From 7a1a7929bd245ebcd206edf575299cf8c94ad41f Mon Sep 17 00:00:00 2001
From: Peter Tripp <peter@zed.dev>
Date: Fri, 6 Dec 2024 18:59:40 +0000
Subject: [PATCH] docs: Add x.ai Grok example (#21655)

- Closes https://github.com/zed-industries/zed/issues/21635

<img width="639" alt="Screenshot 2024-12-06 at 13 57 42"
src="https://github.com/user-attachments/assets/a4434edb-3c7d-40c0-9df8-7e928a9307d0">


Release Notes:

- Document support for x.ai Grok
---
 docs/src/assistant/configuration.md | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/docs/src/assistant/configuration.md b/docs/src/assistant/configuration.md
index 2145bd95045c43177b4218c95d16dd3316c6020c..8e558007bf24ae98f049d95975e22dd0498c2a5b 100644
--- a/docs/src/assistant/configuration.md
+++ b/docs/src/assistant/configuration.md
@@ -192,6 +192,30 @@ The Zed Assistant comes pre-configured to use the latest version for common mode
 
 You must provide the model's Context Window in the `max_tokens` parameter, this can be found [OpenAI Model Docs](https://platform.openai.com/docs/models). OpenAI `o1` models should set `max_completion_tokens` as well to avoid incurring high reasoning token costs. Custom models will be listed in the model dropdown in the assistant panel.
 
+### OpenAI API Compatible
+
+Zed supports using OpenAI compatible APIs by specifying a custom `endpoint` and `available_models` for the OpenAI provider.
+
+#### X.ai Grok
+
+Example configuration for using X.ai Grok with Zed:
+
+```json
+  "language_models": {
+    "openai": {
+      "api_url": "https://api.x.ai/v1",
+      "available_models": [
+        {
+          "name": "grok-beta",
+          "display_name": "X.ai Grok (Beta)",
+          "max_tokens": 131072
+        }
+      ],
+      "version": "1"
+    },
+  }
+```
+
 ### Advanced configuration {#advanced-configuration}
 
 #### Example Configuration