Add OrcaRouter plugin

[zhenjunchen-png]

Plugin Submission Form

1. Metadata

• Plugin Author: orcarouter
• Plugin Name: orcarouter
• Repository URL: https://github.com/zhenjunchen-png/dify-plugin-orcarouter

2. Submission Type

• New plugin submission
• Version update for existing plugin

3. Description

OrcaRouter is an OpenAI-compatible LLM gateway routing requests across 40+ upstream providers (OpenAI, Anthropic, Google, DeepSeek, Qwen, Grok, Kimi, MiniMax, z.ai, etc.) with adaptive routing, fallback chains, and below-list-price billing.

This plugin exposes 120 models across three Dify model types:

• LLM (108) — including a virtual router orcarouter/auto (configurable strategies: cheapest / balanced / quality / adaptive LinUCB / gated_adaptive)
• Text Embedding (5) — OpenAI 3 + Google 2
• TTS (7) — OpenAI tts-1 / tts-1-hd / gpt-4o-mini-tts variants

Key features:

• Native reasoning controls per upstream style: OpenAI reasoning_effort (flat) for gpt-5 / o-series, Anthropic thinking block for Claude 4.x, DeepSeek auto-reasoning for r1 / reasoner
• extra_body routing exposure: per-request fallback model list via orcarouter_fallback_models + orcarouter_route parameters
• customizable-model mode enabled — users can add any model not in the predefined list without waiting for a plugin update

Tested locally on Dify 1.14.1: 505 offline pytest pass, 108 LLM + 5 embedding + 7 TTS live API tests pass, 7 functional scenarios verified through Dify UI.

Previously submitted to langgenius/dify-official-plugins as PR #3103 (Issue #3102); migrated here per maintainer's guidance.

4. Checklist

• I have read and followed the Publish to Dify Marketplace guidelines
• I have read and comply with the Plugin Developer Agreement
• I confirm my plugin works properly on both Dify Community Edition and Cloud Version
• I confirm my plugin has been thoroughly tested for completeness and functionality
• My plugin brings new value to Dify

5. Documentation Checklist

• Step-by-step setup instructions
• Detailed usage instructions
• All required APIs and credentials are clearly listed
• Connection requirements and configuration details
• Link to the repository for the plugin source code

6. Privacy Protection Information

Data Collection

This plugin does not collect any user personal data on its own. It is a thin client for the OrcaRouter API that transmits only:

• The user-provided API key (sent as Authorization: Bearer header to OrcaRouter)
• The prompt / messages / parameters submitted through Dify (forwarded to OrcaRouter for upstream routing)
• Input text for embedding and TTS endpoints

OrcaRouter's own data handling (request logging, billing data retention) is governed by the OrcaRouter privacy policy: https://www.orcarouter.ai/privacy.html

Privacy Policy

• I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

The plugin's README.md includes a "Privacy" section linking to https://www.orcarouter.ai/privacy.html

Disclosure

I'm an engineer on the OrcaRouter team.