added -model

README.md

@@ -10,7 +10,7 @@ Hygate is a standalone, single-binary gateway that exposes Tencent's Hunyuan 3 (
 - Reasoning content passthrough (`reasoning_content`)
 - Tool/function calling, including incremental streaming of tool-call arguments
 - Fibonacci backoff retry on upstream calls
-- Configurable endpoint and User-Agent
+- Configurable endpoint, model name, and User-Agent
 - No external dependencies (standard library only)
 
 ## Installation
@@ -38,13 +38,14 @@ Alternatively, you can directly build from source by running `make`. This produc
 Run the gateway:
 
 ```
-hygate [-port 8080] [-endpoint https://tencent-hy3.hf.space]
+hygate [-port 8080] [-endpoint https://tencent-hy3.hf.space] [-model hy3]
 ```
 
 Available flags:
 
 - `-port` — TCP port to listen on (default `8080`)
 - `-endpoint` — root URL of the Hunyuan Gradio space (default `https://tencent-hy3.hf.space`)
+- `-model` — exposed model name (default `hy3`)
 - `-user-agent` / `-ua` — custom User-Agent sent to the upstream
 
 Endpoints served:
@@ -72,7 +73,7 @@ Even through the Gradio API, Tencent Hy3 is a very fast and performant model whe
 
 ### Which models are reported?
 
-A single model, `hy3`, is advertised via `/v1/models`.
+By default, a single model, `hy3` (configurable via the `-model` flag), is advertised via `/v1/models`.
 
 ### Are token usage counts returned?