Smart Router Configuration & Cost Failover: Liquid AI d1.2-ultra (liquid/d1.2-ultra) to Microsoft MAI Decision 1.1 (microsoft/decision-1.1)
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 (Liquid AI d1.2-ultra — liquid/d1.2-ultra): $0.04 / 1M input tokens, $0.00 / 1M output tokens | TTFT: 85ms | Throughput: 420 tok/s
- Fallback Model (Microsoft MAI Decision 1.1 — microsoft/decision-1.1): $0.04 / 1M input tokens, $0.00 / 1M output tokens | TTFT: 42ms | Throughput: 850 tok/s
2. Zero-Dependency TypeScript / Node.js Smart Router Configuration
export const SMART_ROUTER_CONFIG = {
slaMaxTtftMs: 400,
primary: { model: "liquid/d1.2-ultra", inputPer1M: 0.04, outputPer1M: 0.00 },
fallback: { model: "microsoft/decision-1.1", inputPer1M: 0.04, outputPer1M: 0.00 },
retryOnStatus: [429, 500, 502, 503, 529]
};
3. LiteLLM / OpenRouter YAML Router Configuration (config.yaml)
model_list:
- model_name: production-primary
litellm_params:
model: openrouter/liquid/d1.2-ultra
timeout: 15
- model_name: cost-fallback
litellm_params:
model: openrouter/microsoft/decision-1.1
router_settings:
routing_strategy: latency-based-routing
fallbacks: [{"production-primary": ["cost-fallback"]}]
⚡ Ready for Production Deployment?
Download Full Production TypeScript Failover Gateway + CI Token Guardrails
Includes zero-dependency circuit-breaker router, Redis semantic cache docker-compose & CFO board audit spreadsheet.