LiteLLM

Admin

User

Connecting

🚨 NOTE 🚨:

• LiteLLM requires connection to the network either through on-prem workloads like Coder or using Wireguard
• LiteLLM does not support OAuth and requires and admin provision your account.

1. Login to LiteLLM: https://litellm.internal.galaxygridlabs.com/ui/?page=api-keys
2. Create a new Virtual Key
3. Configure your AI workload to connect

Note: LiteLLM uses a GGL CA signed cert for TLS you need to add it to the trusted CA if you haven’t already see: Trusting Vault root CA

Claude

export ANTHROPIC_BASE_URL="https://litellm.internal.galaxygridlabs.com/"
export ANTHROPIC_AUTH_TOKEN="sk-...."
claude --model Qwen3.6-27B-FP8

OpenCode

cat <<EOF> ~/.config/opencode/opencode.jsonc
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "litellm": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LiteLLM",
      "options": {
        "baseURL": "https://litellm.internal.galaxygridlabs.com/"
      },
      "models": {
        "Qwen3.6-27B-FP8": {
          "name": "Qwen3.6 27B FP8"
        }
      }
    }
  }
}
EOF
 
opencode --model litellm/Qwen3.6-27B-FP8
 
# /connect
# Paste API Key `sk-...`

Hermes

# Install the GGL cert
export SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
hermes setup
> Provider Custom
> base url: https://litellm.internal.galaxygridlabs.com/
> api key: sk-...

You should see in ~/.hermes/config.yaml

model:
  default: Qwen3.6-27B-FP8
  provider: custom:qwen3.6-27b-fp8
  base_url: https://litellm.internal.galaxygridlabs.com/
  api_key: sk-...
// ...
custom_providers:
  - name: Qwen3.6-27B-FP8
    base_url: https://litellm.internal.galaxygridlabs.com/
    api_key: sk-...
    model: Qwen3.6-27B-FP8