From f4a2a6239712bbbfaedbb23ee4faa653ca57f43f Mon Sep 17 00:00:00 2001
From: sirius <95621941@qq.com>
Date: Wed, 8 Jul 2026 09:35:17 +0800
Subject: [PATCH] fix(model-pricing): add openai aliases for kimi and glm
 aliases

---
 model_prices_and_context_window.json | 36 ++++++++++++++++++++++++++++
 tests/test_litellm/test_utils.py     | 28 ++++++++++++++++++++++
 2 files changed, 64 insertions(+)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 6cfa7c9e8be..f0cd408b192 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -38527,6 +38527,42 @@
         "litellm_provider": "openai",
         "mode": "chat"
     },
+    "openai/glm-5.2": {
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4.4e-06,
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
+    "openai/kimi-k2.7-code": {
+        "cache_read_input_token_cost": 1.9e-07,
+        "input_cost_per_token": 9.5e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
+    "openai/kimi-k2.7-code-highspeed": {
+        "cache_read_input_token_cost": 1.9e-07,
+        "input_cost_per_token": 9.5e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "openai/sora-2": {
         "litellm_provider": "openai",
         "mode": "video_generation",
diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py
index c35fb2fcbe2..058a2aa409e 100644
--- a/tests/test_litellm/test_utils.py
+++ b/tests/test_litellm/test_utils.py
@@ -3066,6 +3066,34 @@ def test_model_info_for_openrouter_kimi_k2_5():
     print("openrouter kimi-k2.5 model info", model_info)
 
 
+def test_model_info_for_openai_kimi_and_glm_aliases(local_model_cost_map):
+    kimi = litellm.get_model_info(model="openai/kimi-k2.7-code", custom_llm_provider="openai")
+    assert kimi is not None
+    assert kimi["litellm_provider"] == "openai"
+    assert kimi["input_cost_per_token"] == 9.5e-07
+    assert kimi["output_cost_per_token"] == 4e-06
+    assert kimi["cache_read_input_token_cost"] == 1.9e-07
+    assert kimi["max_input_tokens"] == 262144
+
+    kimi_highspeed = litellm.get_model_info(
+        model="openai/kimi-k2.7-code-highspeed", custom_llm_provider="openai"
+    )
+    assert kimi_highspeed is not None
+    assert kimi_highspeed["litellm_provider"] == "openai"
+    assert kimi_highspeed["input_cost_per_token"] == 9.5e-07
+    assert kimi_highspeed["output_cost_per_token"] == 4e-06
+    assert kimi_highspeed["cache_read_input_token_cost"] == 1.9e-07
+    assert kimi_highspeed["max_input_tokens"] == 262144
+
+    glm = litellm.get_model_info(model="openai/glm-5.2", custom_llm_provider="openai")
+    assert glm is not None
+    assert glm["litellm_provider"] == "openai"
+    assert glm["input_cost_per_token"] == 1.4e-06
+    assert glm["output_cost_per_token"] == 4.4e-06
+    assert glm["cache_read_input_token_cost"] == 2.6e-07
+    assert glm["max_input_tokens"] == 262144
+
+
 def test_gemini_embedding_2_ga_in_cost_map():
     """GA and Vertex preview gemini-embedding-2 entries align with multimodal unit pricing."""
     import json