What's new in Claude Sonnet 5

Anthropic released Claude Sonnet 5, a new AI model with performance close to Opus 4.8 at lower prices, and updated its API by removing temperature, top_p, and top_k parameters. The model's tokenizer is roughly 1.4x more expensive for English text compared to previous versions.

Anthropic say of Sonnet 5 that "its performance is close to that of Opus 4.8, but at lower prices". The system card https://www-cdn.anthropic.com/9e6a1044980d8c4ed85669faf9c2a8342e2e9f1e/Claude%20Sonnet%205%20System%20Card.pdf helps explain how they were able to release the model without being blocked by the US government: Sonnet 5 is significantly less capable at cyber tasks than Mythos 5: its safeguards are thus similar to those we apply to Opus 4.7 and Opus 4.8 models that are more capable than Sonnet 5 but much less capable than Mythos 5 . Of note from the "what's new" API changes: temperature , top p , top k are no longer supported. "thinking": {type: "disabled"} .I used my Claude Token Counter https://tools.simonwillison.net/claude-token-counter tool to try out the new tokenizer. Here are my results for several larger documents: | Document | Sonnet 4.6 | Opus 4.7 | Sonnet 5 | |---|---|---|---| | So the new token is roughly 1.4x times more expensive for English, 1.33x for Spanish, 1.28x for Python code and effectively the same cost for Simplified Mandarin. Here's the pelican https://gist.github.com/simonw/a89e756b621a31e8ffc210e3428efa77 . It's nothing to write home about. Sonnet 5 thinks it looks like a goose. Via Hacker News https://news.ycombinator.com/item?id=48736605 Tags: ai https://simonwillison.net/tags/ai , generative-ai https://simonwillison.net/tags/generative-ai , llms https://simonwillison.net/tags/llms , anthropic https://simonwillison.net/tags/anthropic , claude https://simonwillison.net/tags/claude , llm-pricing https://simonwillison.net/tags/llm-pricing , pelican-riding-a-bicycle https://simonwillison.net/tags/pelican-riding-a-bicycle , llm-release https://simonwillison.net/tags/llm-release