Answers cheaply first, then escalates to a premium model only when a checker fails.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional prepaid key as Bearer cf_... for paid limits. Leave empty for the free demo.
Set to 1 to request the x402 payment challenge ($0.005 USDC on Base) instead of the free demo.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Answer a question the Cheap First way: Dolphin answers, SERV Reasoning scores it, and a premium model answers instead only if the score misses the pass mark. Returns the answer, whether it escalated, the check score, the cost and the estimated saving. Free calls use the public demo limits (600 characters, 10 an hour per IP, 300 a day). Send Authorization: Bearer cf_... or an x402 payment of $0.005 USDC on Base for the paid limits (2000 characters). To receive the x402 challenge, send the header X-Cheap-First-Paid: 1. mode: strict escalates more often (pass mark 85), balanced is the default (75), budget escalates less often (60).
The question. 600 characters on the free demo, 2000 when paid.
strict, balanced (default) or budget. Unknown values are treated as balanced.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http cheap-first https://cheap-first.vercel.app/mcp
Headers
Authorization (optional, not in the config above): Optional prepaid key as Bearer cf_... for paid limits. Leave empty for the free demo.X-Cheap-First-Paid (optional, not in the config above): Set to 1 to request the x402 payment challenge ($0.005 USDC on Base) instead of the free demo.Answer a question the Cheap First way: Dolphin answers, SERV Reasoning scores it, and a premium model answers instead only if the score misses the pass mark. Returns the answer, whether it escalated, the check score, the cost and the estimated saving. Free calls use the public demo limits (600 characters, 10 an hour per IP, 300 a day). Send Authorization: Bearer cf_... or an x402 payment of $0.005 USDC on Base for the paid limits (2000 characters). To receive the x402 challenge, send the header X-Cheap-First-Paid: 1. mode: strict escalates more often (pass mark 85), balanced is the default (75), budget escalates less often (60).
| Argument | Type | Description |
|---|---|---|
| mode | string | strict, balanced (default) or budget. Unknown values are treated as balanced. |
| question* | string | The question. 600 characters on the free demo, 2000 when paid. |
{
"type": "object",
"required": [
"question"
],
"properties": {
"mode": {
"enum": [
"strict",
"balanced",
"budget"
],
"type": "string",
"description": "strict, balanced (default) or budget. Unknown values are treated as balanced."
},
"question": {
"type": "string",
"description": "The question. 600 characters on the free demo, 2000 when paid."
}
}
}Published benchmark figures. The main run is 143 questions: what Cheap First spent, what the premium model alone would have cost, how many Dolphin answered, and the average quality scores. Also includes the harder 97-question run. Does not call a model.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.