diff --git a/ai/setup.py b/ai/setup.py
index 19c8667..e30a0f6 100644
--- a/ai/setup.py
+++ b/ai/setup.py
@@ -34,7 +34,7 @@ def get_optimal_model(base_type="pro"):
 
 def get_default_models():
     return {
-        "logic": {"model": "models/gemini-2.0-pro-exp", "reason": "Fallback: Gemini 2.0 Pro for complex reasoning and JSON adherence.", "estimated_cost": "$0.00/1M (Experimental)"},
+        "logic": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for cost-effective logic and JSON adherence.", "estimated_cost": "$0.10/1M"},
         "writer": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for fast, high-quality creative writing.", "estimated_cost": "$0.10/1M"},
         "artist": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for visual prompt design.", "estimated_cost": "$0.10/1M"},
         "ranking": []
@@ -86,17 +86,18 @@ def select_best_models(force_refresh=False):
         - Gemini 1.5 Pro: ~$1.25 Input / $5.00 Output. (Legacy, expensive).
 
         CRITERIA:
-        - LOGIC: Needs complex reasoning, strict JSON adherence, plot consistency, and instruction following.
-          -> Prefer: Gemini 2.5 Pro > 2.0 Pro > 2.0 Flash > 1.5 Pro
+        - LOGIC: Needs JSON adherence, plot consistency, and instruction following. COST IS THE PRIORITY — use Flash unless no Flash 2.x exists.
+          -> Prefer: Gemini 2.5 Flash > 2.0 Flash > 1.5 Flash > 2.5 Pro > 2.0 Pro > 1.5 Pro
         - WRITER: Needs creativity, prose quality, long-form text generation, and speed.
-          -> Prefer: Gemini 2.5 Flash/Pro > 2.0 Flash > 1.5 Flash (balance quality/cost)
+          -> Prefer: Gemini 2.5 Flash > 2.0 Flash > 1.5 Flash (balance quality/cost; avoid Pro)
         - ARTIST: Needs rich visual description, prompt understanding for cover art design.
           -> Prefer: Gemini 2.0 Flash > 1.5 Flash (speed and visual understanding)
 
         CONSTRAINTS:
+        - Strongly prefer Flash over Pro for all roles — Pro models are expensive and only used selectively at runtime for critical rewrites.
         - Strongly prefer Gemini 2.x over 1.5 where available.
         - Avoid 'experimental' or 'preview' only if a stable 2.x version exists; otherwise experimental 2.x is fine.
-        - 'thinking' models are too slow/expensive for Writer/Artist roles.
+        - 'thinking' models are too slow/expensive for any role.
         - Provide a ranking of ALL available models from best to worst overall.
 
         OUTPUT_FORMAT (JSON only, no markdown):