From 4e7870d53ae0051718c7e4c17703369fdbdf44f3 Mon Sep 17 00:00:00 2001
From: Carlos Alexandro Becker <caarlos0@users.noreply.github.com>
Date: Wed, 21 Jan 2026 17:39:48 -0300
Subject: [PATCH] feat: update z.ai provider list (#161)

Signed-off-by: Carlos Alexandro Becker <caarlos0@users.noreply.github.com>
---
 CRUSH.md                            |  8 +++++
 internal/providers/configs/zai.json | 55 ++++++++++++++++++++++-------
 2 files changed, 50 insertions(+), 13 deletions(-)

diff --git a/CRUSH.md b/CRUSH.md
index a336013b5d9e6b7b9447b2ad8926d6ca889e25b6..133421d942d38fe18e88750f6e521cb0daf62123 100644
--- a/CRUSH.md
+++ b/CRUSH.md
@@ -22,3 +22,11 @@
 - HTTP: Always set timeouts, use context, defer close response bodies
 - JSON: Use `json.MarshalIndent` for pretty output, validate unmarshaling
 - File permissions: Use 0o600 for sensitive config files
+
+## Updating providers manually
+
+### Zai
+
+For `zai`, we'll need to grab the model list and capabilities from `https://docs.z.ai/guides/overview/overview`.
+
+That page does not contain the exact `context_window` and `default_max_tokens` though. We can grab the exact value from `./internal/providers/configs/openrouter.json`.
diff --git a/internal/providers/configs/zai.json b/internal/providers/configs/zai.json
index e010ff00d535c18e5eb2edde887b700375d0ee08..d4cd75ae8deb249b2b355485c7a9823e7c457d69 100644
--- a/internal/providers/configs/zai.json
+++ b/internal/providers/configs/zai.json
@@ -5,54 +5,83 @@
   "api_endpoint": "https://api.z.ai/api/coding/paas/v4",
   "type": "openai-compat",
   "default_large_model_id": "glm-4.7",
-  "default_small_model_id": "glm-4.5-air",
+  "default_small_model_id": "glm-4.7-flash",
   "models": [
     {
       "id": "glm-4.7",
       "name": "GLM-4.7",
-      "cost_per_1m_in": 0.6,
+      "cost_per_1m_in": 0.42,
       "cost_per_1m_out": 2.2,
       "cost_per_1m_in_cached": 0.11,
-      "cost_per_1m_out_cached": 0,
       "context_window": 204800,
-      "default_max_tokens": 131072,
+      "default_max_tokens": 102400,
+      "can_reason": true,
+      "supports_attachments": false
+    },
+    {
+      "id": "glm-4.7-flash",
+      "name": "GLM-4.7 Flash",
+      "cost_per_1m_in": 0.07,
+      "cost_per_1m_out": 0.4,
+      "cost_per_1m_in_cached": 0.01,
+      "context_window": 200000,
+      "default_max_tokens": 65550,
       "can_reason": true,
       "supports_attachments": false
     },
     {
       "id": "glm-4.6",
       "name": "GLM-4.6",
-      "cost_per_1m_in": 0.6,
-      "cost_per_1m_out": 2.2,
+      "cost_per_1m_in": 0.39,
+      "cost_per_1m_out": 1.9,
       "cost_per_1m_in_cached": 0.11,
-      "cost_per_1m_out_cached": 0,
       "context_window": 204800,
-      "default_max_tokens": 131072,
+      "default_max_tokens": 102400,
       "can_reason": true,
       "supports_attachments": false
     },
+    {
+      "id": "glm-4.6v",
+      "name": "GLM-4.6V",
+      "cost_per_1m_in": 0.3,
+      "cost_per_1m_out": 0.9,
+      "context_window": 131072,
+      "default_max_tokens": 65536,
+      "can_reason": true,
+      "supports_attachments": true
+    },
     {
       "id": "glm-4.5",
       "name": "GLM-4.5",
       "cost_per_1m_in": 0.6,
       "cost_per_1m_out": 2.2,
       "cost_per_1m_in_cached": 0.11,
-      "cost_per_1m_out_cached": 0,
       "context_window": 131072,
-      "default_max_tokens": 98304,
+      "default_max_tokens": 49152,
       "can_reason": true,
       "supports_attachments": false
     },
     {
       "id": "glm-4.5-air",
       "name": "GLM-4.5-Air",
-      "cost_per_1m_in": 0.2,
-      "cost_per_1m_out": 1.1,
+      "cost_per_1m_in": 0.13,
+      "cost_per_1m_out": 0.85,
       "cost_per_1m_in_cached": 0.03,
       "context_window": 131072,
-      "default_max_tokens": 98304,
+      "default_max_tokens": 49152,
       "can_reason": true,
       "supports_attachments": false
+    },
+    {
+      "id": "glm-4.5v",
+      "name": "GLM-4.5V",
+      "cost_per_1m_in": 0.6,
+      "cost_per_1m_out": 1.8,
+      "cost_per_1m_in_cached": 0.11,
+      "context_window": 65536,
+      "default_max_tokens": 8192,
+      "can_reason": true,
+      "supports_attachments": true
     }
   ]
 }