diff --git a/src/modules/llms/vendors/unifiedStreamingClient.ts b/src/modules/llms/vendors/unifiedStreamingClient.ts
index 6549b27c0..7c8484bad 100644
--- a/src/modules/llms/vendors/unifiedStreamingClient.ts
+++ b/src/modules/llms/vendors/unifiedStreamingClient.ts
@@ -66,7 +66,7 @@ export async function unifiedStreamingClient<TSourceSetup = unknown, TLLMOptions
 
   // model params (llm)
   const { llmRef, llmTemperature, llmResponseTokens } = (llmOptions as any) || {};
-  if (!llmRef || llmTemperature === undefined || !llmResponseTokens)
+  if (!llmRef || llmTemperature === undefined)
     throw new Error(`Error in configuration for model ${llmId}: ${JSON.stringify(llmOptions)}`);
 
   // prepare the input, similarly to the tRPC openAI.chatGenerate
@@ -75,7 +75,7 @@ export async function unifiedStreamingClient<TSourceSetup = unknown, TLLMOptions
     model: {
       id: llmRef,
       temperature: llmTemperature,
-      maxTokens: llmResponseTokens,
+      ...(llmResponseTokens ? { maxTokens: llmResponseTokens } : {}),
     },
     history: messages,
   };