Cheaplane runs on your own machine — the client starts it, so there is no endpoint to ping. 55 installs a week from pypi. Last commit 16 Aug 2026.
Offload grunt work from your premium agent to cheap models — auto-routing and billing isolation.
Today is the operative word: we check Cheaplane 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 cheaplane -- uvx cheaplane
{
"mcpServers": {
"cheaplane": {
"command": "uvx",
"args": [
"cheaplane"
]
}
}
}
[mcp_servers.cheaplane]
command = "uvx"
args = ["cheaplane"]
{
"mcpServers": {
"cheaplane": {
"command": "uvx",
"args": [
"cheaplane"
]
}
}
}
{
"servers": {
"cheaplane": {
"type": "stdio",
"command": "uvx",
"args": [
"cheaplane"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
DELEGATE_BASE_URL (OpenAI-compatible endpoint serving the cheap models — usually a local LiteLLM proxy), DELEGATE_API_KEY (Key for that endpoint. A local proxy ignores it; set a real one for a hosted endpoint), DELEGATE_TIMEOUT (Per-call timeout in seconds. Raise it for long documents), DELEGATE_MODEL_MAP (JSON remapping the built-in aliases to your proxy's model names, e.g. {"deepseek": "deepseek-v4"}), DELEGATE_NO_LOG (Set to 1 to disable the local savings ledger (metadata only, never task content)).
Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
Model routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.
Plan agent workload routes from evaluation and cost data. $1 USDC per plan; modeled savings only.
Build and run visual creative-production workflows from your AI agent.
Write, validate, deploy and run TypeScript workflow automations on Whenever from your coding agent.
Upload, publish and embed 3D models on any website from your agent.
Run Wiro AI models, build and run workflows, and talk to Studio and your Wiro agents.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Answers built from our own checks of this server.