DeepSeek
DeepSeek Harness Desktop + LLMoxy
The DeepSeek Harness desktop app, with the same interface as the web version. It bundles its own runtime, so you just download and install it, with no Node.js needed.
Quick Start
- 1
Install the desktop app
Download it from the DeepSeek Harness website. The macOS version needs Apple silicon and macOS 13 or later; the Windows version is a 64-bit installer.
Go to downloads - 2
Create an API key
Create a token in the Console, pick the group you want to use, and copy the key.
Create a token - 3
Add a custom model API
Go to "Settings" → "Models" → "Add model provider" and switch to "Custom model API". Set Provider ID to
llmoxy, set the API protocol to OpenAI Chat Completions, enter the base URL below, and paste your key.URL - 4
Add model
Click "Fetch available models" and select the models you want, or enter a model ID directly, such as
deepseek-v4-pro. After saving, select it in the model picker.
Tips
- This is a developer preview. The config format may change after upgrades.
- Provider ID can't be changed after saving, so choose a name that's easy to recognize.
- Each provider uses one protocol. To use OpenAI Responses or Anthropic Messages, create another provider. The Responses URL also includes
/v1; for Anthropic, enterhttps://en.llmoxy.com. - The desktop app's config is in
$DSH_HOME/profiles/desktop/cordis.patch.yml, separate from the web version's (profiles/web). Providers you added in the web version need to be added again in the desktop app. - There's no desktop app for Intel Macs or Linux yet. Use the web version or the
dshcommand line instead.
FAQ
Requests rejected or getting parameter errors?
compat.supportsDeveloperRole: false and compat.maxTokensField: max_tokens to this provider.Model still thinking with reasoning level set to off?
compat.thinkingFormat to deepseek.Other tools
yetone
magpie
Pick models for all your agents in one place. Claude Code, Codex, OpenCode, and others each use their own model, routed through one local gateway.
Anthropic
Claude
Anthropic's AI assistant and coding agent: Claude Desktop, plus Claude Code in the terminal and in VS Code.
OpenAI
ChatGPT (Codex)
OpenAI's coding agent. The ChatGPT desktop app, the CLI, and the IDE extension share one config.toml, so one setup covers all three.
Antigravity
Google's coding agent, the successor to Gemini CLI. For now, only the CLI lets you change the API URL.
View guideAnomaly
OpenCode
Open-source coding agent with a desktop app and a terminal UI. You can configure multiple model providers.
Anysphere
Cursor
AI editor built on VS Code. Override the OpenAI URL to route OpenAI models in chat through LLMoxy.
View guideGitHub
GitHub Copilot
The Copilot app, Copilot CLI, and VS Code all support bring your own key (BYOK), with no Copilot subscription required.
ByteDance
Trae
ByteDance's AI IDE. Both the China and international versions support custom models.
View guideCline
Cline
Open-source coding agent with a full agent loop, available as a command-line tool and as VS Code and JetBrains extensions.
Alibaba
Qoder
Alibaba's AI coding product. The Qoder desktop app and Qoder CLI support custom models; Qoder IDE doesn't yet.
Tencent
CodeBuddy
Tencent's AI coding tools. Both the command-line CodeBuddy Code and CodeBuddy IDE support OpenAI-compatible custom models.
Tencent
WorkBuddy
Tencent's desktop AI workspace for office and coding tasks. It supports custom model services.
View guideCherryHQ
Cherry Studio
Cross-platform desktop AI client. Add a provider to fetch the list of available models in one click.
View guideChatbox AI
Chatbox
AI chat client for desktop and mobile. Add a model provider in settings to connect.
View guideLangGenius
Dify
Open-source LLM app development platform. Connect it as OpenAI-API-compatible to build apps and workflows.
View guiden8n
n8n
Workflow automation platform. Enter the LLMoxy URL in an OpenAI credential to call models.
View guide