lynkr/benchmark-configs/portkey-config.json

Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.

{
  "_comment": "Portkey Gateway Config — multi-provider conditional routing",
  "_note": "Portkey has NO automatic complexity detection. This config uses max_tokens as a proxy for complexity. For real tier routing pass x-portkey-metadata: { 'tier': 'simple|medium|complex|reasoning' } from your client.",

  "strategy": {
    "mode": "conditional"
  },

  "conditions": [
    {
      "_comment": "SIMPLE — short requests (max_tokens <= 256) → Ollama",
      "condition": {
        "query.max_tokens": { "$lte": 256 }
      },
      "target": {
        "provider": "ollama",
        "customHost": "http://localhost:11434",
        "override_params": {
          "model": "qwen2.5-coder:7b"
        }
      }
    },
    {
      "_comment": "MEDIUM — metadata tier=medium → Moonshot",
      "condition": {
        "metadata.tier": { "$eq": "medium" }
      },
      "target": {
        "provider": "openai",
        "apiKey": "{{MOONSHOT_API_KEY}}",
        "baseURL": "https://api.moonshot.ai/v1",
        "override_params": {
          "model": "moonshot-v1-8k"
        }
      }
    },
    {
      "_comment": "REASONING — metadata tier=reasoning → Azure OpenAI o3-mini",
      "condition": {
        "metadata.tier": { "$eq": "reasoning" }
      },
      "target": {
        "provider": "azure-openai",
        "apiKey": "{{AZURE_OPENAI_API_KEY}}",
        "resourceName": "YOUR-RESOURCE",
        "deploymentId": "o3-mini",
        "apiVersion": "2024-12-01-preview"
      }
    }
  ],

  "default": {
    "_comment": "COMPLEX — everything else → Azure OpenAI GPT-4o",
    "provider": "azure-openai",
    "apiKey": "{{AZURE_OPENAI_API_KEY}}",
    "resourceName": "YOUR-RESOURCE",
    "deploymentId": "gpt-4o",
    "apiVersion": "2024-08-01-preview"
  }
}