Add Synthorai as a model provider

Self Checks

• I have read the Contributing Guide and Language Policy.
• I have searched for existing issues, including closed ones.
• I confirm that I am using English to submit this report.
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

I want to use Synthorai (https://synthorai.io) as a model provider inside a Dify workflow, the same way CometAPI and DeerAPI are already supported. Right now the only option is configuring it as a generic "OpenAI-API-compatible" custom model, which works for basic chat calls but loses the per-model catalog, context-window metadata, and pricing display that a dedicated provider plugin gets — so users browsing Model Providers in Dify have no idea Synthorai models are an option at all.

Synthorai is an OpenAI/Anthropic-compatible LLM gateway — one API key routes to 113 models across 11 upstream providers (Claude, GPT, Gemini, GLM-5.2, Kimi-K3, DeepSeek, Qwen, etc.), priced at direct upstream cost with no markup. It's live and stable, not a beta/waitlist product.

2. Additional context or comments

• API docs: https://synthorai.io/docs
• Base URL: https://synthorai.io, OpenAI-compatible /v1/chat/completions, standard Bearer auth
• Free tier for testing/review: 10 calls / up to $1, no card required
• Happy to model the plugin manifest closely on the existing CometAPI (https://github.com/langgenius/dify-official-plugins/pull/1438) or DeerAPI (https://github.com/langgenius/dify-official-plugins/pull/1702) plugins since the shape looks very similar

3. Can you help us with this feature?

• I am interested in contributing to this feature.