diff --git a/packages/ai/src/utils/retry.ts b/packages/ai/src/utils/retry.ts
index f0a180138..24e327ad6 100644
--- a/packages/ai/src/utils/retry.ts
+++ b/packages/ai/src/utils/retry.ts
@@ -79,6 +79,9 @@ const RETRYABLE_PROVIDER_ERROR_PATTERN = buildProviderErrorPattern([
 	"you can retry your request",
 	"try your request again",
 	"please retry your request",
+
+	// gRPC based providers (e.g. NVIDIA NIM)
+	"ResourceExhausted",
 ]);
 
 /**
diff --git a/packages/ai/test/retry.test.ts b/packages/ai/test/retry.test.ts
index 64ff6d429..70b0c4099 100644
--- a/packages/ai/test/retry.test.ts
+++ b/packages/ai/test/retry.test.ts
@@ -6,6 +6,7 @@ const openAIExplicitRetryMessage =
 	"An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID req_******** in your message.";
 const bedrockExplicitRetryMessage =
 	'{"message":"The system encountered an unexpected error during processing. Try your request again."}';
+const nvidiaNIMResourceExhaustedMessage = "ResourceExhausted: Worker local total request limit reached (288/48)";
 const bunFetchSocketClosedMessage =
 	"The socket connection was closed unexpectedly. For more information, pass `verbose: true` in the second argument to fetch()";
 
@@ -21,6 +22,11 @@ describe("provider retry classification", () => {
 				fauxAssistantMessage("", { stopReason: "error", errorMessage: bedrockExplicitRetryMessage }),
 			),
 		).toBe(true);
+		expect(
+			isRetryableAssistantError(
+				fauxAssistantMessage("", { stopReason: "error", errorMessage: nvidiaNIMResourceExhaustedMessage }),
+			),
+		).toBe(true);
 	});
 
 	it("matches Bun fetch socket drop wording", () => {