1.5 KiB
1.5 KiB
AI Model Chain — IT Pro Partner
Updated: July 24, 2026 Active Policy: Cost-Controlled Multi-Tier Fallback Chain
Chain Configuration
| Tier | Model | Provider | Key / Endpoint | Notes |
|---|---|---|---|---|
| Primary | claude-sonnet-5 |
admin-ai |
~/.secure/hermes-normal-ops-key.json |
Main conductor via LiteLLM ($3.33/day cap) |
| Fallback 1 | deepseek-v4-pro |
admin-ai |
~/.secure/hermes-normal-ops-key.json |
Primary workhorse fallback on admin-ai |
| Fallback 2 | deepseek-v4-flash |
admin-ai |
~/.secure/hermes-normal-ops-key.json |
Fast low-cost fallback on admin-ai |
| Fallback 3 | deepseek-chat |
deepseek |
Direct DeepSeek API Key | Independent provider (survives admin-ai outage) |
| Fallback 4 | grok-2-1212 |
xai |
Direct xAI API Key | Independent provider (survives admin-ai outage) |
Admin-AI Proxy (LiteLLM)
- URL:
https://admin-ai.itpropartner.com/v1(app1,152.53.36.131) - Master Key:
/root/docker/litellm/.envon app1 (Hudu [178] LiteLLM Master Key) - Hermes Virtual Key:
hermes-normal-ops-daily-capped(~/.secure/hermes-normal-ops-key.json) - Daily Budget Cap: $3.33/day ($100/30-day cap)
Delegation Subagents
- Model:
deepseek-v4-proviaadmin-ai - Fallback:
deepseek-v4-flashviaadmin-ai
Excluded from Production Routing
- Gemini / Ollama: Excluded from normal production routing per policy.
- GPT-5.6 / Terra / Opus: Escalation-only, requires explicit approval and user confirmation.