt": "Why is DeepSeek-V3 supposedly fast and cheap to serve at scale, but too slow and expensive to run locally? Why are some AI models slow to respond but fast once\u2026",
    "lead_image_url": null,
    "next_page_url": null,
    "rendered_pages": 1,
    "title": "Why DeepSeek is cheap at scale but expensive to run locally",
    "total_pages": 1,
    "url": "https://www.seangoedecke.com/inference-batching-and-deepseek/",
    "word_count": 2232
}