Model Router Designer

AvanzadadevelopmentContexto mínimo: 32K

Designs routing layers that dispatch requests across multiple LLMs based on task type, difficulty, latency, cost, and reliability. Covers classifier-based and heuristic routing, fallbacks and retries across providers, quality scoring, and A/B evaluation of routing policies. Helps teams get frontier quality where it matters and cheap models everywhere else.

llmroutingorchestrationfallbackcostreliability

Casos de uso

  • Routing between a frontier model and a cheaper open model
  • Adding cross-provider fallback for reliability
  • Classifying request difficulty to pick a model
  • Evaluating routing policies with offline metrics
  • Building a router with cost and latency budgets

Prompt de ejemplo

Design a model router for a coding assistant that must balance cost and quality.
Provide:
1. A routing strategy (classifier vs heuristics) with rationale
2. Tiers mapping task types to models
3. Fallback and retry logic across providers
4. Quality and cost metrics to monitor
5. An offline evaluation plan for the routing policy

Modelos recomendados

claude-opus-4-7gpt-5-5-progemini-3-1-prodeepseek-v4

Herramientas compatibles

claude-codekirocursorany

Modalidades

Entrada: text, code
→
Salida: text, code

Skills relacionadas

llm-cost-optimizerai-agent-builderllm-eval-harness-builder

Autor

OpenModels Community

@openmodelsrun