Llmtest MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 28 installs a week from npm. Last commit 22 May 2026.
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.
Today is the operative word: we check Llmtest MCP 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 llmtest-mcp -e 'LLMTEST_API_KEY=<LLMTEST_API_KEY>' -- npx -y llmtest-mcp
{
"mcpServers": {
"llmtest-mcp": {
"command": "npx",
"args": [
"-y",
"llmtest-mcp"
],
"env": {
"LLMTEST_API_KEY": "<LLMTEST_API_KEY>"
}
}
}
}
[mcp_servers.llmtest-mcp]
command = "npx"
args = ["-y", "llmtest-mcp"]
env = { LLMTEST_API_KEY = "<LLMTEST_API_KEY>" }
{
"mcpServers": {
"llmtest-mcp": {
"command": "npx",
"args": [
"-y",
"llmtest-mcp"
],
"env": {
"LLMTEST_API_KEY": "<LLMTEST_API_KEY>"
}
}
}
}
{
"servers": {
"llmtest-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"llmtest-mcp"
],
"env": {
"LLMTEST_API_KEY": "<LLMTEST_API_KEY>"
}
}
}
}
Put your own value in place of
<LLMTEST_API_KEY> (Your LLMTest API key from https://llmtest.io/dashboard).
The author’s registry entry marks it as required.
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.
Find AI models that fit a job from your requirements, sourced benchmarks and real cost.
Live AI compute pricing oracle — real-time LLM model prices across providers
AI tools ranked by real web traffic, with pricing, free plans, alternatives and LLM API benchmarks.
Search, compare and find alternatives across a directory of AI agents, MCP servers and skills.
Cheapest API for any model across official, inference and relay providers; find free credits
Consistent prompts for one human character across image and video models. Paid per call, x402.
Answers built from our own checks of this server.