{"slug": "llm-anthropic-0-25-1", "title": "llm-anthropic 0.25.1", "summary": "Simon Willison released version 0.25.1 of the llm-anthropic plugin, adding support for the new Claude Opus 4.8 model and a fast mode option for eligible accounts. The update also changes the default max_tokens for each model to its maximum output instead of 8,192.", "body_md": "**Release:** [llm-anthropic 0.25.1](https://github.com/simonw/llm-anthropic/releases/tag/0.25.1)\n\n- New model:\n[Claude Opus 4.8](`claude-opus-4.8`\n\n).- New\n`-o fast 1`\n\noption for[fast mode], for organizations with that feature enabled on their account.- Default max_tokens for each model now defaults to that model's maximum output rather than 8,192.\n[#72]\n\nSee also my [notes on Opus 4.8](https://simonwillison.net/2026/May/28/claude-opus-4-8/) - I used this new release of `llm-anthropic`\n\nto generate the pelicans.", "url": "https://wpnews.pro/news/llm-anthropic-0-25-1", "canonical_source": "https://simonwillison.net/2026/May/28/llm-anthropic/#atom-everything", "published_at": "2026-05-28 23:54:56+00:00", "updated_at": "2026-05-29 01:41:51.715086+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "artificial-intelligence"], "entities": ["Anthropic", "Claude Opus 4.8", "llm-anthropic"], "alternates": {"html": "https://wpnews.pro/news/llm-anthropic-0-25-1", "markdown": "https://wpnews.pro/news/llm-anthropic-0-25-1.md", "text": "https://wpnews.pro/news/llm-anthropic-0-25-1.txt", "jsonld": "https://wpnews.pro/news/llm-anthropic-0-25-1.jsonld"}}