AdminSmart Router
A

Smart Router

Live routing rules · model performance · change LLM per task without a deploy

LLM Providers — Live Status

Task Routing Rules

Per-task LLM assignment — click Edit to override the model for any task type

0 rules
No task rules configured

SARAH Platform Routing

Per social-platform routing — Twitter, LinkedIn, Instagram, TikTok and more

0 rules
No platform rules configured

Model Performance Stats

Loading model stats…

Per-Agent Model Config

Priority 2 — overrides generic task rules

Click Edit on any row to override a model at runtime (saved to Redis instantly — no restart needed).

Provider API Keys

— set in .env file, restart API to apply
ProviderEnv VariableModels AvailableStatusPriority
OpenRouterOPENROUTER_API_KEYAll 22 models (gateway)○ Not configured
OpenAIOPENAI_API_KEYGPT-4o, GPT-4o-mini, GPT-4.1, GPT-5...○ Not configured
xAI (Grok)XAI_API_KEYGrok-3, Grok-4.1-fast○ Not configured
AnthropicANTHROPIC_API_KEYClaude 3.5, 3.7, Sonnet 4○ Not configured
Google AIGOOGLE_AI_API_KEYGemini 2.0, 2.5, 3.1...○ Not configured
DeepSeekDEEPSEEK_API_KEYDeepSeek V3, V3.2○ Not configured
MistralMISTRAL_API_KEYMistral Large, Medium...○ Not configured
Groq/LlamaGROQ_API_KEYLlama 3.3 70B, 8B...○ Not configured

To activate a provider: add its API key to morezo/.env → restart API (pm2 restart morezo-api) → provider appears in LLM Control automatically. Set USE_DIRECT_PROVIDERS=true to bypass OpenRouter entirely and use direct APIs.

How Smart Router Works

1

Explicit Model

Agent requests a specific model → used directly, bypassing routing.

2

Task Type

taskType set → router picks the best model per task routing rules above.

3

Platform Rule

SARAH social task → platform-specific routing (Twitter=Grok, LinkedIn=GPT-4o-mini).

4

Fallback Chain

Primary fails → fallback model → highest-priority available provider.