llm-gemini 0.38.1 发布:修正 Gemini 4 系列的 xhigh 推理档位支持
llm-gemini 0.38.1
Simon Willison 修了 llm-gemini 插件的一个配置疏漏,顺便实测出 Gemini 4 Hydrogen 的 xhigh 档位:token 用量涨约 6 倍后,效果能追上 Gemini 4 Neon。用 Gemini API 的人可以看看他的对比表,权衡下成本和质量的取舍。
Simon Willison 发布了 llm-gemini 0.38.1 小版本更新,修正了他此前在插件中遗漏的问题:Gemini 4 Carbon 只支持 low、medium、high 三档推理级别,而 Gemini 4 Hydrogen 和 Gemini 4 Neon 还多一个 xhigh 档位。
这次更新实测了 xhigh 档位的实际效果。以经典的“骑自行车鹈鹕”测试为例,Gemini 4 Hydrogen 在 high 档位输出 5,311 个 token、成本 3.99 美分;切到 xhigh 后输出 token 增至 31,477 个、成本升至 23.61 美分,约 6 倍开销换来了与 Gemini 4 Neon 相当的输出质量。
对开发者来说,这个版本说明推理档位配置直接影响成本与质量的权衡,Hydrogen 的 xhigh 可能在部分任务上以更低价格逼近 Neon 的表现。Willison 同步更新了他的 Gemini 4 对比表格,方便查阅各模型在不同档位下的 token 用量和费用。
llm-gemini 0.38.1
Release: llm-gemini 0.38.1 Gemini 4 Carbon only supports low , medium and high reasoning levels - but Gemini 4 Hydrogen and Gemini 4 Neon both have an extra xhigh level. I missed that when I added those models to the llm-gemini plugin, which is now fixed in this dot release. The xhigh setting for Hydrogen makes a significant difference. I updated my Gemini 4 comparison grid - note how Hydrogen at high used 5,311 output tokens and cost 3.99 cents, but the same model at xhigh used 31,477 output tokens, cost 23.61 cents, and produced a pelican that's competitive with Gemini 4 Neon: Tags: gemini , llm , llm-reasoning , pelican-riding-a-bicycle , ai , llms , google , generative-ai
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Gemini, llm-gemini, Google, reasoning models.
Source attribution: curated from Simon Willison’s Weblog.