Smart Router Configuration & Cost Failover: Microsoft Phi-4 (microsoft/phi-4) to Llama 3.1 8B Instruct (meta-llama/llama-3.1-8b-instruct)

Production LLM API routing configuration, TTFT latency SLA (<400ms), and contribution margin failover benchmark generated by TokenMargin.dev.

1. Pricing & Latency Benchmark Summary

• Primary Model (Microsoft Phi-4 — microsoft/phi-4): $0.06 / 1M input tokens, $0.14 / 1M output tokens | TTFT: 340ms | Throughput: 85 tok/s
• Fallback Model (Llama 3.1 8B Instruct — meta-llama/llama-3.1-8b-instruct): $0.03 / 1M input tokens, $0.05 / 1M output tokens | TTFT: 340ms | Throughput: 85 tok/s

2. Zero-Dependency TypeScript / Node.js Smart Router Configuration

export const SMART_ROUTER_CONFIG = {
  slaMaxTtftMs: 400,
  primary: { model: "microsoft/phi-4", inputPer1M: 0.06, outputPer1M: 0.14 },
  fallback: { model: "meta-llama/llama-3.1-8b-instruct", inputPer1M: 0.03, outputPer1M: 0.05 },
  retryOnStatus: [429, 500, 502, 503, 529]
};

3. LiteLLM / OpenRouter YAML Router Configuration (config.yaml)

model_list:
  - model_name: production-primary
    litellm_params:
      model: openrouter/microsoft/phi-4
      timeout: 15
  - model_name: cost-fallback
    litellm_params:
      model: openrouter/meta-llama/llama-3.1-8b-instruct
router_settings:
  routing_strategy: latency-based-routing
  fallbacks: [{"production-primary": ["cost-fallback"]}]