diff --git a/arch/envoy.template.yaml b/arch/envoy.template.yaml
index c1373335..56070bfe 100644
--- a/arch/envoy.template.yaml
+++ b/arch/envoy.template.yaml
@@ -339,6 +339,26 @@ static_resources:
                             cluster: bright_staff
                             timeout: {{ llm_gateway_listener.timeout }}
                 http_filters:
+                  - name: envoy.filters.http.compressor
+                    typed_config:
+                      "@type": type.googleapis.com/envoy.extensions.filters.http.compressor.v3.Compressor
+                      compressor_library:
+                        name: compress
+                        typed_config:
+                          "@type": type.googleapis.com/envoy.extensions.compression.gzip.compressor.v3.Gzip
+                          memory_level: 3
+                          window_bits: 10
+                  - name: envoy.filters.http.decompressor
+                    typed_config:
+                      "@type": type.googleapis.com/envoy.extensions.filters.http.decompressor.v3.Decompressor
+                      decompressor_library:
+                        name: decompress
+                        typed_config:
+                          "@type": "type.googleapis.com/envoy.extensions.compression.gzip.decompressor.v3.Gzip"
+                          window_bits: 9
+                          chunk_size: 8192
+                          # If this ratio is set too low, then body data will not be decompressed completely.
+                          max_inflate_ratio: 1000
                   - name: envoy.filters.http.router
                     typed_config:
                       "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router