AI Agent Hub
Back to plugins
🤖

dsh-freeroute

Model Inference Updated 2026.08.26

Run the following command in DeepSeek Harness:

dsh plugin install dushaobindoudou/dsh-freeroute

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

In DeepSeek Harness, you can install this plugin by running the command 'dsh plugin install dushaobindoudou/dsh-freeroute'. Source: https://github.com/dushaobindoudou/dsh-freeroute

About this plugin

dsh-freeroute solves the issues of limited quotas and unstable service from free model providers for DeepSeek Harness users. It aggregates multiple free-tier upstreams (such as OpenCode Zen, B.AI, OpenRouter, etc.), ensuring automatic failover so that model inference requests switch to alternatives before the first token is generated, preventing interruptions. Core capabilities include multi-key rotation, privacy protection, health checks, and three-layer configuration management, alongside a local OpenAI-compatible endpoint for external tools to reuse. It is ideal for developers and researchers who want to leverage free model tiers without handling complex key management and failure recovery, as well as users needing a stable local interface for integrating other agents.

Use Cases

  • Automatically switch services when free model provider quotas are exhausted to ensure uninterrupted inference
  • Quickly test multiple free models in local development environments without complex configuration
  • Provide a stable model inference backend for DeepSeek Harness with automatic failure recovery

Best For

  • Developers using DeepSeek Harness for model inference
  • Researchers who want to leverage free model tiers without handling key management
  • Engineers needing a local OpenAI-compatible endpoint to integrate other AI tools