diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index dd367e875de..7f8c464f5b9 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -38770,6 +38770,23 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "together_ai/zai-org/GLM-5.3-Flash": {
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048575,
+        "max_output_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://docs.together.ai/docs/serverless-models",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "tts-1": {
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "openai",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index dd367e875de..7f8c464f5b9 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -38770,6 +38770,23 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "together_ai/zai-org/GLM-5.3-Flash": {
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 1048575,
+        "max_output_tokens": 1048575,
+        "max_tokens": 1048575,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "source": "https://docs.together.ai/docs/serverless-models",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "tts-1": {
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "openai",
diff --git a/tests/test_litellm/test_together_ai_model_metadata.py b/tests/test_litellm/test_together_ai_model_metadata.py
index 5a0aadf4737..fbeb0c35fca 100644
--- a/tests/test_litellm/test_together_ai_model_metadata.py
+++ b/tests/test_litellm/test_together_ai_model_metadata.py
@@ -15,6 +15,7 @@ COST_MAP_ADAPTER: Final = TypeAdapter(CostMap)
 SERVERLESS_CHAT_MODELS: Final = (
     "together_ai/moonshotai/Kimi-K3",
     "together_ai/zai-org/GLM-5.2",
+    "together_ai/zai-org/GLM-5.3-Flash",
     "together_ai/deepseek-ai/DeepSeek-V4-Pro",
     "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813",
     "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731",
@@ -110,6 +111,21 @@ def test_together_glm_52_pricing(cost_map: CostMap):
     assert info["supports_reasoning"] is True
 
 
+def test_together_glm_53_flash_pricing_and_capabilities(cost_map: CostMap):
+    info = cost_map["together_ai/zai-org/GLM-5.3-Flash"]
+    assert info["input_cost_per_token"] == 1.5e-07
+    assert info["output_cost_per_token"] == 5e-07
+    assert info["cache_read_input_token_cost"] == 3e-08
+    assert info["max_input_tokens"] == 1048575
+    assert info["max_output_tokens"] == 1048575
+    assert info["supports_function_calling"] is True
+    assert info["supports_parallel_function_calling"] is True
+    assert info["supports_tool_choice"] is True
+    assert info["supports_response_schema"] is True
+    assert info["supports_vision"] is True
+    assert info["supports_reasoning"] is True
+
+
 def test_together_multilingual_e5_embedding_entry(cost_map: CostMap):
     info = cost_map["together_ai/intfloat/multilingual-e5-large-instruct"]
     assert info["mode"] == "embedding"