lynkr/benchmark-configs/litellm_config.yaml

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.

# ─── LiteLLM Benchmark Config ─────────────────────────────────────────────────
# Multi-provider tier routing via LiteLLM Complexity Router.
#
# Start: litellm --config benchmark-configs/litellm_config.yaml --port 8082
#
# Required env vars:
#   AZURE_OPENAI_API_KEY
#   AZURE_OPENAI_ENDPOINT   (https://YOUR-RESOURCE.openai.azure.com)
#   MOONSHOT_API_KEY
#   (Ollama needs no key — running locally on :11434)
#
# Tier mapping (matches Lynkr benchmark config):
#   SIMPLE    → ollama:minimax-m2.5:cloud
#   MEDIUM    → ollama:minimax-m2.5:cloud
#   COMPLEX   → moonshot:moonshot-v1-auto
#   REASONING → azure-openai:gpt-5.2-chat

model_list:

  # ── SIMPLE + MEDIUM → Ollama minimax-m2.5:cloud ───────────────────────────
  # Note: the model tag is "minimax-m2.5:cloud" — the colon is part of the
  # Ollama model name, NOT a provider separator here.
  - model_name: smart-router
    litellm_params:
      model: "ollama/minimax-m2.5:cloud"
      api_base: http://localhost:11434
  - model_name: smart-router
    litellm_params:
      model: "ollama/minimax-m2.5:cloud"
      api_base: http://localhost:11434

  # ── COMPLEX → Moonshot moonshot-v1-auto (matches Lynkr TIER_COMPLEX) ────────
  - model_name: smart-router
    litellm_params:
      model: openai/moonshot-v1-auto
      api_base: https://api.moonshot.ai/v1
      api_key: os.environ/MOONSHOT_API_KEY

  # ── REASONING → Azure OpenAI gpt-5.2-chat ─────────────────────────────────
  - model_name: smart-router
    litellm_params:
      model: azure/gpt-5.2-chat
      api_base: os.environ/AZURE_OPENAI_ENDPOINT
      api_key: os.environ/AZURE_OPENAI_API_KEY
      api_version: "2024-12-01-preview"

  # ── Direct aliases (for targeted calls outside the benchmark) ─────────────
  - model_name: ollama-minimax
    litellm_params:
      model: "ollama/minimax-m2.5:cloud"
      api_base: http://localhost:11434

  - model_name: moonshot-kimi-k2
    litellm_params:
      model: openai/moonshot-v1-auto
      api_base: https://api.moonshot.ai/v1
      api_key: os.environ/MOONSHOT_API_KEY

  - model_name: azure-gpt5
    litellm_params:
      model: azure/gpt-5.2-chat
      api_base: os.environ/AZURE_OPENAI_ENDPOINT
      api_key: os.environ/AZURE_OPENAI_API_KEY
      api_version: "2024-12-01-preview"

router_settings:
  routing_strategy: cost-based-routing
  # Fallback: if smart-router fails on one deployment, try the next
  fallbacks:
    - smart-router:
        - ollama-minimax
        - moonshot-kimi-k2
        - azure-gpt5
  num_retries: 2
  timeout: 90

litellm_settings:
  drop_params: true
  use_responses_api: false
  return_response_headers: true
  success_callback: []
  failure_callback: []

general_settings:
  master_key: sk-1234        # change this
  port: 8082