The llm-openrouter plugin now works with LLM 0.32 and reasoning LLMs from OpenRouter.
It adds three new server-side tools: Shell, WebFetch, and WebSearch, enabled via command-line options.
What happened
The llm-openrouter plugin has been updated to work with LLM 0.32, adding compatibility with reasoning LLMs through OpenRouter. The update also introduces three new server-side tools—Shell, WebFetch, and WebSearch—which can be enabled via command-line options like -T WebSearch.
Why it matters
This update enables developers and researchers using OpenRouter to access reasoning models more effectively, while new server-side tools expand what the plugin can do without requiring changes to the underlying model.
What to watch
The three new tools (Shell, WebFetch, WebSearch) are enabled through command-line flags, allowing users to add capabilities on demand.
Ask the AI about this article →
The update reflects the plugin's evolution to support OpenRouter's expanding model catalog, particularly reasoning models that require more sophisticated integration points. The move to OpenRouter's Responses API and the addition of server-side tools (Shell, WebFetch, WebSearch) suggests a shift toward enabling more complex, tool-augmented workflows without requiring users to manage separate infrastructure. By allowing tools to be toggled via command-line flags, the plugin maintains backward compatibility while letting advanced users compose more powerful agents.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Chinese large-model developer Z.ai says it can now support large-scale inference using roughly 100,000 domesti…
Analyst Ming-Chi Kuo says Nvidia has revived the Rubin CPX AI accelerator with a substantially redesigned arch…
A UK study by UK AI Security Institute and Limbic AI surveyed 6,474 British adults
Broadcom's Clayton Donley says companies are doing mission-critical work with AI agents quickly, but without t…
OpenAI released a new evaluation framework on July 17, 2026, urging companies to measure AI ROI by 'useful out…
As AI agents perform real business tasks, 'Agentic Identity' (giving each AI a unique employee-like ID) and 'D…
