昨天写了篇《模型福音（dsh-our-free-model）——免费无限制使用最新模型》，阅读量和转发量都不错，看到网友在评论区问“是否可以在 WorkBuddy 中配置这些免费模型使用”，简单在评论区回复了下，其实是可以的，这篇就详细说说如何操作并配置这些免费模型吧。
首先，基于上篇文章，找到插件中的【网关设置】页部分。
开启【启用网关】开关，把下面的“端点链接”和 API Key 分别复制出来。
打开 WorkBuddy，打开设置，找到模型模块。
点击弹窗右上角的【添加模型】按钮，打开添加模型弹框。
配置 dsh-our-free-model 免费的模型相关信息。
供应商：选择最下面的自定义
接口地址：粘贴上面步骤保存的“端点链接”
API Key：粘贴上面步骤保存的“API Key”
模型名称：后面详细说如何获取
高级配置：如果配置的免费模型支持图片、思考等，那就选上吧
点击保存，回到 WorkBuddy 首页面，新建会话，选择刚才配置的模型，开始测试。
到此使用 dsh-our-free-model 免费的模型如何配置到 WorkBuddy 就算完成了，当然也可以多配置几个想使用的免费模型。
不过要 特别注意：由于模型地址是本机环境，所以不能关闭 DeepSeek Harness，否则插件未加载启动，模型不可用。所以说与其在 WorkBuddy 中使用这些模型，不如直接在 DeepSeek Harness 中直接使用这些模型。启动两个智能体客户端，主机电脑性能一般的话，又吵又烫，你懂得~
接下来补充下上面的模型名称如何填写。
Window 电脑打开 CMD 命令窗口，贴入以下命令获取即可。
C:\Users\tzhuw> -H “Authorization: Bearer 上面步骤保存的API Key”
获取可用的模型信息后如下：
注意填写 id 对应的信息，而不是 name。为了查阅方面，下面贴一下当前可用模型的列表，供参考。
| # | 模型 ID | 显示名 | 输入 | 思考档位 | 默认 | 备注 |
|---|---|---|---|---|---|---|
| 1 | our-free-model/big-pickle | Big Pickle | text/image | light/balanced/deep | balanced | vision + text input · 256K context · tunable thinking budget |
| 2 | our-free-model/flint-40b-free | Flint 40b Free | text | light/balanced/deep | balanced | text input · 128K context · tunable thinking budget |
| 3 | our-free-model/mimo-v2.6-flash-free | MiMo V2.6 Flash | text/image | light/balanced/deep | balanced | vision + text input · 1024K context · thinking always on · 16K default ceiling, shared with the answer |
| 4 | our-free-model/nemotron-3.5-super-vl-free | Nemotron 3 5 Super Vl Free | text/image | disabled/minimal/low/medium/high/xhigh | high | vision + text input · 1024K context · thinking levels: disabled / minimal / low / medium / high / xhigh |
| 5 | our-free-model/nemotron-3.5-lightning-free | Nemotron 3.5 Lightning | text | light/balanced/deep | balanced | text input · 125K context · tunable thinking budget |
| 6 | our-free-model/deepseek-v4.1-flash-free | DeepSeek V4.1 Flash | text/image | disabled/low/high/max | high | vision + text input · 1024K context · thinking levels: disabled / low / high / max |
| 7 | our-free-model/glm-5.3-flash-free | GLM 5.3 Flash | text/image | low/high/max | high | vision + text input · 1024K context · thinking levels: low / high / max |
| 8 | our-free-model/opencode/glm-5.3-flash-free | EAC GLM 5.3 Flash Highspeed | text/image | disabled/minimal/low/medium/high/xhigh/max | high | vision + text input · 1024K context · thinking levels: disabled / minimal / low / medium / high / xhigh / max |
| 9 | our-free-model/opencode/nemotron-3.5-super-vl-free | EAC Nemotron 3 5 Super Vl Free | text | light/balanced/deep | balanced | text input · 128K context · thinking always on · 16K default ceiling, shared with the answer |
| 10 | our-free-model/opencode/flint-40b-free | EAC Flint 40b Free | text | light/balanced/deep | balanced | text input · 128K context · thinking always on · 16K default ceiling, shared with the answer |
| 11 | our-free-model/opencode/deepseek-v4.1-flash-free | EAC DeepSeek V4.1 Flash Highspeed | text/image | disabled/minimal/low/medium/high/xhigh/max | high | vision + text input · 1024K context · thinking levels: disabled / minimal / low / medium / high / xhigh / max |
| 12 | our-free-model/opencode/nemotron-3.5-lightning-free | EAC Nemotron 3 5 Lightning Free | text | light/balanced/deep | balanced | text input · 128K context · thinking always on · 16K default ceiling, shared with the answer |
| 13 | our-free-model/kilo-auto/free | Kilo Auto Free | text | low/medium/high | high | text input · 250K context · thinking levels: low / medium / high |
| 14 | our-free-model/nvidia/nemotron-3.5-super-vl:free | Kilo Nemotron 3.5 Super VL | text/image | disabled/low/medium/high | high | vision + text input · 977K context · thinking levels: disabled / low / medium / high |
| 15 | our-free-model/reflection/beam-free | Kilo Beam 1.0 | text | disabled/low/medium/high | high | text input · 1024K context · thinking levels: disabled / low / medium / high |
| 16 | our-free-model/stealth/glyph-cluster | Kilo Glyph Cluster | text | disabled/low/medium/high | high | text input · 250K context · thinking levels: disabled / low / medium / high |
| 17 | our-free-model/dots-studio/dots-3-note-preview:free | Kilo Dots3-Note Preview | text/image | disabled/low/medium/high | high | vision + text input · 500K context · thinking levels: disabled / low / medium / high |
| 18 | our-free-model/nvidia/nemotron-3.5-lightning:free | Kilo Nemotron 3.5 Lightning | text | disabled/low/medium/high | high | text input · 977K context · thinking levels: disabled / low / medium / high |
| 19 | our-free-model/cohere/north-mini-code:free | Kilo North Mini Code | text | disabled/low/medium/high | high | text input · 250K context · thinking levels: disabled / low / medium / high |
| 20 | our-free-model/nvidia/nemotron-3-ultra-550b-a55b:free | Kilo Nemotron 3 Ultra | text | disabled/low/medium/high | high | text input · 977K context · thinking levels: disabled / low / medium / high |
| 21 | our-free-model/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Kilo Nemotron 3 Nano Omni | text/image | disabled/low/medium/high | high | vision + text input · 250K context · thinking levels: disabled / low / medium / high |
| 22 | our-free-model/openrouter/free | Kilo OpenRouter Free Models Router | text/image | low/medium/high | high | vision + text input · 195K context · thinking levels: low / medium / high |
| 23 | our-free-model/combo:recommended-free | 推荐免费组 | text/image | light/balanced/deep | balanced | vision + text input · 1024K context · 2-model chain: deepseek-v4.1-flash-free -> glm-5.3-flash-free |
如果你想配置模型到其它智能体客户端，也都是一样的操作，有兴趣可以翻翻之前的一些文章，比如在 OpenClaw、Hermes、CherryStudio、OpenCode 配置模型如何使用等
你学废了么 ^ ^ Good Luck~
《WorkBuddy 配置使用 dsh-our-free-model 免费的模型》有0条回应