lynkr/config/model-tiers.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.

{
  "tiers": {
    "SIMPLE": {
      "description": "Greetings, simple Q&A, confirmations, basic lookups",
      "range": [0, 25],
      "priority": 1,
      "preferred": {
        "ollama": ["llama3.2", "gemma2", "phi3", "qwen2.5:7b", "mistral"],
        "llamacpp": ["default"],
        "lmstudio": ["default"],
        "openai": ["gpt-4o-mini", "gpt-3.5-turbo"],
        "azure-openai": ["gpt-4o-mini", "gpt-35-turbo"],
        "anthropic": ["claude-3-haiku-20240307", "claude-3-5-haiku-20241022"],
        "bedrock": ["anthropic.claude-3-haiku-20240307-v1:0", "amazon.nova-lite-v1:0"],
        "databricks": ["databricks-claude-haiku-4-5", "databricks-gpt-5-nano"],
        "google": ["gemini-2.0-flash", "gemini-1.5-flash"],
        "openrouter": ["google/gemini-flash-1.5", "deepseek/deepseek-chat"],
        "zai": ["GLM-4-Flash"],
        "moonshot": ["kimi-k2-turbo-preview"]
      }
    },
    "MEDIUM": {
      "description": "Code reading, simple edits, research, documentation",
      "range": [26, 50],
      "priority": 2,
      "preferred": {
        "ollama": ["qwen2.5:32b", "deepseek-coder:33b", "codellama:34b"],
        "llamacpp": ["default"],
        "lmstudio": ["default"],
        "openai": ["gpt-4o", "gpt-4-turbo"],
        "azure-openai": ["gpt-4o", "gpt-4"],
        "anthropic": ["claude-sonnet-4-20250514", "claude-3-5-sonnet-20241022"],
        "bedrock": ["anthropic.claude-3-5-sonnet-20241022-v2:0", "amazon.nova-pro-v1:0"],
        "databricks": ["databricks-claude-sonnet-4-5", "databricks-gpt-5-1"],
        "google": ["gemini-1.5-pro", "gemini-2.0-pro"],
        "openrouter": ["anthropic/claude-3.5-sonnet", "openai/gpt-4o"],
        "zai": ["GLM-4.7"],
        "moonshot": ["kimi-k2-turbo-preview"]
      }
    },
    "COMPLEX": {
      "description": "Multi-file changes, debugging, architecture, refactoring",
      "range": [51, 75],
      "priority": 3,
      "preferred": {
        "ollama": ["qwen2.5:72b", "llama3.1:70b", "deepseek-coder-v2:236b"],
        "openai": ["o1-mini", "o3-mini", "gpt-4o"],
        "azure-openai": ["o1-mini", "gpt-4o"],
        "anthropic": ["claude-sonnet-4-20250514", "claude-3-5-sonnet-20241022"],
        "bedrock": ["anthropic.claude-3-5-sonnet-20241022-v2:0"],
        "databricks": ["databricks-claude-sonnet-4-5", "databricks-gpt-5-1-codex-max"],
        "google": ["gemini-2.5-pro", "gemini-1.5-pro"],
        "openrouter": ["anthropic/claude-3.5-sonnet", "meta-llama/llama-3.1-405b"],
        "zai": ["GLM-4.7"],
        "moonshot": ["kimi-k2-turbo-preview"]
      }
    },
    "REASONING": {
      "description": "Complex analysis, security audits, novel problems, deep thinking",
      "range": [76, 100],
      "priority": 4,
      "preferred": {
        "openai": ["o1", "o1-pro", "o3"],
        "azure-openai": ["o1", "o1-pro"],
        "anthropic": ["claude-opus-4-20250514", "claude-3-opus-20240229"],
        "bedrock": ["anthropic.claude-3-opus-20240229-v1:0"],
        "databricks": ["databricks-claude-opus-4-6", "databricks-claude-opus-4-5", "databricks-gpt-5-2"],
        "google": ["gemini-2.5-pro"],
        "openrouter": ["anthropic/claude-3-opus", "deepseek/deepseek-reasoner", "openai/o1"],
        "deepseek": ["deepseek-reasoner", "deepseek-r1"],
        "moonshot": ["kimi-k2-thinking", "kimi-k2-turbo-preview"]
      }
    }
  },
  "localProviders": {
    "ollama": { "free": true, "defaultTier": "SIMPLE" },
    "llamacpp": { "free": true, "defaultTier": "SIMPLE" },
    "lmstudio": { "free": true, "defaultTier": "SIMPLE" }
  },
  "providerAliases": {
    "azure": "azure-openai",
    "aws": "bedrock",
    "amazon": "bedrock",
    "claude": "anthropic",
    "gemini": "google",
    "vertex": "google",
    "kimi": "moonshot"
  }
}