Returns the optimal LLM for any task based on real-time pricing, latency, and quality data across 13 models from Anthropic, OpenAI, Google, Meta, Mistral, and DeepSeek. Helps agents reduce costs by routing to the cheapest capable model. $0.01/query via x402 (Solana USDC). Free health and discovery endpoints.
Server Config
{
"mcpServers": {
"getkin-model-oracle": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://getkin-api.fly.dev/mcp/tools"
]
}
}
}