diff --git a/hosts/FredOS-Mediaserver.nix b/hosts/FredOS-Mediaserver.nix
index 65da41a..4459f23 100644
--- a/hosts/FredOS-Mediaserver.nix
+++ b/hosts/FredOS-Mediaserver.nix
@@ -112,7 +112,18 @@
         ${pkgs.coreutils}/bin/mkdir -p "$work" || { echo "qs-ask: cannot create $work" >&2; exit 0; }
         cd "$work" || { echo "qs-ask: cannot enter $work" >&2; exit 0; }
 
-        ans=$(printf '%s' "$q" | ${pkgs.claude-code}/bin/claude -p \
+        # MAX_THINKING_TOKENS=0 is the single biggest win here, worth ~2.4x.
+        # Measured: Haiku defaults to extended thinking, and it spent 225 output
+        # tokens and 1.9s deliberating before emitting an 80-character answer
+        # about the height of a tower. With thinking off: 43 output tokens,
+        # time-to-first-text 2657ms -> 1122ms, wall clock 5.7s -> 2.4s, same
+        # answer. A one-line lookup has nothing to reason about.
+        #
+        # For the record, two things that are NOT the bottleneck, both measured:
+        # process startup (0.12s boot + 28ms to fire the request, so keeping a
+        # warm process saves nothing) and prompt size (184 input tokens).
+        ans=$(printf '%s' "$q" | ${pkgs.coreutils}/bin/env MAX_THINKING_TOKENS=0 \
+          ${pkgs.claude-code}/bin/claude -p \
           --safe-mode \
           --no-session-persistence \
           --tools "" \