diff --git a/packages/phoenix-evals/src/phoenix/evals/models/bedrock.py b/packages/phoenix-evals/src/phoenix/evals/models/bedrock.py
index 1234980e854..a1874c5ebe8 100644
--- a/packages/phoenix-evals/src/phoenix/evals/models/bedrock.py
+++ b/packages/phoenix-evals/src/phoenix/evals/models/bedrock.py
@@ -1,3 +1,4 @@
+import asyncio
 import json
 import logging
 from dataclasses import dataclass, field
@@ -21,8 +22,9 @@ class BedrockModel(BaseModel):
     AWS API are dynamically throttled when encountering rate limit errors. Requires the `boto3`
     package to be installed.
 
-    Supports Async: ❌
-        `boto3` does not support async calls
+    Supports Async: 🟡
+        `boto3` does not support async calls, but the syncrhonous call is wrapped in an 
+        executor to allow for concurrent calls.
 
     Args:
         model_id (str): The model name to use.
@@ -109,7 +111,8 @@ def _generate(self, prompt: str, **kwargs: Dict[str, Any]) -> str:
         return self._parse_output(response) or ""
 
     async def _async_generate(self, prompt: str, **kwargs: Dict[str, Any]) -> str:
-        return self._generate(prompt, **kwargs)
+        loop = asyncio.get_event_loop()
+        return await loop.run_in_executor(None, self._generate, prompt, **kwargs)
 
     def _rate_limited_completion(self, **kwargs: Any) -> Any:
         """Use tenacity to retry the completion call."""