{"slug": "how-fast-is-10-tokens-per-second-really", "title": "How fast is 10 tokens per second really?", "summary": "This article, published on May 20, 2026, highlights a simple HTML tool created by Mike Veerman that simulates different LLM token output speeds, ranging from 5 to 800 tokens per second. The tool is designed to help users visualize and understand the real-world feel of advertised speeds, such as \"30 tokens per second.\"", "body_md": "20th May 2026 - Link Blog\nHow fast is 10 tokens per second really? (via) Neat little HTML app by Mike Veerman (source code here) which simulates LLM token output speeds from 5/second to 800/second.\nUseful if you see a model advertised as \"30 tokens/second\" and want to get a feel for what that actually looks like.\nRecent articles\n- Gemini 3.5 Flash: more expensive, but Google plan to use it for everything - 19th May 2026\n- The last six months in LLMs in five minutes - 19th May 2026\n- Notes on the xAI/Anthropic data center deal - 7th May 2026", "url": "https://wpnews.pro/news/how-fast-is-10-tokens-per-second-really", "canonical_source": "https://simonwillison.net/2026/May/20/tokens-per-second/#atom-everything", "published_at": "2026-05-20 17:57:45+00:00", "updated_at": "2026-05-20 18:36:10.438560+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools"], "entities": ["Mike Veerman"], "alternates": {"html": "https://wpnews.pro/news/how-fast-is-10-tokens-per-second-really", "markdown": "https://wpnews.pro/news/how-fast-is-10-tokens-per-second-really.md", "text": "https://wpnews.pro/news/how-fast-is-10-tokens-per-second-really.txt", "jsonld": "https://wpnews.pro/news/how-fast-is-10-tokens-per-second-really.jsonld"}}