diff --git a/workers/augorWorker.js b/workers/augorWorker.js
index 2eb424b..3e44754 100644
--- a/workers/augorWorker.js
+++ b/workers/augorWorker.js
@@ -306,6 +306,9 @@ async function callLlm(llmConfig, prompt) {
     model: llmConfig.llmModel || llmConfig.model,
     messages: [{ role: "user", content: prompt }],
     temperature: 0.1,
+    // Unbounded requests get a 402 for reserving the model's whole output
+    // window against the remaining key budget, before running anything.
+    max_tokens: Math.max(512, Number(process.env.OPEN_ROUTER_MAX_TOKENS) || 6000),
   });
 
   const url = new URL("https://openrouter.ai/api/v1/chat/completions");
diff --git a/workers/consolidationWorker.js b/workers/consolidationWorker.js
index 559f815..f17a4a4 100644
--- a/workers/consolidationWorker.js
+++ b/workers/consolidationWorker.js
@@ -220,6 +220,9 @@ Rules:
     model: llmConfig.llmModel || llmConfig.model,
     messages: [{ role: "user", content: prompt }],
     temperature: 0.1,
+    // Unbounded requests get a 402 for reserving the model's whole output
+    // window against the remaining key budget, before running anything.
+    max_tokens: Math.max(512, Number(process.env.OPEN_ROUTER_MAX_TOKENS) || 6000),
   });
 
   const url = new URL("https://openrouter.ai/api/v1/chat/completions");
diff --git a/workers/signalWorker.js b/workers/signalWorker.js
index 78aaf61..1da1cb1 100644
--- a/workers/signalWorker.js
+++ b/workers/signalWorker.js
@@ -297,6 +297,9 @@ async function callLlm(llmConfig, prompt) {
     model: llmConfig.llmModel || llmConfig.model,
     messages: [{ role: "user", content: prompt }],
     temperature: 0.1,
+    // Unbounded requests get a 402 for reserving the model's whole output
+    // window against the remaining key budget, before running anything.
+    max_tokens: Math.max(512, Number(process.env.OPEN_ROUTER_MAX_TOKENS) || 4000),
   });
 
   const url = new URL("https://openrouter.ai/api/v1/chat/completions");