Per-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.
- GitHub stars
- 2
- License
- MIT
- Added
- 2026-08-19
GitHub info
- GitHub stars
- 2
- License
- MIT
- Primary language
- JavaScript
- Last push
- Aug 19, 2026, 8:46 AM
- Maintainer
- superfish058
- Added
- 2026-08-19
Install
Install command
dsh plugin --profile web add @superfish058/dsh-llm-proxyREADME badge
Add this Markdown to your plugin README to link back to its listing.
Listed onDSH Get
[](https://dshget.com/plugins/superfish058/dsh-llm-proxy)Related plugins
Models & Providersdsh-plugin-subscriptions
★ 297Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.
Models & ProvidersV1ki
dsh-commandcode-provider
★ 126Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.
Models & ProvidersMars-Sea
dsh-AuthInOne
★ 105Adds account login, API and custom Provider setup, model switching, image fallback for text-only models, and token/cost attribution to DeepSeek Harness 47f.
Models & ProvidersStormycry-cryp