diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md
index 4404bf6898f..869bab3d827 100644
--- a/docs/my-website/docs/proxy/config_settings.md
+++ b/docs/my-website/docs/proxy/config_settings.md
@@ -480,6 +480,7 @@ router_settings:
 | DEFAULT_FAILURE_THRESHOLD_PERCENT | Threshold percentage of failures to cool down a deployment. Default is 0.5 (50%)
 | DEFAULT_FLUSH_INTERVAL_SECONDS | Default interval in seconds for flushing operations. Default is 5
 | DEFAULT_HEALTH_CHECK_INTERVAL | Default interval in seconds for health checks. Default is 300 (5 minutes)
+| DEFAULT_HEALTH_CHECK_PROMPT | Default prompt used during health checks for non-image models. Default is "test from litellm"
 | DEFAULT_IMAGE_HEIGHT | Default height for images. Default is 300
 | DEFAULT_IMAGE_TOKEN_COUNT | Default token count for images. Default is 250
 | DEFAULT_IMAGE_WIDTH | Default width for images. Default is 300
diff --git a/docs/my-website/docs/proxy/health.md b/docs/my-website/docs/proxy/health.md
index 7df7685f335..6f98265e40a 100644
--- a/docs/my-website/docs/proxy/health.md
+++ b/docs/my-website/docs/proxy/health.md
@@ -106,6 +106,13 @@ model_list:
       mode: image_generation # 👈 ADD THIS
 ```
 
+#### Custom Health Check Prompt
+
+By default, health checks use the prompt `"test from litellm"`. You can customize this prompt globally by setting an environment variable, or per-model via config:
+
+```bash
+DEFAULT_HEALTH_CHECK_PROMPT="this is a test prompt"
+```
 
 ### Text Completion Models 
 
diff --git a/litellm/constants.py b/litellm/constants.py
index 7a39596a7ef..17de0e0bd19 100644
--- a/litellm/constants.py
+++ b/litellm/constants.py
@@ -1,6 +1,7 @@
 import os
 from typing import List, Literal
 
+DEFAULT_HEALTH_CHECK_PROMPT = str(os.getenv("DEFAULT_HEALTH_CHECK_PROMPT", "test from litellm"))
 AZURE_DEFAULT_RESPONSES_API_VERSION = str(
     os.getenv("AZURE_DEFAULT_RESPONSES_API_VERSION", "preview")
 )
diff --git a/litellm/proxy/health_check.py b/litellm/proxy/health_check.py
index 2f4bb081819..427a16a9801 100644
--- a/litellm/proxy/health_check.py
+++ b/litellm/proxy/health_check.py
@@ -8,7 +8,7 @@ from typing import List, Optional
 import litellm
 
 logger = logging.getLogger(__name__)
-from litellm.constants import HEALTH_CHECK_TIMEOUT_SECONDS
+from litellm.constants import HEALTH_CHECK_TIMEOUT_SECONDS, DEFAULT_HEALTH_CHECK_PROMPT
 
 ILLEGAL_DISPLAY_PARAMS = [
     "messages",
@@ -99,7 +99,7 @@ async def _perform_health_check(model_list: list, details: Optional[bool] = True
             litellm.ahealth_check(
                 model["litellm_params"],
                 mode=mode,
-                prompt="test from litellm",
+                prompt=DEFAULT_HEALTH_CHECK_PROMPT,
                 input=["test from litellm"],
             ),
             timeout,
diff --git a/tests/litellm_utils_tests/test_health_check.py b/tests/litellm_utils_tests/test_health_check.py
index 4d55a25f334..8af19f9c18a 100644
--- a/tests/litellm_utils_tests/test_health_check.py
+++ b/tests/litellm_utils_tests/test_health_check.py
@@ -518,4 +518,67 @@ async def test_ahealth_check_ocr():
         mode="ocr",
     )
     print(response)
-    return response
\ No newline at end of file
+    return response
+
+@pytest.mark.asyncio
+async def test_image_generation_health_check_prompt(monkeypatch):
+    """Health checks should respect default and environment-configured prompts."""
+
+    import importlib
+    import litellm.constants as litellm_constants
+    import litellm.proxy.health_check as health_check
+
+    def reload_modules():
+        reloaded_constants = importlib.reload(litellm_constants)
+        reloaded_health_check = importlib.reload(health_check)
+        return reloaded_constants, reloaded_health_check
+
+    async def run_health_check(health_check_module):
+        health_check_calls = []
+
+        async def mock_health_check(litellm_params, mode=None, prompt=None, input=None):
+            health_check_calls.append(
+                {
+                    "mode": mode,
+                    "prompt": prompt,
+                    "model": litellm_params.get("model"),
+                }
+            )
+            return {"status": "healthy"}
+
+        model_list = [
+            {
+                "litellm_params": {"model": "dall-e-3", "api_key": "fake-key"},
+                "model_info": {
+                    "mode": "image_generation",
+                },
+            }
+        ]
+
+        with patch(
+            "litellm.proxy.health_check.litellm.ahealth_check",
+            side_effect=mock_health_check,
+        ):
+            await health_check_module._perform_health_check(model_list)
+
+        return health_check_calls
+
+    # Default prompt is used when env var is unset
+    monkeypatch.delenv("DEFAULT_HEALTH_CHECK_PROMPT", raising=False)
+    litellm_constants, health_check = reload_modules()
+    health_check_calls = await run_health_check(health_check)
+
+    assert len(health_check_calls) == 1
+    assert (
+        health_check_calls[0]["prompt"]
+        == litellm_constants.DEFAULT_HEALTH_CHECK_PROMPT
+    )
+
+    # Environment override should change the prompt without code changes
+    override_prompt = "environment override prompt"
+    monkeypatch.setenv("DEFAULT_HEALTH_CHECK_PROMPT", override_prompt)
+    litellm_constants, health_check = reload_modules()
+    health_check_calls = await run_health_check(health_check)
+
+    assert len(health_check_calls) == 1
+    assert health_check_calls[0]["prompt"] == override_prompt
\ No newline at end of file