diff --git a/src/autonomy/llm.js b/src/autonomy/llm.js
index d532629..9a4a583 100644
--- a/src/autonomy/llm.js
+++ b/src/autonomy/llm.js
@@ -35,12 +35,14 @@ async function callCoordinator(config, prompt, options = {}) {
       body: JSON.stringify({
         model: config.openRouter.llmModel,
         temperature: 0,
-        // Sized against reality rather than guessed: the largest proposal this has
-        // ever produced was ~1,258 tokens carrying 12 predictions, the average is
-        // ~50. Reasoning models spend completion tokens thinking first, so this is
-        // still several times the worst case actually observed.
+        // Deliberately far above any output we have seen, because the cap exists to
+        // satisfy openrouter's affordability check, not to ration tokens: you are
+        // billed for what is used, not what is reserved. 6000 was tight enough to
+        // truncate a real replay article. The 402 handler below walks this down
+        // automatically when the budget cannot cover it, so a high ceiling costs
+        // nothing while funded and degrades on its own when not.
         max_tokens: options.maxTokens
-          || Math.max(512, Number(config?.openRouter?.maxTokens || process.env.OPEN_ROUTER_MAX_TOKENS) || 6000),
+          || Math.max(512, Number(config?.openRouter?.maxTokens || process.env.OPEN_ROUTER_MAX_TOKENS) || 32000),
         response_format: { type: 'json_object' },
         messages: [
           { role: 'system', content: 'You are a coordinator. Extract only evidence-backed categorical hypotheses. Never output probabilities, expected returns, confidence scores, position sizes, or trade actions.' },