AI Agent Hub
Back to plugins
🤖

dsh-provider-qoder

Model Inference Updated 2026.09.16

Run the following command in DeepSeek Harness:

dsh plugin install mo-n/dsh-provider-qoder

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install mo-n/dsh-provider-qoder in your terminal to install the plugin. The source repository is at https://github.com/mo-n/dsh-provider-qoder . After installation, restart your DSH profile and configure the PAT and model selection under Settings → Models.

About this plugin

If you already hold a Qoder subscription and want to call its models directly from within DeepSeek Harness, you need a bridge. dsh-provider-qoder is a community adapter plugin that plugs Qoder's text, image, streaming, and tool-calling capabilities into the DSH workflow.

It supports both the Global and China service regions, authenticates via a Personal Access Token, and auto-discovers available models on your account with pricing multipliers and reasoning-effort tiers. For vision-capable models, images are published to the Qoder center service and referenced by URL to keep payloads small; if publication fails, the image is sent inline so the turn still completes. Streaming responses, reasoning content, tool calls, and multi-turn interactions all work natively within DSH. The settings page also surfaces account details, personal quota, organization resource packs, and reset dates.

This plugin suits developers who already run Qoder subscriptions inside DSH and want a single, manageable model pipeline-especially those juggling both Global and China regions, relying on image input, or chaining multi-step tool calls. The plugin handles only authentication and model communication; tool execution, workspace operations, and permission management remain with DSH itself, keeping responsibilities clean.

Use Cases

  • Call Qoder models directly inside DSH for multi-turn chat and streaming output
  • Combine image and text input with Qoder vision models and chain tool calls
  • Manage Qoder subscriptions across both Global and China regions from one interface

Best For

  • Developers with an active Qoder subscription who want a unified DSH interface
  • AI application builders relying on image input and multi-step tool-calling chains
  • Teams managing model services across both Global and China regions