From ca44fb5ef9be74cf7f0dd1432a51ab3fa79eeff0 Mon Sep 17 00:00:00 2001 From: ai-bot Date: Thu, 24 Sep 2026 19:20:42 +0000 Subject: [PATCH] Update model example from deprecated glm-5-2 to glm-5-3 --- instructions.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/instructions.md b/instructions.md index 4c30e3c..b9a0501 100644 --- a/instructions.md +++ b/instructions.md @@ -48,7 +48,7 @@ Point any OpenAI-compatible client at the API address: ``` POST /v1/chat/completions -{"model": "private/glm-5-2", "messages": [{"role": "user", "content": "Hello"}]} +{"model": "private/glm-5-3", "messages": [{"role": "user", "content": "Hello"}]} ``` Anthropic-SDK clients (including Claude Code) can use the native endpoint at @@ -56,7 +56,7 @@ Anthropic-SDK clients (including Claude Code) can use the native endpoint at ``` export ANTHROPIC_BASE_URL="" -export ANTHROPIC_MODEL="private/glm-5-2" +export ANTHROPIC_MODEL="private/glm-5-3" ``` `GET /v1/models` lists the available private models, and the Status @@ -76,7 +76,7 @@ LXC-bridge address instead, which is plain HTTP (no TLS involved): 2. Copy the URL it prints — `http://:/v1`. 3. In Open WebUI: **Admin Panel → Connections → OpenAI API**, paste the URL in the URL field, click **Save**, and add the `private/` model IDs shown on the - Status Page (for example `private/glm-5-2`). + Status Page (for example `private/glm-5-3`). Any other service container on the same server can use the same URL. It is not reachable from your browser — that is what the LAN `https://` address is for. @@ -98,4 +98,4 @@ address, it means anyone with the address. Keeping it on the LAN, or on Tor with the address kept private, is the safe default. Backups of this service include your saved API key, and restoring a backup -restores it — keep that in mind when handling backup drives. \ No newline at end of file +restores it — keep that in mind when handling backup drives.