Megadose AI progress, ranked and analyzed.

llm-anthropic 0.28

Simon Willison ·
`llm-anthropic` now shows supported Claude reasoning traces by default.

Version 0.28 adds default display of reasoning traces for Anthropic models that support them. It also introduces a new `llm_anthropic.ClaudeRefusal` exception for Claude refusal cases. The release covers LLM access to Anthropic models, including the Claude series Claude Fable 5.1. Source: Simon Willison's note.

score 8

Categories: Model Releases