diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index ed673f1a..da2ea33d 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed OpenRouter/Poolside context overflow detection for `maximum allowed input length` errors ([#4943](https://github.com/earendil-works/pi/issues/4943)).
+
 ## [0.75.5] - 2026-05-23
 
 ### Breaking Changes
diff --git a/packages/ai/src/utils/overflow.ts b/packages/ai/src/utils/overflow.ts
index 8b908e85..e3a9b37a 100644
--- a/packages/ai/src/utils/overflow.ts
+++ b/packages/ai/src/utils/overflow.ts
@@ -16,6 +16,7 @@ import type { AssistantMessage } from "../types.ts";
  * - xAI: "This model's maximum prompt length is 131072 but the request contains 537812 tokens"
  * - Groq: "Please reduce the length of the messages or completion"
  * - OpenRouter: "This endpoint's maximum context length is X tokens. However, you requested about Y tokens"
+ * - OpenRouter/Poolside: "Input length X exceeds the maximum allowed input length of Y tokens."
  * - Together AI: "The input (X tokens) is longer than the model's context length (Y tokens)."
  * - llama.cpp: "the request exceeds the available context size, try increasing it"
  * - LM Studio: "tokens to keep from the initial prompt is greater than the context length"
@@ -39,7 +40,8 @@ const OVERFLOW_PATTERNS = [
 	/input token count.*exceeds the maximum/i, // Google (Gemini)
 	/maximum prompt length is \d+/i, // xAI (Grok)
 	/reduce the length of the messages/i, // Groq
-	/maximum context length is \d+ tokens/i, // OpenRouter (all backends)
+	/maximum context length is \d+ tokens/i, // OpenRouter (most backends)
+	/exceeds (?:the )?maximum allowed input length of [\d,]+ tokens?/i, // OpenRouter/Poolside
 	/input \(\d+ tokens\) is longer than the model'?s context length \(\d+ tokens\)/i, // Together AI
 	/exceeds the limit of \d+/i, // GitHub Copilot
 	/exceeds the available context size/i, // llama.cpp server
@@ -89,7 +91,8 @@ const NON_OVERFLOW_PATTERNS = [
  * - Groq: "reduce the length of the messages"
  * - Cerebras: 400/413 status code (no body)
  * - Mistral: "Prompt contains X tokens ... too large for model with Y maximum context length"
- * - OpenRouter (all backends): "maximum context length is X tokens"
+ * - OpenRouter (most backends): "maximum context length is X tokens"
+ * - OpenRouter/Poolside: "Input length X exceeds the maximum allowed input length of Y tokens."
  * - Together AI: "The input (X tokens) is longer than the model's context length (Y tokens)."
  * - llama.cpp: "exceeds the available context size"
  * - LM Studio: "greater than the context length"
diff --git a/packages/ai/test/overflow.test.ts b/packages/ai/test/overflow.test.ts
index b26948e2..346d2006 100644
--- a/packages/ai/test/overflow.test.ts
+++ b/packages/ai/test/overflow.test.ts
@@ -49,6 +49,13 @@ describe("isContextOverflow", () => {
 		expect(isContextOverflow(message, 131072)).toBe(true);
 	});
 
+	it("detects OpenRouter Poolside maximum allowed input length errors", () => {
+		const message = createErrorMessage(
+			"Provider returned error: Input length 131393 exceeds the maximum allowed input length of 131040 tokens.",
+		);
+		expect(isContextOverflow(message, 131072)).toBe(true);
+	});
+
 	it("does not treat generic non-overflow Ollama errors as overflow", () => {
 		const message = createErrorMessage("500 `model runner crashed unexpectedly`");
 		expect(isContextOverflow(message, 32768)).toBe(false);