OrcaRouter runs on your own machine — the client starts it, so there is no endpoint to ping. 103 installs a week from npm. Last commit 26 May 2026.
Browse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.
Today is the operative word: we check OrcaRouter every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add orcarouter-mcp -- npx -y @orcarouter/mcp
{
"mcpServers": {
"orcarouter-mcp": {
"command": "npx",
"args": [
"-y",
"@orcarouter/mcp"
]
}
}
}
[mcp_servers.orcarouter-mcp]
command = "npx"
args = ["-y", "@orcarouter/mcp"]
{
"mcpServers": {
"orcarouter-mcp": {
"command": "npx",
"args": [
"-y",
"@orcarouter/mcp"
]
}
}
}
{
"servers": {
"orcarouter-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@orcarouter/mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ORCAROUTER_API_KEY (OrcaRouter API key. Required only for orcarouter_chat. Catalog tools (orcarouter_models_list, orcarouter_model_card, orcarouter_providers_list) work without it), ORCAROUTER_BASE_URL (Override the gateway base URL. Defaults to https://api.orcarouter.ai), ORCAROUTER_REQUEST_TIMEOUT (Per-request timeout in seconds. Defaults to 300 (5 minutes) to accommodate long reasoning-model completions).
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
Search 200+ UnoRouter models (most free), check pricing, and chat through one key
Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.
MCP server for Groq: fast LLM chat, model list. Needs a free API key.
Pay-per-call LLM API for agents: model catalog, pricing, unpaid x402/MPP quotes, how-to-pay.
Live model catalog with prices and measured uptime, rankings, credits and spend, spend-capped chat.
LLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.
Answers built from our own checks of this server.