diff --git a/litellm/litellm_core_utils/health_check_utils.py b/litellm/litellm_core_utils/health_check_utils.py
index ff252855f0d..874d260eba7 100644
--- a/litellm/litellm_core_utils/health_check_utils.py
+++ b/litellm/litellm_core_utils/health_check_utils.py
@@ -2,10 +2,29 @@
 Utils used for litellm.ahealth_check()
 """
 
+#: litellm params that ``_update_litellm_params_for_health_check`` injects for
+#: chat-completion health checks but that are invalid (or rejected) on every
+#: other handler in :class:`HealthCheckHelpers.get_mode_handlers` — image and
+#: video generation, embeddings, audio speech / transcription, rerank, ocr,
+#: responses, batch, etc. ``messages`` is always chat-only; ``max_tokens`` is
+#: chat/completion-only and is rejected by strict providers (e.g. OpenAI's
+#: image-generation endpoints return 400 ``Unknown parameter: 'max_tokens'``).
+_NON_CHAT_HEALTH_CHECK_STRIP_KEYS = {"messages", "max_tokens"}
+
 
 def _filter_model_params(model_params: dict) -> dict:
-    """Remove 'messages' param from model params."""
-    return {k: v for k, v in model_params.items() if k != "messages"}
+    """Strip chat-only params before invoking a non-chat health check handler.
+
+    ``litellm.acompletion`` is the only mode handler that consumes
+    ``model_params`` unfiltered; every other handler routes through this
+    helper, so removing chat-completion-only keys here keeps strict providers
+    (OpenAI image generation, etc.) from rejecting the request.
+    """
+    return {
+        k: v
+        for k, v in model_params.items()
+        if k not in _NON_CHAT_HEALTH_CHECK_STRIP_KEYS
+    }
 
 
 def _create_health_check_response(response_headers: dict) -> dict: