diff --git a/llm-proxy.py b/llm-proxy.py
index dd67468..f6f24e1 100644
--- a/llm-proxy.py
+++ b/llm-proxy.py
@@ -659,7 +659,11 @@ class Handler(http.server.BaseHTTPRequestHandler):
         bytes_out = 0
         try:
             while True:
-                chunk = resp.read(65536)
+                # read1(): return as soon as ANY data is available (one underlying read),
+                # instead of read()'s "block until 64KB or EOF" -- otherwise a small
+                # streaming response (a few KB of SSE) only flushes at EOF, so reasoning
+                # + content land in one burst at the end instead of streaming through.
+                chunk = resp.read1(65536)
                 if not chunk:
                     break
                 self.wfile.write(chunk)