From b99124971f7138087f90c0befad0ba9f37710856 Mon Sep 17 00:00:00 2001
From: "liangjie.wanglj" <122603020@qq.com>
Date: Fri, 13 Feb 2026 16:38:14 +0800
Subject: [PATCH] feat: add zai/glm-5 model configuration

Add pricing and configuration for zai/glm-5:
- 200k input, 128k output tokens
- Supports reasoning, prompt caching, function calling, and tool choice
- Cache read cost: 2e-05 per token
- Input cost: 1e-04 per token
- Output cost: 3.2e-04 per token

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---
 .../model_prices_and_context_window_backup.json   | 15 +++++++++++++++
 model_prices_and_context_window.json              | 15 +++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 71fb82b2d78..c4883b4e944 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -31946,6 +31946,21 @@
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
+    "zai/glm-5": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 2e-05,
+        "input_cost_per_token": 1e-04,
+        "output_cost_per_token": 3.2e-04,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
     "zai/glm-4.6": {
         "cache_creation_input_token_cost": 0,
         "cache_read_input_token_cost": 1.1e-07,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index f43e3dcbde5..c2155bcdbe3 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -31946,6 +31946,21 @@
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
+    "zai/glm-5": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 2e-05,
+        "input_cost_per_token": 1e-04,
+        "output_cost_per_token": 3.2e-04,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
     "zai/glm-4.6": {
         "cache_creation_input_token_cost": 0,
         "cache_read_input_token_cost": 1.1e-07,