llm-anthropic 0.25.1

2026-05-28 · Source: Simon Willison's Weblog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

The "llm-anthropic" plugin, version 0.25.1, was released on May 28th, 2026, significantly enhancing access to Anthropic's Claude series large language models. This update introduces direct support for the newly available Claude Opus 4.8 model, which can be accessed using the "claude-opus-4.8" identifier. A key new feature is the "-o fast 1" option, designed to enable "fast mode" for organizations that have this capability activated on their Anthropic accounts, potentially speeding up certain operations. Additionally, the plugin now intelligently sets the default max_tokens for each model to match its maximum possible output, rather than a previously fixed 8,192. This change, addressing issue #72, optimizes token handling and improves overall model utilization for users interacting with Anthropic's latest offerings.

Key takeaway

For AI Engineers integrating Anthropic models, this "llm-anthropic" 0.25.1 update is crucial. You should upgrade your plugin to immediately access Claude Opus 4.8, enabling use of Anthropic's latest flagship model. If your organization has fast mode enabled, utilize the new "-o fast 1" option to potentially accelerate inference. Additionally, the improved default max_tokens handling means you no longer need to manually configure this for optimal model output, streamlining your development workflow.

Key insights

llm-anthropic 0.25.1 integrates Claude Opus 4.8, adds fast mode, and optimizes max_tokens defaults for better model interaction.

In practice

• Access Claude Opus 4.8 via `llm-anthropic`.
• Enable fast mode with `-o fast 1` option.
• Utilize automatic max_tokens for models.

Topics

• llm-anthropic
• Claude Opus 4.8
• Large Language Models
• Anthropic API
• Fast Mode
• Token Management

Code references

• simonw/llm-anthropic

Best for: AI Engineer, Machine Learning Engineer, NLP Engineer

Related on AIssential

• llm-anthropic 0.25 — The `llm-anthropic` library update adds new Claude models and enhanced control over model "thinking" processes.
• 🗞️ Anthropic added a Fast Mode (2.5× higher output tokens per second) switch for Claude Opus 4.6 — Fast Mode boosts Claude Opus 4.6 output speed at a 6x cost premium, while TinyLoRA enables reasoning gains with minimal parameter updates.
• Anthropic just dropped Opus 4.6... — Claude Opus 4.6 significantly advances LLM agentic autonomy and context handling, especially for complex coding and enterprise tasks.
• Anthropic Unveils Updated Opus 4.7 Model — AI model development is rapidly advancing, with a clear distinction between general-purpose and specialized, high-risk applications.
• [AINews] Anthropic Claude Opus 4.7 - literally one step better than 4.6 in every dimension — Claude Opus 4.7 significantly advances AI capabilities in coding, vision, and complex task execution, despite potential token cost increases.
• Wtf Anthropic — Anthropic's compute miscalculation and opaque policies are alienating users, while OpenAI aggressively captures market share.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Simon Willison's Weblog.