AI News HubLIVE
原文

llm-anthropic 0.25.1

Release of llm-anthropic 0.25.1 adds support for Claude Opus 4.8, fast mode option for eligible accounts, and changes default max_tokens to each model's maximum output.

Article intelligence

EngineersIntermediate

Key points

  • New model: Claude Opus 4.8 (claude-opus-4.8).
  • New -o fast 1 option for fast mode (for organizations with feature enabled).
  • Default max_tokens now defaults to each model's maximum output instead of 8,192.

Why it matters

This matters because new model: Claude Opus 4.8 (claude-opus-4.8).

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

Release: llm-anthropic 0.25.1

Simon Willison’s Weblog

Subscribe

28th May 2026

Release

llm-anthropic 0.25.1 — LLM access to models by Anthropic, including the Claude series

New model: Claude Opus 4.8 (claude-opus-4.8).

New -o fast 1 option 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. #72

See also my notes on Opus 4.8 - I used this new release of llm-anthropic to generate the pelicans.

Recent articles

Claude Opus 4.8: "a modest but tangible improvement" - 28th May 2026

I think Anthropic and OpenAI have found product-market fit - 27th May 2026

Notes on Pope Leo XIV's encyclical on AI - 25th May 2026

This is a beat by Simon Willison, posted on 28th May 2026.

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe

Disclosures

Colophon

©

2002

2003

2004

2005

2006

2007

2008

2009

2010

2011

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023

2024

2025

2026