From bd794f9f18c7422824a36e7d02086ebea25e8ec2 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Mon, 31 Aug 2026 13:26:37 -0700
Subject: [PATCH] fix(friendli): track GLM-5.3 discounted live pricing and
 declare effort levels

---
 model_prices_and_context_window.json                | 13 ++++++++-----
 .../test_friendli_glm_5_3_model_metadata.py         |  9 ++++-----
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 24aad7c90c8..f70a0ac63d9 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -19571,12 +19571,15 @@
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "max_output_tokens": 1048576,
-        "input_cost_per_token": 1.4e-06,
-        "output_cost_per_token": 4.4e-06,
-        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.26e-06,
+        "output_cost_per_token": 3.96e-06,
+        "cache_read_input_token_cost": 2.34e-07,
         "supports_prompt_caching": true,
-        "supports_max_reasoning_effort": true,
-        "supports_low_reasoning_effort": true,
+        "reasoning_effort_levels": [
+            "low",
+            "high",
+            "max"
+        ],
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
         "supports_native_structured_output": true,
diff --git a/tests/test_litellm/test_friendli_glm_5_3_model_metadata.py b/tests/test_litellm/test_friendli_glm_5_3_model_metadata.py
index 5e7a1ede699..5282b0f589e 100644
--- a/tests/test_litellm/test_friendli_glm_5_3_model_metadata.py
+++ b/tests/test_litellm/test_friendli_glm_5_3_model_metadata.py
@@ -16,15 +16,14 @@ def test_friendli_glm_5_3_model_info():
     ), f"{model} not found in model_prices_and_context_window.json"
     assert info["litellm_provider"] == "friendliai"
     assert info["mode"] == "chat"
-    assert info["input_cost_per_token"] == 1.4e-06
-    assert info["output_cost_per_token"] == 4.4e-06
-    assert info["cache_read_input_token_cost"] == 2.6e-07
+    assert info["input_cost_per_token"] == 1.26e-06
+    assert info["output_cost_per_token"] == 3.96e-06
+    assert info["cache_read_input_token_cost"] == 2.34e-07
     assert info["max_input_tokens"] == 1048576
     assert info["max_output_tokens"] == 1048576
     assert info["supports_function_calling"] is True
     assert info["supports_reasoning"] is True
-    assert info["supports_low_reasoning_effort"] is True
-    assert info["supports_max_reasoning_effort"] is True
+    assert info["reasoning_effort_levels"] == ["low", "high", "max"]
     assert info["supports_tool_choice"] is True
     assert info["supports_prompt_caching"] is True
     assert info["supports_vision"] is False