Smart Router Configuration & Cost Failover: Google Gemma 3 27B Instruct (google/gemma-3-27b-it) to Mistral Small 3.1 24B Instruct (mistralai/mistral-small-3.1-24b-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 (Google Gemma 3 27B Instruct — google/gemma-3-27b-it): $0.10 / 1M input tokens, $0.20 / 1M output tokens | TTFT: 340ms | Throughput: 85 tok/s
• Fallback Model (Mistral Small 3.1 24B Instruct — mistralai/mistral-small-3.1-24b-instruct): $0.05 / 1M input tokens, $0.10 / 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: "google/gemma-3-27b-it", inputPer1M: 0.10, outputPer1M: 0.20 },
  fallback: { model: "mistralai/mistral-small-3.1-24b-instruct", inputPer1M: 0.05, outputPer1M: 0.10 },
  retryOnStatus: [429, 500, 502, 503, 529]
};

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

model_list:
  - model_name: production-primary
    litellm_params:
      model: openrouter/google/gemma-3-27b-it
      timeout: 15
  - model_name: cost-fallback
    litellm_params:
      model: openrouter/mistralai/mistral-small-3.1-24b-instruct
router_settings:
  routing_strategy: latency-based-routing
  fallbacks: [{"production-primary": ["cost-fallback"]}]